| 92 92 92 1 50 49 1 1 49 1 1 1 50 39 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Socket Closing - normal and abnormal * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/workqueue.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/tcp.h> #include "smc.h" #include "smc_tx.h" #include "smc_cdc.h" #include "smc_close.h" /* release the clcsock that is assigned to the smc_sock */ void smc_clcsock_release(struct smc_sock *smc) { struct socket *tcp; if (smc->listen_smc && current_work() != &smc->smc_listen_work) cancel_work_sync(&smc->smc_listen_work); mutex_lock(&smc->clcsock_release_lock); if (smc->clcsock) { tcp = smc->clcsock; smc->clcsock = NULL; sock_release(tcp); } mutex_unlock(&smc->clcsock_release_lock); } static void smc_close_cleanup_listen(struct sock *parent) { struct sock *sk; /* Close non-accepted connections */ while ((sk = smc_accept_dequeue(parent, NULL))) smc_close_non_accepted(sk); } /* wait for sndbuf data being transmitted */ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = &smc->sk; if (!timeout) return; if (!smc_tx_prepared_sends(&smc->conn)) return; /* Send out corked data remaining in sndbuf */ smc_tx_pending(&smc->conn); smc->wait_close_tx_prepared = 1; add_wait_queue(sk_sleep(sk), &wait); while (!signal_pending(current) && timeout) { int rc; rc = sk_wait_event(sk, &timeout, !smc_tx_prepared_sends(&smc->conn) || READ_ONCE(sk->sk_err) == ECONNABORTED || READ_ONCE(sk->sk_err) == ECONNRESET || smc->conn.killed, &wait); if (rc) break; } remove_wait_queue(sk_sleep(sk), &wait); smc->wait_close_tx_prepared = 0; } void smc_close_wake_tx_prepared(struct smc_sock *smc) { if (smc->wait_close_tx_prepared) /* wake up socket closing */ smc->sk.sk_state_change(&smc->sk); } static int smc_close_wr(struct smc_connection *conn) { conn->local_tx_ctrl.conn_state_flags.peer_done_writing = 1; return smc_cdc_get_slot_and_msg_send(conn); } static int smc_close_final(struct smc_connection *conn) { if (atomic_read(&conn->bytes_to_rcv)) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; else conn->local_tx_ctrl.conn_state_flags.peer_conn_closed = 1; if (conn->killed) return -EPIPE; return smc_cdc_get_slot_and_msg_send(conn); } int smc_close_abort(struct smc_connection *conn) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; return smc_cdc_get_slot_and_msg_send(conn); } static void smc_close_cancel_work(struct smc_sock *smc) { struct sock *sk = &smc->sk; release_sock(sk); if (cancel_work_sync(&smc->conn.close_work)) sock_put(sk); cancel_delayed_work_sync(&smc->conn.tx_work); lock_sock(sk); } /* terminate smc socket abnormally - active abort * link group is terminated, i.e. RDMA communication no longer possible */ void smc_close_active_abort(struct smc_sock *smc) { struct sock *sk = &smc->sk; bool release_clcsock = false; if (sk->sk_state != SMC_INIT && smc->clcsock && smc->clcsock->sk) { sk->sk_err = ECONNABORTED; if (smc->clcsock && smc->clcsock->sk) tcp_abort(smc->clcsock->sk, ECONNABORTED); } switch (sk->sk_state) { case SMC_ACTIVE: case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); if (sk->sk_state != SMC_PEERABORTWAIT) break; sk->sk_state = SMC_CLOSED; sock_put(sk); /* (postponed) passive closing */ break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); if (sk->sk_state != SMC_PEERABORTWAIT) break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; sock_put(sk); /* passive closing */ break; case SMC_PROCESSABORT: case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); if (sk->sk_state != SMC_PEERABORTWAIT) break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; break; case SMC_INIT: case SMC_PEERABORTWAIT: case SMC_CLOSED: break; } smc_sock_set_flag(sk, SOCK_DEAD); sk->sk_state_change(sk); if (release_clcsock) { release_sock(sk); smc_clcsock_release(smc); lock_sock(sk); } } static inline bool smc_close_sent_any_close(struct smc_connection *conn) { return conn->local_tx_ctrl.conn_state_flags.peer_conn_abort || conn->local_tx_ctrl.conn_state_flags.peer_conn_closed; } int smc_close_active(struct smc_sock *smc) { struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int old_state; long timeout; int rc = 0; int rc1 = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT; old_state = sk->sk_state; again: switch (sk->sk_state) { case SMC_INIT: sk->sk_state = SMC_CLOSED; break; case SMC_LISTEN: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); release_sock(sk); flush_work(&smc->tcp_listen_work); lock_sock(sk); break; case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state == SMC_ACTIVE) { /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; /* actively shutdown clcsock before peer close it, * prevent peer from entering TIME_WAIT state. */ if (smc->clcsock && smc->clcsock->sk) { rc1 = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); rc = rc ? rc : rc1; } } else { /* peer event has changed the state */ goto again; } break; case SMC_APPFINCLOSEWAIT: /* socket already shutdown wr or both (active close) */ if (txflags->peer_done_writing && !smc_close_sent_any_close(conn)) { /* just shutdown wr done, send close request */ rc = smc_close_final(conn); } sk->sk_state = SMC_CLOSED; break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: if (!smc_cdc_rxed_any_close(conn)) smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state != SMC_APPCLOSEWAIT1 && sk->sk_state != SMC_APPCLOSEWAIT2) goto again; /* confirm close from peer */ rc = smc_close_final(conn); if (smc_cdc_rxed_any_close(conn)) { /* peer has closed the socket already */ sk->sk_state = SMC_CLOSED; sock_put(sk); /* postponed passive closing */ } else { /* peer has just issued a shutdown write */ sk->sk_state = SMC_PEERFINCLOSEWAIT; } break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: if (txflags->peer_done_writing && !smc_close_sent_any_close(conn)) { /* just shutdown wr done, send close request */ rc = smc_close_final(conn); } /* peer sending PeerConnectionClosed will cause transition */ break; case SMC_PEERFINCLOSEWAIT: /* peer sending PeerConnectionClosed will cause transition */ break; case SMC_PROCESSABORT: rc = smc_close_abort(conn); sk->sk_state = SMC_CLOSED; break; case SMC_PEERABORTWAIT: sk->sk_state = SMC_CLOSED; break; case SMC_CLOSED: /* nothing to do, add tracing in future patch */ break; } if (old_state != sk->sk_state) sk->sk_state_change(sk); return rc; } static void smc_close_passive_abort_received(struct smc_sock *smc) { struct smc_cdc_conn_state_flags *txflags = &smc->conn.local_tx_ctrl.conn_state_flags; struct sock *sk = &smc->sk; switch (sk->sk_state) { case SMC_INIT: case SMC_ACTIVE: case SMC_APPCLOSEWAIT1: sk->sk_state = SMC_PROCESSABORT; sock_put(sk); /* passive closing */ break; case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PROCESSABORT; break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: if (txflags->peer_done_writing && !smc_close_sent_any_close(&smc->conn)) /* just shutdown, but not yet closed locally */ sk->sk_state = SMC_PROCESSABORT; else sk->sk_state = SMC_CLOSED; sock_put(sk); /* passive closing */ break; case SMC_APPCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_CLOSED; sock_put(sk); /* passive closing */ break; case SMC_PEERABORTWAIT: sk->sk_state = SMC_CLOSED; break; case SMC_PROCESSABORT: /* nothing to do, add tracing in future patch */ break; } } /* Either some kind of closing has been received: peer_conn_closed, * peer_conn_abort, or peer_done_writing * or the link group of the connection terminates abnormally. */ static void smc_close_passive_work(struct work_struct *work) { struct smc_connection *conn = container_of(work, struct smc_connection, close_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_cdc_conn_state_flags *rxflags; bool release_clcsock = false; struct sock *sk = &smc->sk; int old_state; lock_sock(sk); old_state = sk->sk_state; rxflags = &conn->local_rx_ctrl.conn_state_flags; if (rxflags->peer_conn_abort) { /* peer has not received all data */ smc_close_passive_abort_received(smc); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); goto wakeup; } switch (sk->sk_state) { case SMC_INIT: sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; /* postpone sock_put() for passive closing to cover * received SEND_SHUTDOWN as well */ break; case SMC_PEERCLOSEWAIT1: if (rxflags->peer_done_writing) sk->sk_state = SMC_PEERCLOSEWAIT2; fallthrough; /* to check for closing */ case SMC_PEERCLOSEWAIT2: if (!smc_cdc_rxed_any_close(conn)) break; if (sock_flag(sk, SOCK_DEAD) && smc_close_sent_any_close(conn)) { /* smc_release has already been called locally */ sk->sk_state = SMC_CLOSED; } else { /* just shutdown, but not yet closed locally */ sk->sk_state = SMC_APPFINCLOSEWAIT; } sock_put(sk); /* passive closing */ break; case SMC_PEERFINCLOSEWAIT: if (smc_cdc_rxed_any_close(conn)) { sk->sk_state = SMC_CLOSED; sock_put(sk); /* passive closing */ } break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: /* postpone sock_put() for passive closing to cover * received SEND_SHUTDOWN as well */ break; case SMC_APPFINCLOSEWAIT: case SMC_PEERABORTWAIT: case SMC_PROCESSABORT: case SMC_CLOSED: /* nothing to do, add tracing in future patch */ break; } wakeup: sk->sk_data_ready(sk); /* wakeup blocked rcvbuf consumers */ sk->sk_write_space(sk); /* wakeup blocked sndbuf producers */ if (old_state != sk->sk_state) { sk->sk_state_change(sk); if ((sk->sk_state == SMC_CLOSED) && (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); if (smc->clcsock) release_clcsock = true; } } release_sock(sk); if (release_clcsock) smc_clcsock_release(smc); sock_put(sk); /* sock_hold done by schedulers of close_work */ } int smc_close_shutdown_write(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int old_state; long timeout; int rc = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT; old_state = sk->sk_state; again: switch (sk->sk_state) { case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state != SMC_ACTIVE) goto again; /* send close wr request */ rc = smc_close_wr(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; break; case SMC_APPCLOSEWAIT1: /* passive close */ if (!smc_cdc_rxed_any_close(conn)) smc_close_stream_wait(smc, timeout); release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); lock_sock(sk); if (sk->sk_state != SMC_APPCLOSEWAIT1) goto again; /* confirm close from peer */ rc = smc_close_wr(conn); sk->sk_state = SMC_APPCLOSEWAIT2; break; case SMC_APPCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_APPFINCLOSEWAIT: case SMC_PROCESSABORT: case SMC_PEERABORTWAIT: /* nothing to do, add tracing in future patch */ break; } if (old_state != sk->sk_state) sk->sk_state_change(sk); return rc; } /* Initialize close properties on connection establishment. */ void smc_close_init(struct smc_sock *smc) { INIT_WORK(&smc->conn.close_work, smc_close_passive_work); } |
| 5808 5889 5883 5894 5837 4187 4179 10 2 2 1 1 10 13 8 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | #include <linux/bpf.h> #include <linux/vmalloc.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/namei.h> #include <linux/user_namespace.h> #include <linux/security.h> static bool bpf_ns_capable(struct user_namespace *ns, int cap) { return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); } bool bpf_token_capable(const struct bpf_token *token, int cap) { struct user_namespace *userns; /* BPF token allows ns_capable() level of capabilities */ userns = token ? token->userns : &init_user_ns; if (!bpf_ns_capable(userns, cap)) return false; if (token && security_bpf_token_capable(token, cap) < 0) return false; return true; } void bpf_token_inc(struct bpf_token *token) { atomic64_inc(&token->refcnt); } static void bpf_token_free(struct bpf_token *token) { security_bpf_token_free(token); put_user_ns(token->userns); kfree(token); } static void bpf_token_put_deferred(struct work_struct *work) { struct bpf_token *token = container_of(work, struct bpf_token, work); bpf_token_free(token); } void bpf_token_put(struct bpf_token *token) { if (!token) return; if (!atomic64_dec_and_test(&token->refcnt)) return; INIT_WORK(&token->work, bpf_token_put_deferred); schedule_work(&token->work); } static int bpf_token_release(struct inode *inode, struct file *filp) { struct bpf_token *token = filp->private_data; bpf_token_put(token); return 0; } static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_token *token = filp->private_data; u64 mask; BUILD_BUG_ON(__MAX_BPF_CMD >= 64); mask = BIT_ULL(__MAX_BPF_CMD) - 1; if ((token->allowed_cmds & mask) == mask) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; if ((token->allowed_maps & mask) == mask) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; if ((token->allowed_progs & mask) == mask) seq_printf(m, "allowed_progs:\tany\n"); else seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; if ((token->allowed_attachs & mask) == mask) seq_printf(m, "allowed_attachs:\tany\n"); else seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" static const struct inode_operations bpf_token_iops = { }; static const struct file_operations bpf_token_fops = { .release = bpf_token_release, .show_fdinfo = bpf_token_show_fdinfo, }; int bpf_token_create(union bpf_attr *attr) { struct bpf_mount_opts *mnt_opts; struct bpf_token *token = NULL; struct user_namespace *userns; struct inode *inode; struct file *file; CLASS(fd, f)(attr->token_create.bpffs_fd); struct path path; struct super_block *sb; umode_t mode; int err, fd; if (fd_empty(f)) return -EBADF; path = fd_file(f)->f_path; sb = path.dentry->d_sb; if (path.dentry != sb->s_root) return -EINVAL; if (sb->s_op != &bpf_super_ops) return -EINVAL; err = path_permission(&path, MAY_ACCESS); if (err) return err; userns = sb->s_user_ns; /* * Enforce that creators of BPF tokens are in the same user * namespace as the BPF FS instance. This makes reasoning about * permissions a lot easier and we can always relax this later. */ if (current_user_ns() != userns) return -EPERM; if (!ns_capable(userns, CAP_BPF)) return -EPERM; /* Creating BPF token in init_user_ns doesn't make much sense. */ if (current_user_ns() == &init_user_ns) return -EOPNOTSUPP; mnt_opts = sb->s_fs_info; if (mnt_opts->delegate_cmds == 0 && mnt_opts->delegate_maps == 0 && mnt_opts->delegate_progs == 0 && mnt_opts->delegate_attachs == 0) return -ENOENT; /* no BPF token delegation is set up */ mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); inode = bpf_get_inode(sb, NULL, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &bpf_token_iops; inode->i_fop = &bpf_token_fops; clear_nlink(inode); /* make sure it is unlinked */ file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); if (IS_ERR(file)) { iput(inode); return PTR_ERR(file); } token = kzalloc(sizeof(*token), GFP_USER); if (!token) { err = -ENOMEM; goto out_file; } atomic64_set(&token->refcnt, 1); /* remember bpffs owning userns for future ns_capable() checks */ token->userns = get_user_ns(userns); token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; token->allowed_progs = mnt_opts->delegate_progs; token->allowed_attachs = mnt_opts->delegate_attachs; err = security_bpf_token_create(token, attr, &path); if (err) goto out_token; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; goto out_token; } file->private_data = token; fd_install(fd, file); return fd; out_token: bpf_token_free(token); out_file: fput(file); return err; } struct bpf_token *bpf_token_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_token *token; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_token_fops) return ERR_PTR(-EINVAL); token = fd_file(f)->private_data; bpf_token_inc(token); return token; } bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; if (!(token->allowed_cmds & BIT_ULL(cmd))) return false; return security_bpf_token_cmd(token, cmd) == 0; } bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) { if (!token || type >= __MAX_BPF_MAP_TYPE) return false; return token->allowed_maps & BIT_ULL(type); } bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type) { if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) return false; return (token->allowed_progs & BIT_ULL(prog_type)) && (token->allowed_attachs & BIT_ULL(attach_type)); } |
| 6825 852 485 6720 551 551 552 550 552 551 552 23776 548 24 3764 23786 78 23786 24494 24442 24488 13987 14022 6826 6719 552 551 393 160 551 17535 190 17563 556 559 559 17540 190 559 17 17526 | 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 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" #include "services.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[] __counted_by(len); }; #define index_to_sid(index) ((index) + SECINITSID_NUM + 1) #define sid_to_index(sid) ((sid) - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_equal(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { unsigned int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; unsigned int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc( SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ convert = s->convert; if (convert) { struct sidtab *target = convert->target; rc = -ENOMEM; dst_convert = sidtab_do_lookup(target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = services_convert_context(convert->args, context, &dst_convert->context, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); target->count = count + 1; hash_add_rcu(target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = services_convert_context( convert->args, &esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, GFP_KERNEL); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(struct_size(cache, str, str_len), GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 5 1 5 2 5 4 4 4 4 5 5 5 3 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS: Weighted Round-Robin Scheduling module * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Changes: * Wensong Zhang : changed the ip_vs_wrr_schedule to return dest * Wensong Zhang : changed some comestics things for debugging * Wensong Zhang : changed for the d-linked destination list * Wensong Zhang : added the ip_vs_wrr_update_svc * Julian Anastasov : fixed the bug of returning destination * with weight 0 when all weights are zero */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/gcd.h> #include <net/ip_vs.h> /* The WRR algorithm depends on some caclulations: * - mw: maximum weight * - di: weight step, greatest common divisor from all weights * - cw: current required weight * As result, all weights are in the [di..mw] range with a step=di. * * First, we start with cw = mw and select dests with weight >= cw. * Then cw is reduced with di and all dests are checked again. * Last pass should be with cw = di. We have mw/di passes in total: * * pass 1: cw = max weight * pass 2: cw = max weight - di * pass 3: cw = max weight - 2 * di * ... * last pass: cw = di * * Weights are supposed to be >= di but we run in parallel with * weight changes, it is possible some dest weight to be reduced * below di, bad if it is the only available dest. * * So, we modify how mw is calculated, now it is reduced with (di - 1), * so that last cw is 1 to catch such dests with weight below di: * pass 1: cw = max weight - (di - 1) * pass 2: cw = max weight - di - (di - 1) * pass 3: cw = max weight - 2 * di - (di - 1) * ... * last pass: cw = 1 * */ /* * current destination pointer for weighted round-robin scheduling */ struct ip_vs_wrr_mark { struct ip_vs_dest *cl; /* current dest or head */ int cw; /* current weight */ int mw; /* maximum weight */ int di; /* decreasing interval */ struct rcu_head rcu_head; }; static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; int weight; int g = 0; list_for_each_entry(dest, &svc->destinations, n_list) { weight = atomic_read(&dest->weight); if (weight > 0) { if (g > 0) g = gcd(weight, g); else g = weight; } } return g ? g : 1; } /* * Get the maximum weight of the service destinations. */ static int ip_vs_wrr_max_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; int new_weight, weight = 0; list_for_each_entry(dest, &svc->destinations, n_list) { new_weight = atomic_read(&dest->weight); if (new_weight > weight) weight = new_weight; } return weight; } static int ip_vs_wrr_init_svc(struct ip_vs_service *svc) { struct ip_vs_wrr_mark *mark; /* * Allocate the mark variable for WRR scheduling */ mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_KERNEL); if (mark == NULL) return -ENOMEM; mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list); mark->di = ip_vs_wrr_gcd_weight(svc); mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1); mark->cw = mark->mw; svc->sched_data = mark; return 0; } static void ip_vs_wrr_done_svc(struct ip_vs_service *svc) { struct ip_vs_wrr_mark *mark = svc->sched_data; /* * Release the mark variable */ kfree_rcu(mark, rcu_head); } static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc, struct ip_vs_dest *dest) { struct ip_vs_wrr_mark *mark = svc->sched_data; spin_lock_bh(&svc->sched_lock); mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list); mark->di = ip_vs_wrr_gcd_weight(svc); mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1); if (mark->cw > mark->mw || !mark->cw) mark->cw = mark->mw; else if (mark->di > 1) mark->cw = (mark->cw / mark->di) * mark->di + 1; spin_unlock_bh(&svc->sched_lock); return 0; } /* * Weighted Round-Robin Scheduling */ static struct ip_vs_dest * ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *last, *stop = NULL; struct ip_vs_wrr_mark *mark = svc->sched_data; bool last_pass = false, restarted = false; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); spin_lock_bh(&svc->sched_lock); dest = mark->cl; /* No available dests? */ if (mark->mw == 0) goto err_noavail; last = dest; /* Stop only after all dests were checked for weight >= 1 (last pass) */ while (1) { list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) { if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) && atomic_read(&dest->weight) >= mark->cw) goto found; if (dest == stop) goto err_over; } mark->cw -= mark->di; if (mark->cw <= 0) { mark->cw = mark->mw; /* Stop if we tried last pass from first dest: * 1. last_pass: we started checks when cw > di but * then all dests were checked for w >= 1 * 2. last was head: the first and only traversal * was for weight >= 1, for all dests. */ if (last_pass || &last->n_list == &svc->destinations) goto err_over; restarted = true; } last_pass = mark->cw <= mark->di; if (last_pass && restarted && &last->n_list != &svc->destinations) { /* First traversal was for w >= 1 but only * for dests after 'last', now do the same * for all dests up to 'last'. */ stop = last; } } found: IP_VS_DBG_BUF(6, "WRR: server %s:%u " "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), refcount_read(&dest->refcnt), atomic_read(&dest->weight)); mark->cl = dest; out: spin_unlock_bh(&svc->sched_lock); return dest; err_noavail: mark->cl = dest; dest = NULL; ip_vs_scheduler_err(svc, "no destination available"); goto out; err_over: mark->cl = dest; dest = NULL; ip_vs_scheduler_err(svc, "no destination available: " "all destinations are overloaded"); goto out; } static struct ip_vs_scheduler ip_vs_wrr_scheduler = { .name = "wrr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list), .init_service = ip_vs_wrr_init_svc, .done_service = ip_vs_wrr_done_svc, .add_dest = ip_vs_wrr_dest_changed, .del_dest = ip_vs_wrr_dest_changed, .upd_dest = ip_vs_wrr_dest_changed, .schedule = ip_vs_wrr_schedule, }; static int __init ip_vs_wrr_init(void) { return register_ip_vs_scheduler(&ip_vs_wrr_scheduler) ; } static void __exit ip_vs_wrr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_wrr_scheduler); synchronize_rcu(); } module_init(ip_vs_wrr_init); module_exit(ip_vs_wrr_cleanup); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ipvs weighted round-robin scheduler"); |
| 962 963 1005 963 976 29 51 51 51 51 1061 1007 907 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 9P entry point * * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/kmod.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/moduleparam.h> #include <net/9p/9p.h> #include <linux/fs.h> #include <linux/parser.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include <linux/list.h> #include <linux/spinlock.h> #ifdef CONFIG_NET_9P_DEBUG unsigned int p9_debug_level; /* feature-rific global debug level */ EXPORT_SYMBOL(p9_debug_level); module_param_named(debug, p9_debug_level, uint, 0); MODULE_PARM_DESC(debug, "9P debugging level"); void _p9_debug(enum p9_debug_flags level, const char *func, const char *fmt, ...) { struct va_format vaf; va_list args; if ((p9_debug_level & level) != level) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (level == P9_DEBUG_9P) pr_notice("(%8.8d) %pV", task_pid_nr(current), &vaf); else pr_notice("-- %s (%d): %pV", func, task_pid_nr(current), &vaf); va_end(args); } EXPORT_SYMBOL(_p9_debug); #endif /* Dynamic Transport Registration Routines */ static DEFINE_SPINLOCK(v9fs_trans_lock); static LIST_HEAD(v9fs_trans_list); /** * v9fs_register_trans - register a new transport with 9p * @m: structure describing the transport module and entry points * */ void v9fs_register_trans(struct p9_trans_module *m) { spin_lock(&v9fs_trans_lock); list_add_tail(&m->list, &v9fs_trans_list); spin_unlock(&v9fs_trans_lock); } EXPORT_SYMBOL(v9fs_register_trans); /** * v9fs_unregister_trans - unregister a 9p transport * @m: the transport to remove * */ void v9fs_unregister_trans(struct p9_trans_module *m) { spin_lock(&v9fs_trans_lock); list_del_init(&m->list); spin_unlock(&v9fs_trans_lock); } EXPORT_SYMBOL(v9fs_unregister_trans); static struct p9_trans_module *_p9_get_trans_by_name(const char *s) { struct p9_trans_module *t, *found = NULL; spin_lock(&v9fs_trans_lock); list_for_each_entry(t, &v9fs_trans_list, list) if (strcmp(t->name, s) == 0 && try_module_get(t->owner)) { found = t; break; } spin_unlock(&v9fs_trans_lock); return found; } /** * v9fs_get_trans_by_name - get transport with the matching name * @s: string identifying transport * */ struct p9_trans_module *v9fs_get_trans_by_name(const char *s) { struct p9_trans_module *found = NULL; found = _p9_get_trans_by_name(s); #ifdef CONFIG_MODULES if (!found) { request_module("9p-%s", s); found = _p9_get_trans_by_name(s); } #endif return found; } EXPORT_SYMBOL(v9fs_get_trans_by_name); static const char * const v9fs_default_transports[] = { "virtio", "tcp", "fd", "unix", "xen", "rdma", }; /** * v9fs_get_default_trans - get the default transport * */ struct p9_trans_module *v9fs_get_default_trans(void) { struct p9_trans_module *t, *found = NULL; int i; spin_lock(&v9fs_trans_lock); list_for_each_entry(t, &v9fs_trans_list, list) if (t->def && try_module_get(t->owner)) { found = t; break; } if (!found) list_for_each_entry(t, &v9fs_trans_list, list) if (try_module_get(t->owner)) { found = t; break; } spin_unlock(&v9fs_trans_lock); for (i = 0; !found && i < ARRAY_SIZE(v9fs_default_transports); i++) found = v9fs_get_trans_by_name(v9fs_default_transports[i]); return found; } EXPORT_SYMBOL(v9fs_get_default_trans); /** * v9fs_put_trans - put trans * @m: transport to put * */ void v9fs_put_trans(struct p9_trans_module *m) { if (m) module_put(m->owner); } /** * init_p9 - Initialize module * */ static int __init init_p9(void) { int ret; ret = p9_client_init(); if (ret) return ret; p9_error_init(); pr_info("Installing 9P2000 support\n"); return ret; } /** * exit_p9 - shutdown module * */ static void __exit exit_p9(void) { pr_info("Unloading 9P2000 support\n"); p9_client_exit(); } module_init(init_p9) module_exit(exit_p9) MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>"); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Plan 9 Resource Sharing Support (9P2000)"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Public Key Signature Algorithm * * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/sig.h> #include <linux/cryptouser.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/string.h> #include <net/netlink.h> #include "internal.h" static void crypto_sig_exit_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); struct sig_alg *alg = crypto_sig_alg(sig); alg->exit(sig); } static int crypto_sig_init_tfm(struct crypto_tfm *tfm) { struct crypto_sig *sig = __crypto_sig_tfm(tfm); struct sig_alg *alg = crypto_sig_alg(sig); if (alg->exit) sig->base.exit = crypto_sig_exit_tfm; if (alg->init) return alg->init(sig); return 0; } static void crypto_sig_free_instance(struct crypto_instance *inst) { struct sig_instance *sig = sig_instance(inst); sig->free(sig); } static void __maybe_unused crypto_sig_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : sig\n"); } static int __maybe_unused crypto_sig_report(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_sig rsig = {}; strscpy(rsig.type, "sig", sizeof(rsig.type)); return nla_put(skb, CRYPTOCFGA_REPORT_SIG, sizeof(rsig), &rsig); } static const struct crypto_type crypto_sig_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_sig_init_tfm, .free = crypto_sig_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_sig_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_sig_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SIG, .tfmsize = offsetof(struct crypto_sig, base), }; struct crypto_sig *crypto_alloc_sig(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_sig_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_sig); static int sig_default_sign(struct crypto_sig *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { return -ENOSYS; } static int sig_default_verify(struct crypto_sig *tfm, const void *src, unsigned int slen, const void *dst, unsigned int dlen) { return -ENOSYS; } static int sig_default_set_key(struct crypto_sig *tfm, const void *key, unsigned int keylen) { return -ENOSYS; } static int sig_prepare_alg(struct sig_alg *alg) { struct crypto_alg *base = &alg->base; if (!alg->sign) alg->sign = sig_default_sign; if (!alg->verify) alg->verify = sig_default_verify; if (!alg->set_priv_key) alg->set_priv_key = sig_default_set_key; if (!alg->set_pub_key) return -EINVAL; if (!alg->key_size) return -EINVAL; if (!alg->max_size) alg->max_size = alg->key_size; if (!alg->digest_size) alg->digest_size = alg->key_size; base->cra_type = &crypto_sig_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_SIG; return 0; } int crypto_register_sig(struct sig_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = sig_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_sig); void crypto_unregister_sig(struct sig_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_sig); int sig_register_instance(struct crypto_template *tmpl, struct sig_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = sig_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, sig_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(sig_register_instance); int crypto_grab_sig(struct crypto_sig_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_sig_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_sig); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Public Key Signature Algorithms"); |
| 21 13 | 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 | /* * DRBG based on NIST SP800-90A * * Copyright Stephan Mueller <smueller@chronox.de>, 2014 * * 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, and the entire permission notice in its entirety, * including the disclaimer of warranties. * 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. The name of the author may not be used to endorse or promote * products derived from this software without specific prior * written permission. * * ALTERNATIVELY, this product may be distributed under the terms of * the GNU General Public License, in which case the provisions of the GPL are * required INSTEAD OF the above restrictions. (This clause is * necessary due to a potential bad interaction between the GPL and * the restrictions contained in a BSD-style copyright.) * * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF * WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR 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 NOT ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. */ #ifndef _DRBG_H #define _DRBG_H #include <linux/random.h> #include <linux/scatterlist.h> #include <crypto/hash.h> #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/crypto.h> #include <linux/slab.h> #include <crypto/internal/rng.h> #include <crypto/rng.h> #include <linux/fips.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/workqueue.h> /* * Concatenation Helper and string operation helper * * SP800-90A requires the concatenation of different data. To avoid copying * buffers around or allocate additional memory, the following data structure * is used to point to the original memory with its size. In addition, it * is used to build a linked list. The linked list defines the concatenation * of individual buffers. The order of memory block referenced in that * linked list determines the order of concatenation. */ struct drbg_string { const unsigned char *buf; size_t len; struct list_head list; }; static inline void drbg_string_fill(struct drbg_string *string, const unsigned char *buf, size_t len) { string->buf = buf; string->len = len; INIT_LIST_HEAD(&string->list); } struct drbg_state; typedef uint32_t drbg_flag_t; struct drbg_core { drbg_flag_t flags; /* flags for the cipher */ __u8 statelen; /* maximum state length */ __u8 blocklen_bytes; /* block size of output in bytes */ char cra_name[CRYPTO_MAX_ALG_NAME]; /* mapping to kernel crypto API */ /* kernel crypto API backend cipher name */ char backend_cra_name[CRYPTO_MAX_ALG_NAME]; }; struct drbg_state_ops { int (*update)(struct drbg_state *drbg, struct list_head *seed, int reseed); int (*generate)(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen, struct list_head *addtl); int (*crypto_init)(struct drbg_state *drbg); int (*crypto_fini)(struct drbg_state *drbg); }; struct drbg_test_data { struct drbg_string *testentropy; /* TEST PARAMETER: test entropy */ }; enum drbg_seed_state { DRBG_SEED_STATE_UNSEEDED, DRBG_SEED_STATE_PARTIAL, /* Seeded with !rng_is_initialized() */ DRBG_SEED_STATE_FULL, }; struct drbg_state { struct mutex drbg_mutex; /* lock around DRBG */ unsigned char *V; /* internal state 10.1.1.1 1a) */ unsigned char *Vbuf; /* hash: static value 10.1.1.1 1b) hmac / ctr: key */ unsigned char *C; unsigned char *Cbuf; /* Number of RNG requests since last reseed -- 10.1.1.1 1c) */ size_t reseed_ctr; size_t reseed_threshold; /* some memory the DRBG can use for its operation */ unsigned char *scratchpad; unsigned char *scratchpadbuf; void *priv_data; /* Cipher handle */ struct crypto_skcipher *ctr_handle; /* CTR mode cipher handle */ struct skcipher_request *ctr_req; /* CTR mode request handle */ __u8 *outscratchpadbuf; /* CTR mode output scratchpad */ __u8 *outscratchpad; /* CTR mode aligned outbuf */ struct crypto_wait ctr_wait; /* CTR mode async wait obj */ struct scatterlist sg_in, sg_out; /* CTR mode SGLs */ enum drbg_seed_state seeded; /* DRBG fully seeded? */ unsigned long last_seed_time; bool pr; /* Prediction resistance enabled? */ bool fips_primed; /* Continuous test primed? */ unsigned char *prev; /* FIPS 140-2 continuous test value */ struct crypto_rng *jent; const struct drbg_state_ops *d_ops; const struct drbg_core *core; struct drbg_string test_data; }; static inline __u8 drbg_statelen(struct drbg_state *drbg) { if (drbg && drbg->core) return drbg->core->statelen; return 0; } static inline __u8 drbg_blocklen(struct drbg_state *drbg) { if (drbg && drbg->core) return drbg->core->blocklen_bytes; return 0; } static inline __u8 drbg_keylen(struct drbg_state *drbg) { if (drbg && drbg->core) return (drbg->core->statelen - drbg->core->blocklen_bytes); return 0; } static inline size_t drbg_max_request_bytes(struct drbg_state *drbg) { /* SP800-90A requires the limit 2**19 bits, but we return bytes */ return (1 << 16); } static inline size_t drbg_max_addtl(struct drbg_state *drbg) { /* SP800-90A requires 2**35 bytes additional info str / pers str */ #if (__BITS_PER_LONG == 32) /* * SP800-90A allows smaller maximum numbers to be returned -- we * return SIZE_MAX - 1 to allow the verification of the enforcement * of this value in drbg_healthcheck_sanity. */ return (SIZE_MAX - 1); #else return (1UL<<35); #endif } static inline size_t drbg_max_requests(struct drbg_state *drbg) { /* SP800-90A requires 2**48 maximum requests before reseeding */ return (1<<20); } /* * This is a wrapper to the kernel crypto API function of * crypto_rng_generate() to allow the caller to provide additional data. * * @drng DRBG handle -- see crypto_rng_get_bytes * @outbuf output buffer -- see crypto_rng_get_bytes * @outlen length of output buffer -- see crypto_rng_get_bytes * @addtl_input additional information string input buffer * @addtllen length of additional information string buffer * * return * see crypto_rng_get_bytes */ static inline int crypto_drbg_get_bytes_addtl(struct crypto_rng *drng, unsigned char *outbuf, unsigned int outlen, struct drbg_string *addtl) { return crypto_rng_generate(drng, addtl->buf, addtl->len, outbuf, outlen); } /* * TEST code * * This is a wrapper to the kernel crypto API function of * crypto_rng_generate() to allow the caller to provide additional data and * allow furnishing of test_data * * @drng DRBG handle -- see crypto_rng_get_bytes * @outbuf output buffer -- see crypto_rng_get_bytes * @outlen length of output buffer -- see crypto_rng_get_bytes * @addtl_input additional information string input buffer * @addtllen length of additional information string buffer * @test_data filled test data * * return * see crypto_rng_get_bytes */ static inline int crypto_drbg_get_bytes_addtl_test(struct crypto_rng *drng, unsigned char *outbuf, unsigned int outlen, struct drbg_string *addtl, struct drbg_test_data *test_data) { crypto_rng_set_entropy(drng, test_data->testentropy->buf, test_data->testentropy->len); return crypto_rng_generate(drng, addtl->buf, addtl->len, outbuf, outlen); } /* * TEST code * * This is a wrapper to the kernel crypto API function of * crypto_rng_reset() to allow the caller to provide test_data * * @drng DRBG handle -- see crypto_rng_reset * @pers personalization string input buffer * @perslen length of additional information string buffer * @test_data filled test data * * return * see crypto_rng_reset */ static inline int crypto_drbg_reset_test(struct crypto_rng *drng, struct drbg_string *pers, struct drbg_test_data *test_data) { crypto_rng_set_entropy(drng, test_data->testentropy->buf, test_data->testentropy->len); return crypto_rng_reset(drng, pers->buf, pers->len); } /* DRBG type flags */ #define DRBG_CTR ((drbg_flag_t)1<<0) #define DRBG_HMAC ((drbg_flag_t)1<<1) #define DRBG_HASH ((drbg_flag_t)1<<2) #define DRBG_TYPE_MASK (DRBG_CTR | DRBG_HMAC | DRBG_HASH) /* DRBG strength flags */ #define DRBG_STRENGTH128 ((drbg_flag_t)1<<3) #define DRBG_STRENGTH192 ((drbg_flag_t)1<<4) #define DRBG_STRENGTH256 ((drbg_flag_t)1<<5) #define DRBG_STRENGTH_MASK (DRBG_STRENGTH128 | DRBG_STRENGTH192 | \ DRBG_STRENGTH256) enum drbg_prefixes { DRBG_PREFIX0 = 0x00, DRBG_PREFIX1, DRBG_PREFIX2, DRBG_PREFIX3 }; #endif /* _DRBG_H */ |
| 84 83 27 61 61 37 56 1 55 49 137 137 141 140 56 76 8 49 49 49 49 84 84 84 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "timers.h" #include "device.h" #include "peer.h" #include "socket.h" #include "messages.h" #include "cookie.h" #include <linux/uio.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <net/ip_tunnels.h> #include <net/udp.h> #include <net/sock.h> static void wg_packet_send_handshake_initiation(struct wg_peer *peer) { struct message_handshake_initiation packet; if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT)) return; /* This function is rate limited. */ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); wg_timers_handshake_initiated(peer); } } void wg_packet_handshake_send_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_handshake_work); wg_packet_send_handshake_initiation(peer); wg_peer_put(peer); } void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry) { if (!is_retry) peer->timer_handshake_attempts = 0; rcu_read_lock_bh(); /* We check last_sent_handshake here in addition to the actual function * we're queueing up, so that we don't queue things if not strictly * necessary: */ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT) || unlikely(READ_ONCE(peer->is_dead))) goto out; wg_peer_get(peer); /* Queues up calling packet_send_queued_handshakes(peer), where we do a * peer_put(peer) after: */ if (!queue_work(peer->device->handshake_send_wq, &peer->transmit_handshake_work)) /* If the work was already queued, we want to drop the * extra reference: */ wg_peer_put(peer); out: rcu_read_unlock_bh(); } void wg_packet_send_handshake_response(struct wg_peer *peer) { struct message_handshake_response packet; atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_response(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); if (wg_noise_handshake_begin_session(&peer->handshake, &peer->keypairs)) { wg_timers_session_derived(peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); } } } void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index) { struct message_handshake_cookie packet; net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n", wg->dev->name, initiating_skb); wg_cookie_message_create(&packet, initiating_skb, sender_index, &wg->cookie_checker); wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet, sizeof(packet)); } static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); send = keypair && READ_ONCE(keypair->sending.is_valid) && (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES || (keypair->i_am_the_initiator && wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } static unsigned int calculate_skb_padding(struct sk_buff *skb) { unsigned int padded_size, last_unit = skb->len; if (unlikely(!PACKET_CB(skb)->mtu)) return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the * padded_size being clamped. Fortunately, that's very rarely the case, * so we optimize for that not happening. */ if (unlikely(last_unit > PACKET_CB(skb)->mtu)) last_unit %= PACKET_CB(skb)->mtu; padded_size = min(PACKET_CB(skb)->mtu, ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) { unsigned int padding_len, plaintext_len, trailer_len; struct scatterlist sg[MAX_SKB_FRAGS + 8]; struct message_data *header; struct sk_buff *trailer; int num_frags; /* Force hash calculation before encryption so that flow analysis is * consistent over the inner packet. */ skb_get_hash(skb); /* Calculate lengths. */ padding_len = calculate_skb_padding(skb); trailer_len = padding_len + noise_encrypted_len(0); plaintext_len = skb->len + padding_len; /* Expand data section to have room for padding and auth tag. */ num_frags = skb_cow_data(skb, trailer_len, &trailer); if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) return false; /* Set the padding to zeros, and make sure it and the auth tag are part * of the skb. */ memset(skb_tail_pointer(trailer), 0, padding_len); /* Expand head section to have room for our header and the network * stack's headers. */ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0)) return false; /* Finalize checksum calculation for the inner packet, if required. */ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) return false; /* Only after checksumming can we safely add on the padding at the end * and the header. */ skb_set_inner_network_header(skb, 0); header = (struct message_data *)skb_push(skb, sizeof(*header)); header->header.type = cpu_to_le32(MESSAGE_DATA); header->key_idx = keypair->remote_index; header->counter = cpu_to_le64(PACKET_CB(skb)->nonce); pskb_put(skb, trailer, trailer_len); /* Now we can encrypt the scattergather segments */ sg_init_table(sg, num_frags); if (skb_to_sgvec(skb, sg, sizeof(struct message_data), noise_encrypted_len(plaintext_len)) <= 0) return false; return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0, PACKET_CB(skb)->nonce, keypair->sending.key); } void wg_packet_send_keepalive(struct wg_peer *peer) { struct sk_buff *skb; if (skb_queue_empty_lockless(&peer->staged_packet_queue)) { skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, GFP_ATOMIC); if (unlikely(!skb)) return; skb_reserve(skb, DATA_PACKET_HEAD_ROOM); skb->dev = peer->device->dev; PACKET_CB(skb)->mtu = skb->dev->mtu; skb_queue_tail(&peer->staged_packet_queue, skb); net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); } wg_packet_send_staged_packets(peer); } static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); skb_list_walk_safe(first, skb, next) { is_keepalive = skb->len == message_data_len(0); if (likely(!wg_socket_send_skb_to_peer(peer, skb, PACKET_CB(skb)->ds) && !is_keepalive)) data_sent = true; } if (likely(data_sent)) wg_timers_data_sent(peer); keep_key_fresh(peer); } void wg_packet_tx_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) wg_packet_create_data_done(peer, first); else kfree_skb_list(first); wg_noise_keypair_put(keypair, false); wg_peer_put(peer); if (need_resched()) cond_resched(); } } void wg_packet_encrypt_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct sk_buff *first, *skb, *next; while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) { enum packet_state state = PACKET_STATE_CRYPTED; skb_list_walk_safe(first, skb, next) { if (likely(encrypt_packet(skb, PACKET_CB(first)->keypair))) { wg_reset_packet(skb, true); } else { state = PACKET_STATE_DEAD; break; } } wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { struct wg_device *wg = peer->device; int ret = -EINVAL; rcu_read_lock_bh(); if (unlikely(READ_ONCE(peer->is_dead))) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) return; wg_noise_keypair_put(PACKET_CB(first)->keypair, false); wg_peer_put(peer); kfree_skb_list(first); } void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); DEV_STATS_ADD(peer->device->dev, tx_dropped, peer->staged_packet_queue.qlen); __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } void wg_packet_send_staged_packets(struct wg_peer *peer) { struct noise_keypair *keypair; struct sk_buff_head packets; struct sk_buff *skb; /* Steal the current queue into our local one. */ __skb_queue_head_init(&packets); spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice_init(&peer->staged_packet_queue, &packets); spin_unlock_bh(&peer->staged_packet_queue.lock); if (unlikely(skb_queue_empty(&packets))) return; /* First we make sure we have a valid reference to a valid key. */ rcu_read_lock_bh(); keypair = wg_noise_keypair_get( rcu_dereference_bh(peer->keypairs.current_keypair)); rcu_read_unlock_bh(); if (unlikely(!keypair)) goto out_nokey; if (unlikely(!READ_ONCE(keypair->sending.is_valid))) goto out_nokey; if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, REJECT_AFTER_TIME))) goto out_invalid; /* After we know we have a somewhat valid key, we now try to assign * nonces to all of the packets in the queue. If we can't assign nonces * for all of them, we just consider it a failure and wait for the next * handshake. */ skb_queue_walk(&packets, skb) { /* 0 for no outer TOS: no leak. TODO: at some later point, we * might consider using flowi->tos as outer instead. */ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); PACKET_CB(skb)->nonce = atomic64_inc_return(&keypair->sending_counter) - 1; if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) goto out_invalid; } packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; wg_packet_create_data(peer, packets.next); return; out_invalid: WRITE_ONCE(keypair->sending.is_valid, false); out_nokey: wg_noise_keypair_put(keypair, false); /* We orphan the packets if we're waiting on a handshake, so that they * don't block a socket's pool. */ skb_queue_walk(&packets, skb) skb_orphan(skb); /* Then we put them back on the top of the queue. We're not too * concerned about accidentally getting things a little out of order if * packets are being added really fast, because this queue is for before * packets can even be sent and it's small anyway. */ spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); /* If we're exiting because there's something wrong with the key, it * means we should initiate a new handshake. */ wg_packet_send_queued_handshake_initiation(peer, false); } |
| 169 169 1 170 170 170 170 170 169 1 79 2 5 1 1 1 2 2 1 2 1 1 60 60 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Restartable sequences system call * * Copyright (C) 2015, Google, Inc., * Paul Turner <pjt@google.com> and Andrew Hunter <ahh@google.com> * Copyright (C) 2015-2018, EfficiOS Inc., * Mathieu Desnoyers <mathieu.desnoyers@efficios.com> */ #include <linux/sched.h> #include <linux/uaccess.h> #include <linux/syscalls.h> #include <linux/rseq.h> #include <linux/types.h> #include <linux/ratelimit.h> #include <asm/ptrace.h> #define CREATE_TRACE_POINTS #include <trace/events/rseq.h> /* The original rseq structure size (including padding) is 32 bytes. */ #define ORIG_RSEQ_SIZE 32 #define RSEQ_CS_NO_RESTART_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT | \ RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \ RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE) #ifdef CONFIG_DEBUG_RSEQ static struct rseq *rseq_kernel_fields(struct task_struct *t) { return (struct rseq *) t->rseq_fields; } static int rseq_validate_ro_fields(struct task_struct *t) { static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); u32 cpu_id_start, cpu_id, node_id, mm_cid; struct rseq __user *rseq = t->rseq; /* * Validate fields which are required to be read-only by * user-space. */ if (!user_read_access_begin(rseq, t->rseq_len)) goto efault; unsafe_get_user(cpu_id_start, &rseq->cpu_id_start, efault_end); unsafe_get_user(cpu_id, &rseq->cpu_id, efault_end); unsafe_get_user(node_id, &rseq->node_id, efault_end); unsafe_get_user(mm_cid, &rseq->mm_cid, efault_end); user_read_access_end(); if ((cpu_id_start != rseq_kernel_fields(t)->cpu_id_start || cpu_id != rseq_kernel_fields(t)->cpu_id || node_id != rseq_kernel_fields(t)->node_id || mm_cid != rseq_kernel_fields(t)->mm_cid) && __ratelimit(&_rs)) { pr_warn("Detected rseq corruption for pid: %d, name: %s\n" "\tcpu_id_start: %u ?= %u\n" "\tcpu_id: %u ?= %u\n" "\tnode_id: %u ?= %u\n" "\tmm_cid: %u ?= %u\n", t->pid, t->comm, cpu_id_start, rseq_kernel_fields(t)->cpu_id_start, cpu_id, rseq_kernel_fields(t)->cpu_id, node_id, rseq_kernel_fields(t)->node_id, mm_cid, rseq_kernel_fields(t)->mm_cid); } /* For now, only print a console warning on mismatch. */ return 0; efault_end: user_read_access_end(); efault: return -EFAULT; } /* * Update an rseq field and its in-kernel copy in lock-step to keep a coherent * state. */ #define rseq_unsafe_put_user(t, value, field, error_label) \ do { \ unsafe_put_user(value, &t->rseq->field, error_label); \ rseq_kernel_fields(t)->field = value; \ } while (0) #else static int rseq_validate_ro_fields(struct task_struct *t) { return 0; } #define rseq_unsafe_put_user(t, value, field, error_label) \ unsafe_put_user(value, &t->rseq->field, error_label) #endif /* * * Restartable sequences are a lightweight interface that allows * user-level code to be executed atomically relative to scheduler * preemption and signal delivery. Typically used for implementing * per-cpu operations. * * It allows user-space to perform update operations on per-cpu data * without requiring heavy-weight atomic operations. * * Detailed algorithm of rseq user-space assembly sequences: * * init(rseq_cs) * cpu = TLS->rseq::cpu_id_start * [1] TLS->rseq::rseq_cs = rseq_cs * [start_ip] ---------------------------- * [2] if (cpu != TLS->rseq::cpu_id) * goto abort_ip; * [3] <last_instruction_in_cs> * [post_commit_ip] ---------------------------- * * The address of jump target abort_ip must be outside the critical * region, i.e.: * * [abort_ip] < [start_ip] || [abort_ip] >= [post_commit_ip] * * Steps [2]-[3] (inclusive) need to be a sequence of instructions in * userspace that can handle being interrupted between any of those * instructions, and then resumed to the abort_ip. * * 1. Userspace stores the address of the struct rseq_cs assembly * block descriptor into the rseq_cs field of the registered * struct rseq TLS area. This update is performed through a single * store within the inline assembly instruction sequence. * [start_ip] * * 2. Userspace tests to check whether the current cpu_id field match * the cpu number loaded before start_ip, branching to abort_ip * in case of a mismatch. * * If the sequence is preempted or interrupted by a signal * at or after start_ip and before post_commit_ip, then the kernel * clears TLS->__rseq_abi::rseq_cs, and sets the user-space return * ip to abort_ip before returning to user-space, so the preempted * execution resumes at abort_ip. * * 3. Userspace critical section final instruction before * post_commit_ip is the commit. The critical section is * self-terminating. * [post_commit_ip] * * 4. <success> * * On failure at [2], or if interrupted by preempt or signal delivery * between [1] and [3]: * * [abort_ip] * F1. <failure> */ static int rseq_update_cpu_node_id(struct task_struct *t) { struct rseq __user *rseq = t->rseq; u32 cpu_id = raw_smp_processor_id(); u32 node_id = cpu_to_node(cpu_id); u32 mm_cid = task_mm_cid(t); /* * Validate read-only rseq fields. */ if (rseq_validate_ro_fields(t)) goto efault; WARN_ON_ONCE((int) mm_cid < 0); if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; rseq_unsafe_put_user(t, cpu_id, cpu_id_start, efault_end); rseq_unsafe_put_user(t, cpu_id, cpu_id, efault_end); rseq_unsafe_put_user(t, node_id, node_id, efault_end); rseq_unsafe_put_user(t, mm_cid, mm_cid, efault_end); /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally updated only if * t->rseq_len != ORIG_RSEQ_SIZE. */ user_write_access_end(); trace_rseq_update(t); return 0; efault_end: user_write_access_end(); efault: return -EFAULT; } static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) { struct rseq __user *rseq = t->rseq; u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0, mm_cid = 0; /* * Validate read-only rseq fields. */ if (rseq_validate_ro_fields(t)) goto efault; if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; /* * Reset all fields to their initial state. * * All fields have an initial state of 0 except cpu_id which is set to * RSEQ_CPU_ID_UNINITIALIZED, so that any user coming in after * unregistration can figure out that rseq needs to be registered * again. */ rseq_unsafe_put_user(t, cpu_id_start, cpu_id_start, efault_end); rseq_unsafe_put_user(t, cpu_id, cpu_id, efault_end); rseq_unsafe_put_user(t, node_id, node_id, efault_end); rseq_unsafe_put_user(t, mm_cid, mm_cid, efault_end); /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally reset only if * t->rseq_len != ORIG_RSEQ_SIZE. */ user_write_access_end(); return 0; efault_end: user_write_access_end(); efault: return -EFAULT; } /* * Get the user-space pointer value stored in the 'rseq_cs' field. */ static int rseq_get_rseq_cs_ptr_val(struct rseq __user *rseq, u64 *rseq_cs) { if (!rseq_cs) return -EFAULT; #ifdef CONFIG_64BIT if (get_user(*rseq_cs, &rseq->rseq_cs)) return -EFAULT; #else if (copy_from_user(rseq_cs, &rseq->rseq_cs, sizeof(*rseq_cs))) return -EFAULT; #endif return 0; } /* * If the rseq_cs field of 'struct rseq' contains a valid pointer to * user-space, copy 'struct rseq_cs' from user-space and validate its fields. */ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) { struct rseq_cs __user *urseq_cs; u64 ptr; u32 __user *usig; u32 sig; int ret; ret = rseq_get_rseq_cs_ptr_val(t->rseq, &ptr); if (ret) return ret; /* If the rseq_cs pointer is NULL, return a cleared struct rseq_cs. */ if (!ptr) { memset(rseq_cs, 0, sizeof(*rseq_cs)); return 0; } /* Check that the pointer value fits in the user-space process space. */ if (ptr >= TASK_SIZE) return -EINVAL; urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr; if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs))) return -EFAULT; if (rseq_cs->start_ip >= TASK_SIZE || rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE || rseq_cs->abort_ip >= TASK_SIZE || rseq_cs->version > 0) return -EINVAL; /* Check for overflow. */ if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip) return -EINVAL; /* Ensure that abort_ip is not in the critical section. */ if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset) return -EINVAL; usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32)); ret = get_user(sig, usig); if (ret) return ret; if (current->rseq_sig != sig) { printk_ratelimited(KERN_WARNING "Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n", sig, current->rseq_sig, current->pid, usig); return -EINVAL; } return 0; } static bool rseq_warn_flags(const char *str, u32 flags) { u32 test_flags; if (!flags) return false; test_flags = flags & RSEQ_CS_NO_RESTART_FLAGS; if (test_flags) pr_warn_once("Deprecated flags (%u) in %s ABI structure", test_flags, str); test_flags = flags & ~RSEQ_CS_NO_RESTART_FLAGS; if (test_flags) pr_warn_once("Unknown flags (%u) in %s ABI structure", test_flags, str); return true; } static int rseq_need_restart(struct task_struct *t, u32 cs_flags) { u32 flags, event_mask; int ret; if (rseq_warn_flags("rseq_cs", cs_flags)) return -EINVAL; /* Get thread flags. */ ret = get_user(flags, &t->rseq->flags); if (ret) return ret; if (rseq_warn_flags("rseq", flags)) return -EINVAL; /* * Load and clear event mask atomically with respect to * scheduler preemption. */ preempt_disable(); event_mask = t->rseq_event_mask; t->rseq_event_mask = 0; preempt_enable(); return !!event_mask; } static int clear_rseq_cs(struct rseq __user *rseq) { /* * The rseq_cs field is set to NULL on preemption or signal * delivery on top of rseq assembly block, as well as on top * of code outside of the rseq assembly block. This performs * a lazy clear of the rseq_cs field. * * Set rseq_cs to NULL. */ #ifdef CONFIG_64BIT return put_user(0UL, &rseq->rseq_cs); #else if (clear_user(&rseq->rseq_cs, sizeof(rseq->rseq_cs))) return -EFAULT; return 0; #endif } /* * Unsigned comparison will be true when ip >= start_ip, and when * ip < start_ip + post_commit_offset. */ static bool in_rseq_cs(unsigned long ip, struct rseq_cs *rseq_cs) { return ip - rseq_cs->start_ip < rseq_cs->post_commit_offset; } static int rseq_ip_fixup(struct pt_regs *regs) { unsigned long ip = instruction_pointer(regs); struct task_struct *t = current; struct rseq_cs rseq_cs; int ret; ret = rseq_get_rseq_cs(t, &rseq_cs); if (ret) return ret; /* * Handle potentially not being within a critical section. * If not nested over a rseq critical section, restart is useless. * Clear the rseq_cs pointer and return. */ if (!in_rseq_cs(ip, &rseq_cs)) return clear_rseq_cs(t->rseq); ret = rseq_need_restart(t, rseq_cs.flags); if (ret <= 0) return ret; ret = clear_rseq_cs(t->rseq); if (ret) return ret; trace_rseq_ip_fixup(ip, rseq_cs.start_ip, rseq_cs.post_commit_offset, rseq_cs.abort_ip); instruction_pointer_set(regs, (unsigned long)rseq_cs.abort_ip); return 0; } /* * This resume handler must always be executed between any of: * - preemption, * - signal delivery, * and return to user-space. * * This is how we can ensure that the entire rseq critical section * will issue the commit instruction only if executed atomically with * respect to other threads scheduled on the same CPU, and with respect * to signal handlers. */ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { struct task_struct *t = current; int ret, sig; if (unlikely(t->flags & PF_EXITING)) return; /* * regs is NULL if and only if the caller is in a syscall path. Skip * fixup and leave rseq_cs as is so that rseq_sycall() will detect and * kill a misbehaving userspace on debug kernels. */ if (regs) { ret = rseq_ip_fixup(regs); if (unlikely(ret < 0)) goto error; } if (unlikely(rseq_update_cpu_node_id(t))) goto error; return; error: sig = ksig ? ksig->sig : 0; force_sigsegv(sig); } #ifdef CONFIG_DEBUG_RSEQ /* * Terminate the process if a syscall is issued within a restartable * sequence. */ void rseq_syscall(struct pt_regs *regs) { unsigned long ip = instruction_pointer(regs); struct task_struct *t = current; struct rseq_cs rseq_cs; if (!t->rseq) return; if (rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs)) force_sig(SIGSEGV); } #endif /* * sys_rseq - setup restartable sequences for caller thread. */ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) { int ret; u64 rseq_cs; if (flags & RSEQ_FLAG_UNREGISTER) { if (flags & ~RSEQ_FLAG_UNREGISTER) return -EINVAL; /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; if (rseq_len != current->rseq_len) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; ret = rseq_reset_rseq_cpu_node_id(current); if (ret) return ret; current->rseq = NULL; current->rseq_sig = 0; current->rseq_len = 0; return 0; } if (unlikely(flags)) return -EINVAL; if (current->rseq) { /* * If rseq is already registered, check whether * the provided address differs from the prior * one. */ if (current->rseq != rseq || rseq_len != current->rseq_len) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; /* Already registered. */ return -EBUSY; } /* * If there was no rseq previously registered, ensure the provided rseq * is properly aligned, as communcated to user-space through the ELF * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq * size, the required alignment is the original struct rseq alignment. * * In order to be valid, rseq_len is either the original rseq size, or * large enough to contain all supported fields, as communicated to * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. */ if (rseq_len < ORIG_RSEQ_SIZE || (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || rseq_len < offsetof(struct rseq, end)))) return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; /* * If the rseq_cs pointer is non-NULL on registration, clear it to * avoid a potential segfault on return to user-space. The proper thing * to do would have been to fail the registration but this would break * older libcs that reuse the rseq area for new threads without * clearing the fields. */ if (rseq_get_rseq_cs_ptr_val(rseq, &rseq_cs)) return -EFAULT; if (rseq_cs && clear_rseq_cs(rseq)) return -EFAULT; #ifdef CONFIG_DEBUG_RSEQ /* * Initialize the in-kernel rseq fields copy for validation of * read-only fields. */ if (get_user(rseq_kernel_fields(current)->cpu_id_start, &rseq->cpu_id_start) || get_user(rseq_kernel_fields(current)->cpu_id, &rseq->cpu_id) || get_user(rseq_kernel_fields(current)->node_id, &rseq->node_id) || get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid)) return -EFAULT; #endif /* * Activate the registration by setting the rseq area address, length * and signature in the task struct. */ current->rseq = rseq; current->rseq_len = rseq_len; current->rseq_sig = sig; /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields * are updated before returning to user-space. */ rseq_set_notify_resume(current); return 0; } |
| 712 2302 6361 712 84 45 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* fs/ internal definitions * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ struct super_block; struct file_system_type; struct iomap; struct iomap_ops; struct linux_binprm; struct path; struct mount; struct shrink_control; struct fs_context; struct pipe_inode_info; struct iov_iter; struct mnt_idmap; struct ns_common; /* * block/bdev.c */ #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); #else static inline void bdev_cache_init(void) { } #endif /* CONFIG_BLOCK */ /* * buffer.c */ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap); /* * char_dev.c */ extern void __init chrdev_init(void); /* * fs_context.c */ extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); /* * namei.c */ extern int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root); int do_rmdir(int dfd, struct filename *name); int do_unlinkat(int dfd, struct filename *name); int may_linkat(struct mnt_idmap *idmap, const struct path *link); int do_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); int do_mkdirat(int dfd, struct filename *name, umode_t mode); int do_symlinkat(struct filename *from, int newdfd, struct filename *to); int do_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags); int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); /* * namespace.c */ extern struct vfsmount *lookup_mnt(const struct path *); extern int finish_automount(struct vfsmount *, const struct path *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); int mnt_get_write_access_file(struct file *file); void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page); int path_umount(struct path *path, int flags); int show_path(struct seq_file *m, struct dentry *root); /* * fs_struct.c */ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred); static inline void file_put_write_access(struct file *file) { put_write_access(file->f_inode); mnt_put_write_access(file->f_path.mnt); if (unlikely(file->f_mode & FMODE_BACKING)) mnt_put_write_access(backing_file_user_path(file)->mnt); } static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { file_put_write_access(file); } } void fput_close_sync(struct file *); void fput_close(struct file *); /* * super.c */ extern int reconfigure_super(struct fs_context *); extern bool super_trylock_shared(struct super_block *sb); struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); int sb_init_dio_done_wq(struct super_block *sb); /* * Prepare superblock for changing its read-only state (i.e., either remount * read-write superblock read-only or vice versa). After this function returns * mnt_is_readonly() will return true for any mount of the superblock if its * caller is able to observe any changes done by the remount. This holds until * sb_end_ro_state_change() is called. */ static inline void sb_start_ro_state_change(struct super_block *sb) { WRITE_ONCE(sb->s_readonly_remount, 1); /* * For RO->RW transition, the barrier pairs with the barrier in * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in * mnt_get_write_access() before the mnt_is_readonly() check. * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } /* * Ends section changing read-only state of the superblock. After this function * returns if mnt_is_readonly() returns false, the caller will be able to * observe all the changes remount did to the superblock. */ static inline void sb_end_ro_state_change(struct super_block *sb) { /* * This barrier provides release semantics that pairs with * the smp_rmb() acquire semantics in mnt_is_readonly(). * This barrier pair ensure that when mnt_is_readonly() sees * 0 for sb->s_readonly_remount, it will also see all the * preceding flag changes that were made during the RO state * change. */ smp_wmb(); WRITE_ONCE(sb->s_readonly_remount, 0); } /* * open.c */ struct open_flags { int open_flag; umode_t mode; int acc_mode; int intent; int lookup_flags; }; extern struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op); extern struct file *do_file_open_root(const struct path *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); struct file *file_close_fd_locked(struct files_struct *files, unsigned fd); int do_ftruncate(struct file *file, loff_t length, int small); int do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); int chown_common(const struct path *path, uid_t user, gid_t group); extern int vfs_open(const struct path *, struct file *); /* * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * fs-writeback.c */ extern long get_nr_dirty_inodes(void); /* * dcache.c */ extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern char *simple_dname(struct dentry *, char *, int); extern void dput_to_list(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); extern void shrink_dcache_for_umount(struct super_block *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); extern void d_genocide(struct dentry *); /* * pipe.c */ extern const struct file_operations pipefifo_fops; /* * fs_pin.c */ extern void group_pin_kill(struct hlist_head *p); extern void mnt_pin_kill(struct mount *m); /* * fs/nsfs.c */ extern const struct dentry_operations ns_dentry_operations; int open_namespace(struct ns_common *ns); /* * fs/stat.c: */ int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer); int do_statx_fd(int fd, unsigned int flags, unsigned int mask, struct statx __user *buffer); /* * fs/splice.c: */ ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); /* * fs/xattr.c: */ struct xattr_name { char name[XATTR_NAME_MAX + 1]; }; struct kernel_xattr_ctx { /* Value of attribute */ union { const void __user *cvalue; void __user *value; }; void *kvalue; size_t size; /* Attribute name */ struct xattr_name *kname; unsigned int flags; }; ssize_t file_getxattr(struct file *file, struct kernel_xattr_ctx *ctx); ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int file_setxattr(struct file *file, struct kernel_xattr_ctx *ctx); int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx); int import_xattr_name(struct xattr_name *kname, const char __user *name); int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode); #ifdef CONFIG_FS_POSIX_ACL int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size); ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size); #else static inline int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { return -EOPNOTSUPP; } static inline ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { return -EOPNOTSUPP; } #endif ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); /* * fs/attr.c */ struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); struct stashed_operations { void (*put_data)(void *data); int (*init_inode)(struct inode *inode, void *data); }; int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path); void stashed_dentry_prune(struct dentry *dentry); struct dentry *stashed_dentry_get(struct dentry **stashed); /** * path_mounted - check whether path is mounted * @path: path to check * * Determine whether @path refers to the root of a mount. * * Return: true if @path is the root of a mount, false if not. */ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } void file_f_owner_release(struct file *file); bool file_seek_cur_needs_f_lock(struct file *file); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map); |
| 1147 | 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> |
| 9 39 38 39 39 41 41 14 35 9 35 35 39 35 14 1 1 13 13 13 13 13 13 13 13 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <crypto/hash.h> #include <linux/cpu.h> #include <linux/kref.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/workqueue.h> #include <net/tcp.h> static size_t __scratch_size; struct sigpool_scratch { local_lock_t bh_lock; void __rcu *pad; }; static DEFINE_PER_CPU(struct sigpool_scratch, sigpool_scratch) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; struct sigpool_entry { struct crypto_ahash *hash; const char *alg; struct kref kref; uint16_t needs_key:1, reserved:15; }; #define CPOOL_SIZE (PAGE_SIZE / sizeof(struct sigpool_entry)) static struct sigpool_entry cpool[CPOOL_SIZE]; static unsigned int cpool_populated; static DEFINE_MUTEX(cpool_mutex); /* Slow-path */ struct scratches_to_free { struct rcu_head rcu; unsigned int cnt; void *scratches[]; }; static void free_old_scratches(struct rcu_head *head) { struct scratches_to_free *stf; stf = container_of(head, struct scratches_to_free, rcu); while (stf->cnt--) kfree(stf->scratches[stf->cnt]); kfree(stf); } /** * sigpool_reserve_scratch - re-allocates scratch buffer, slow-path * @size: request size for the scratch/temp buffer */ static int sigpool_reserve_scratch(size_t size) { struct scratches_to_free *stf; size_t stf_sz = struct_size(stf, scratches, num_possible_cpus()); int cpu, err = 0; lockdep_assert_held(&cpool_mutex); if (__scratch_size >= size) return 0; stf = kmalloc(stf_sz, GFP_KERNEL); if (!stf) return -ENOMEM; stf->cnt = 0; size = max(size, __scratch_size); cpus_read_lock(); for_each_possible_cpu(cpu) { void *scratch, *old_scratch; scratch = kmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (!scratch) { err = -ENOMEM; break; } old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu), scratch, lockdep_is_held(&cpool_mutex)); if (!cpu_online(cpu) || !old_scratch) { kfree(old_scratch); continue; } stf->scratches[stf->cnt++] = old_scratch; } cpus_read_unlock(); if (!err) __scratch_size = size; call_rcu(&stf->rcu, free_old_scratches); return err; } static void sigpool_scratch_free(void) { int cpu; for_each_possible_cpu(cpu) kfree(rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu), NULL, lockdep_is_held(&cpool_mutex))); __scratch_size = 0; } static int __cpool_try_clone(struct crypto_ahash *hash) { struct crypto_ahash *tmp; tmp = crypto_clone_ahash(hash); if (IS_ERR(tmp)) return PTR_ERR(tmp); crypto_free_ahash(tmp); return 0; } static int __cpool_alloc_ahash(struct sigpool_entry *e, const char *alg) { struct crypto_ahash *cpu0_hash; int ret; e->alg = kstrdup(alg, GFP_KERNEL); if (!e->alg) return -ENOMEM; cpu0_hash = crypto_alloc_ahash(alg, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(cpu0_hash)) { ret = PTR_ERR(cpu0_hash); goto out_free_alg; } e->needs_key = crypto_ahash_get_flags(cpu0_hash) & CRYPTO_TFM_NEED_KEY; ret = __cpool_try_clone(cpu0_hash); if (ret) goto out_free_cpu0_hash; e->hash = cpu0_hash; kref_init(&e->kref); return 0; out_free_cpu0_hash: crypto_free_ahash(cpu0_hash); out_free_alg: kfree(e->alg); e->alg = NULL; return ret; } /** * tcp_sigpool_alloc_ahash - allocates pool for ahash requests * @alg: name of async hash algorithm * @scratch_size: reserve a tcp_sigpool::scratch buffer of this size */ int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size) { int i, ret; /* slow-path */ mutex_lock(&cpool_mutex); ret = sigpool_reserve_scratch(scratch_size); if (ret) goto out; for (i = 0; i < cpool_populated; i++) { if (!cpool[i].alg) continue; if (strcmp(cpool[i].alg, alg)) continue; /* pairs with tcp_sigpool_release() */ if (!kref_get_unless_zero(&cpool[i].kref)) kref_init(&cpool[i].kref); ret = i; goto out; } for (i = 0; i < cpool_populated; i++) { if (!cpool[i].alg) break; } if (i >= CPOOL_SIZE) { ret = -ENOSPC; goto out; } ret = __cpool_alloc_ahash(&cpool[i], alg); if (!ret) { ret = i; if (i == cpool_populated) cpool_populated++; } out: mutex_unlock(&cpool_mutex); return ret; } EXPORT_SYMBOL_GPL(tcp_sigpool_alloc_ahash); static void __cpool_free_entry(struct sigpool_entry *e) { crypto_free_ahash(e->hash); kfree(e->alg); memset(e, 0, sizeof(*e)); } static void cpool_cleanup_work_cb(struct work_struct *work) { bool free_scratch = true; unsigned int i; mutex_lock(&cpool_mutex); for (i = 0; i < cpool_populated; i++) { if (kref_read(&cpool[i].kref) > 0) { free_scratch = false; continue; } if (!cpool[i].alg) continue; __cpool_free_entry(&cpool[i]); } if (free_scratch) sigpool_scratch_free(); mutex_unlock(&cpool_mutex); } static DECLARE_WORK(cpool_cleanup_work, cpool_cleanup_work_cb); static void cpool_schedule_cleanup(struct kref *kref) { schedule_work(&cpool_cleanup_work); } /** * tcp_sigpool_release - decreases number of users for a pool. If it was * the last user of the pool, releases any memory that was consumed. * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() */ void tcp_sigpool_release(unsigned int id) { if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg)) return; /* slow-path */ kref_put(&cpool[id].kref, cpool_schedule_cleanup); } EXPORT_SYMBOL_GPL(tcp_sigpool_release); /** * tcp_sigpool_get - increases number of users (refcounter) for a pool * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() */ void tcp_sigpool_get(unsigned int id) { if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg)) return; kref_get(&cpool[id].kref); } EXPORT_SYMBOL_GPL(tcp_sigpool_get); int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c) __cond_acquires(RCU_BH) { struct crypto_ahash *hash; rcu_read_lock_bh(); if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg)) { rcu_read_unlock_bh(); return -EINVAL; } hash = crypto_clone_ahash(cpool[id].hash); if (IS_ERR(hash)) { rcu_read_unlock_bh(); return PTR_ERR(hash); } c->req = ahash_request_alloc(hash, GFP_ATOMIC); if (!c->req) { crypto_free_ahash(hash); rcu_read_unlock_bh(); return -ENOMEM; } ahash_request_set_callback(c->req, 0, NULL, NULL); /* Pairs with tcp_sigpool_reserve_scratch(), scratch area is * valid (allocated) until tcp_sigpool_end(). */ local_lock_nested_bh(&sigpool_scratch.bh_lock); c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch.pad)); return 0; } EXPORT_SYMBOL_GPL(tcp_sigpool_start); void tcp_sigpool_end(struct tcp_sigpool *c) __releases(RCU_BH) { struct crypto_ahash *hash = crypto_ahash_reqtfm(c->req); local_unlock_nested_bh(&sigpool_scratch.bh_lock); rcu_read_unlock_bh(); ahash_request_free(c->req); crypto_free_ahash(hash); } EXPORT_SYMBOL_GPL(tcp_sigpool_end); /** * tcp_sigpool_algo - return algorithm of tcp_sigpool * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() * @buf: buffer to return name of algorithm * @buf_len: size of @buf */ size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len) { if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg)) return -EINVAL; return strscpy(buf, cpool[id].alg, buf_len); } EXPORT_SYMBOL_GPL(tcp_sigpool_algo); /** * tcp_sigpool_hash_skb_data - hash data in skb with initialized tcp_sigpool * @hp: tcp_sigpool pointer * @skb: buffer to add sign for * @header_len: TCP header length for this segment */ int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, const struct sk_buff *skb, unsigned int header_len) { const unsigned int head_data_len = skb_headlen(skb) > header_len ? skb_headlen(skb) - header_len : 0; const struct skb_shared_info *shi = skb_shinfo(skb); const struct tcphdr *tp = tcp_hdr(skb); struct ahash_request *req = hp->req; struct sk_buff *frag_iter; struct scatterlist sg; unsigned int i; sg_init_table(&sg, 1); sg_set_buf(&sg, ((u8 *)tp) + header_len, head_data_len); ahash_request_set_crypt(req, &sg, NULL, head_data_len); if (crypto_ahash_update(req)) return 1; for (i = 0; i < shi->nr_frags; ++i) { const skb_frag_t *f = &shi->frags[i]; unsigned int offset = skb_frag_off(f); struct page *page; page = skb_frag_page(f) + (offset >> PAGE_SHIFT); sg_set_page(&sg, page, skb_frag_size(f), offset_in_page(offset)); ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f)); if (crypto_ahash_update(req)) return 1; } skb_walk_frags(skb, frag_iter) if (tcp_sigpool_hash_skb_data(hp, frag_iter, 0)) return 1; return 0; } EXPORT_SYMBOL(tcp_sigpool_hash_skb_data); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Per-CPU pool of crypto requests"); |
| 41 41 40 41 4 4 3 2 9 11 11 1 9 9 9 29 29 25 3 3 3 29 29 6 3 3 3 3 1 2 3 2 1 16 13 1 2 2 1 1 2 2 2 60 60 1 1 53 1 3 1 39 18 2 44 4 1 6 10 1 4 5 18 2 38 39 1 40 64 418 418 390 390 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * DCCP over IPv6 * Linux INET6 implementation * * Based on net/dccp6/ipv6.c * * Arnaldo Carvalho de Melo <acme@ghostprotocols.net> */ #include <linux/module.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/xfrm.h> #include <linux/string.h> #include <net/addrconf.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/inet_sock.h> #include <net/inet6_connection_sock.h> #include <net/inet6_hashtables.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/rstreason.h> #include "dccp.h" #include "ipv6.h" #include "feat.h" struct dccp_v6_pernet { struct sock *v6_ctl_sk; }; static unsigned int dccp_v6_pernet_id __read_mostly; /* The per-net v6_ctl_sk is used for sending RSTs and ACKs */ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr) { return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr); } static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, dccp_hdr(skb)->dccph_dport, dccp_hdr(skb)->dccph_sport ); } static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr; const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; 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; hdr = (const struct ipv6hdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, ntohs(dh->dccph_sport), inet6_iif(skb), 0); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_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 (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; } np = inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (!ip6_sk_accept_pmtu(sk)) goto out; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; dst = inet6_csk_update_pmtu(sk, ntohl(info)); if (!dst) goto out; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; /* * Wake people up to see the error * (see connect in sock.c) */ sk_error_report(sk); dccp_done(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } goto out; } if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { sk->sk_err = err; sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct in6_addr *final_p, final; struct flowi6 fl6; int err = -1; struct dst_entry *dst; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_DCCP; fl6.daddr = ireq->ir_v6_rmt_addr; fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowlabel = 0; fl6.flowi6_oif = ireq->ir_iif; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = htons(ireq->ir_num); security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); rcu_read_lock(); final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto done; } skb = dccp_make_response(sk, dst, req); if (skb != NULL) { struct dccp_hdr *dh = dccp_hdr(skb); struct ipv6_txoptions *opt; dh->dccph_checksum = dccp_v6_csum_finish(skb, &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6.daddr = ireq->ir_v6_rmt_addr; rcu_read_lock(); opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, &fl6, READ_ONCE(sk->sk_mark), opt, np->tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); err = net_xmit_eval(err); } done: dst_release(dst); return err; } static void dccp_v6_reqsk_destructor(struct request_sock *req) { dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); kfree(inet_rsk(req)->ipv6_opt); kfree_skb(inet_rsk(req)->pktopts); } static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb, enum sk_rst_reason reason) { const struct ipv6hdr *rxip6h; struct sk_buff *skb; struct flowi6 fl6; struct net *net = dev_net(skb_dst(rxskb)->dev); struct dccp_v6_pernet *pn; struct sock *ctl_sk; struct dst_entry *dst; if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; if (!ipv6_unicast_destination(rxskb)) return; pn = net_generic(net, dccp_v6_pernet_id); ctl_sk = pn->v6_ctl_sk; skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) return; rxip6h = ipv6_hdr(rxskb); dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr, &rxip6h->daddr); memset(&fl6, 0, sizeof(fl6)); fl6.daddr = rxip6h->saddr; fl6.saddr = rxip6h->daddr; fl6.flowi6_proto = IPPROTO_DCCP; fl6.flowi6_oif = inet6_iif(rxskb); fl6.fl6_dport = dccp_hdr(skb)->dccph_dport; fl6.fl6_sport = dccp_hdr(skb)->dccph_sport; security_skb_classify_flow(rxskb, flowi6_to_flowi_common(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); DCCP_INC_STATS(DCCP_MIB_OUTRSTS); return; } kfree_skb(skb); } static struct request_sock_ops dccp6_request_sock_ops = { .family = AF_INET6, .obj_size = sizeof(struct dccp6_request_sock), .rtx_syn_ack = dccp_v6_send_response, .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v6_reqsk_destructor, .send_reset = dccp_v6_ctl_send_reset, .syn_ack_timeout = dccp_syn_ack_timeout, }; static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct request_sock *req; struct dccp_request_sock *dreq; struct inet_request_sock *ireq; struct ipv6_pinfo *np = inet6_sk(sk); const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) return 0; /* discard, don't send a reset here */ if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } if (dccp_bad_service_code(sk, service)) { dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; } /* * There are no SYN attacks on IPv6, yet... */ 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(&dccp6_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); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ir_rmt_addr = LOOPBACK4_IPV6; ireq->ir_loc_addr = LOOPBACK4_IPV6; ireq->ireq_family = AF_INET6; ireq->ir_mark = inet_request_mark(sk, skb); if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { refcount_inc(&skb->users); ireq->pktopts = skb; } ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if); /* So that link locals have meaning */ if (!ireq->ir_iif && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = inet6_iif(skb); /* * 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_v6_init_sequence(skb); dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; if (dccp_v6_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; } static struct sock *dccp_v6_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 = inet_rsk(req); struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; if (skb->protocol == htons(ETH_P_IP)) { /* * v6 mapped */ newsk = dccp_v4_request_recv_sock(sk, skb, req, dst, req_unhash, own_req); if (newsk == NULL) return NULL; newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->mcast_oif = inet_iif(skb); newnp->mcast_hops = ip_hdr(skb)->ttl; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count * here, dccp_create_openreq_child now does this for us, see the comment in * that function for the gory details. -acme */ /* It is tricky place. Until this moment IPv4 tcp worked with IPv6 icsk.icsk_af_ops. Sync it now. */ dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { struct flowi6 fl6; dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP); if (!dst) goto out; } newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks * count here, dccp_create_openreq_child now does this for us, see the * comment in that function for the gory details. -acme */ ip6_dst_store(newsk, dst, NULL, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->saddr = ireq->ir_v6_loc_addr; /* Now IPv6 options... First: no IPv4 options. */ newinet->inet_opt = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; /* * Clone native IPv6 options from listening socket (if any) * * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); RCU_INIT_POINTER(newnp->opt, opt); } inet_csk(newsk)->icsk_ext_hdr_len = 0; if (opt) inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + opt->opt_flen; dccp_sync_mss(newsk, dst_mtu(dst)); if (__inet_inherit_port(sk, newsk) < 0) { inet_csk_prepare_forced_close(newsk); dccp_done(newsk); goto out; } *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; } return newsk; out_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: dst_release(dst); out: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; } /* The socket must have it's spinlock held when we get * here. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *opt_skb = NULL; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. From backlog it always goes here. Kerboom... Fortunately, dccp_rcv_established and rcv_established handle them correctly, but it is not case with dccp_v6_hnd_req and dccp_v6_ctl_send_reset(). --ANK */ if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_do_rcv(sk, skb); if (sk_filter(sk, skb)) goto discard; /* * socket locking is here for SMP purposes as backlog rcv is currently * called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. Yes, guys, it is the only place in our code, where we may make it not affecting IPv4. The rest of code is protocol independent, and I do not like idea to uglify IPv4. Actually, all the idea behind IPV6_PKTOPTIONS looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. --ANK (980728) */ if (np->rxopt.all && sk->sk_state != DCCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; } /* * Step 3: Process LISTEN state * If S.state == LISTEN, * 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, dccp_hdr(skb), skb->len)) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; reset: dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); discard: if (opt_skb != NULL) __kfree_skb(opt_skb); kfree_skb(skb); return 0; /* Handling IPV6_PKTOPTIONS skb the similar * way it's done for net/ipv6/tcp_ipv6.c */ ipv6_pktoptions: if (!((1 << sk->sk_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) WRITE_ONCE(np->mcast_oif, inet6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (inet6_test_bit(REPFLOW, sk)) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); opt_skb = xchg(&np->pktoptions, NULL); } } kfree_skb(opt_skb); return 0; } static int dccp_v6_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; bool refcounted; struct sock *sk; int min_cov; /* Step 1: Check header basics */ if (dccp_invalid_packet(skb)) goto discard_it; /* Step 1: If header checksum is incorrect, drop packet and return. */ if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->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; if (dccp_packet_without_ack(skb)) DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; else DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); lookup: sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, inet6_iif(skb), 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_v6_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: send Data Dropped option (see also dccp_v4_rcv) */ goto discard_and_relse; } if (!xfrm6_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) ? -1 : 0; no_dccp_socket: if (!xfrm6_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_v6_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 int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_sock *dp = dccp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; struct ipv6_txoptions *opt; struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; dp->dccps_role = DCCP_ROLE_CLIENT; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl6, 0, sizeof(fl6)); if (inet6_test_bit(SNDFLOW, sk)) { fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6.flowlabel); if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) usin->sin6_addr.s6_addr[15] = 1; addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type & IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != usin->sin6_scope_id) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* * DCCP over IPv4 */ if (addr_type == IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; net_dbg_ratelimited("connect: ipv4 mapped\n"); if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; icsk->icsk_af_ops = &dccp_ipv6_mapped; sk->sk_backlog_rcv = dccp_v4_do_rcv; err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; icsk->icsk_af_ops = &dccp_ipv6_af_ops; sk->sk_backlog_rcv = dccp_v6_do_rcv; goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_DCCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } if (saddr == NULL) { saddr = &fl6.saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; inet->inet_dport = usin->sin6_port; dccp_set_state(sk, DCCP_REQUESTING); err = inet6_hash_connect(&dccp_death_row, sk); if (err) goto late_failure; dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); err = dccp_connect(sk); if (err) goto late_failure; return 0; late_failure: dccp_set_state(sk, DCCP_CLOSED); inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .queue_xmit = inet6_csk_xmit, .send_check = dccp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, .conn_request = dccp_v6_conn_request, .syn_recv_sock = dccp_v6_request_recv_sock, .net_header_len = sizeof(struct ipv6hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, }; /* * DCCP over IPv4 via INET6 API */ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .conn_request = dccp_v6_conn_request, .syn_recv_sock = dccp_v6_request_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, }; static void dccp_v6_sk_destruct(struct sock *sk) { dccp_destruct_common(sk); inet6_sock_destruct(sk); } /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int dccp_v6_init_sock(struct sock *sk) { static __u8 dccp_v6_ctl_sock_initialized; int err = dccp_init_sock(sk, dccp_v6_ctl_sock_initialized); if (err == 0) { if (unlikely(!dccp_v6_ctl_sock_initialized)) dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; sk->sk_destruct = dccp_v6_sk_destruct; } return err; } static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; static struct proto dccp_v6_prot = { .name = "DCCPv6", .owner = THIS_MODULE, .close = dccp_close, .connect = dccp_v6_connect, .disconnect = dccp_disconnect, .ioctl = dccp_ioctl, .init = dccp_v6_init_sock, .setsockopt = dccp_setsockopt, .getsockopt = dccp_getsockopt, .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v6_do_rcv, .hash = inet6_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 dccp6_sock), .ipv6_pinfo_offset = offsetof(struct dccp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, }; static const struct inet6_protocol dccp_v6_protocol = { .handler = dccp_v6_rcv, .err_handler = dccp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; static const struct proto_ops inet6_dccp_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet6_getname, .poll = dccp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .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, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw dccp_v6_protosw = { .type = SOCK_DCCP, .protocol = IPPROTO_DCCP, .prot = &dccp_v6_prot, .ops = &inet6_dccp_ops, .flags = INET_PROTOSW_ICSK, }; static int __net_init dccp_v6_init_net(struct net *net) { struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id); if (dccp_hashinfo.bhash == NULL) return -ESOCKTNOSUPPORT; return inet_ctl_sock_create(&pn->v6_ctl_sk, PF_INET6, SOCK_DCCP, IPPROTO_DCCP, net); } static void __net_exit dccp_v6_exit_net(struct net *net) { struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id); inet_ctl_sock_destroy(pn->v6_ctl_sk); } static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; static int __init dccp_v6_init(void) { int err = proto_register(&dccp_v6_prot, 1); if (err) goto out; inet6_register_protosw(&dccp_v6_protosw); err = register_pernet_subsys(&dccp_v6_ops); if (err) goto out_destroy_ctl_sock; err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP); if (err) goto out_unregister_proto; out: return err; out_unregister_proto: unregister_pernet_subsys(&dccp_v6_ops); out_destroy_ctl_sock: inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); goto out; } static void __exit dccp_v6_exit(void) { inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); unregister_pernet_subsys(&dccp_v6_ops); inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); } module_init(dccp_v6_init); module_exit(dccp_v6_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_INET6-proto-0-type-SOCK_DCCP */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol"); |
| 50 50 15 15 21 17 21 17 1 5 30 30 2 2 2 1 3 20 30 14 14 14 14 14 6 6 6 6 1 1 3 2 3 3 3 3 3 3 3 2 3 3 3 3 3 3 3 3 3 1 5 5 1 1 1 1 2 1 3 5 11 11 9 14 5 14 9 2 5 1 2 4 6 4 3 6 9 5 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * PPP async serial channel driver for Linux. * * Copyright 1999 Paul Mackerras. * * This driver provides the encapsulation and framing for sending * and receiving PPP frames over async serial lines. It relies on * the generic PPP layer to give it frames to send and to process * received frames. It implements the PPP line discipline. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/tty.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/crc-ccitt.h> #include <linux/ppp_defs.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/jiffies.h> #include <linux/slab.h> #include <linux/unaligned.h> #include <linux/uaccess.h> #include <asm/string.h> #define PPP_VERSION "2.4.2" #define OBUFSIZE 4096 /* Structure for storing local state. */ struct asyncppp { struct tty_struct *tty; unsigned int flags; unsigned int state; unsigned int rbits; int mru; spinlock_t xmit_lock; spinlock_t recv_lock; unsigned long xmit_flags; u32 xaccm[8]; u32 raccm; unsigned int bytes_sent; unsigned int bytes_rcvd; struct sk_buff *tpkt; int tpkt_pos; u16 tfcs; unsigned char *optr; unsigned char *olim; unsigned long last_xmit; struct sk_buff *rpkt; int lcp_fcs; struct sk_buff_head rqueue; struct tasklet_struct tsk; refcount_t refcnt; struct completion dead; struct ppp_channel chan; /* interface to generic ppp layer */ unsigned char obuf[OBUFSIZE]; }; /* Bit numbers in xmit_flags */ #define XMIT_WAKEUP 0 #define XMIT_FULL 1 #define XMIT_BUSY 2 /* State bits */ #define SC_TOSS 1 #define SC_ESCAPE 2 #define SC_PREV_ERROR 4 /* Bits in rbits */ #define SC_RCV_BITS (SC_RCV_B7_1|SC_RCV_B7_0|SC_RCV_ODDP|SC_RCV_EVNP) static int flag_time = HZ; module_param(flag_time, int, 0); MODULE_PARM_DESC(flag_time, "ppp_async: interval between flagged packets (in clock ticks)"); MODULE_DESCRIPTION("PPP async serial channel module"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_PPP); /* * Prototypes. */ static int ppp_async_encode(struct asyncppp *ap); static int ppp_async_send(struct ppp_channel *chan, struct sk_buff *skb); static int ppp_async_push(struct asyncppp *ap); static void ppp_async_flush_output(struct asyncppp *ap); static void ppp_async_input(struct asyncppp *ap, const unsigned char *buf, const u8 *flags, int count); static int ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg); static void ppp_async_process(struct tasklet_struct *t); static void async_lcp_peek(struct asyncppp *ap, unsigned char *data, int len, int inbound); static const struct ppp_channel_ops async_ops = { .start_xmit = ppp_async_send, .ioctl = ppp_async_ioctl, }; /* * Routines implementing the PPP line discipline. */ /* * We have a potential race on dereferencing tty->disc_data, * because the tty layer provides no locking at all - thus one * cpu could be running ppp_asynctty_receive while another * calls ppp_asynctty_close, which zeroes tty->disc_data and * frees the memory that ppp_asynctty_receive is using. The best * way to fix this is to use a rwlock in the tty struct, but for now * we use a single global rwlock for all ttys in ppp line discipline. * * FIXME: this is no longer true. The _close path for the ldisc is * now guaranteed to be sane. */ static DEFINE_RWLOCK(disc_data_lock); static struct asyncppp *ap_get(struct tty_struct *tty) { struct asyncppp *ap; read_lock(&disc_data_lock); ap = tty->disc_data; if (ap != NULL) refcount_inc(&ap->refcnt); read_unlock(&disc_data_lock); return ap; } static void ap_put(struct asyncppp *ap) { if (refcount_dec_and_test(&ap->refcnt)) complete(&ap->dead); } /* * Called when a tty is put into PPP line discipline. Called in process * context. */ static int ppp_asynctty_open(struct tty_struct *tty) { struct asyncppp *ap; int err; int speed; if (tty->ops->write == NULL) return -EOPNOTSUPP; err = -ENOMEM; ap = kzalloc(sizeof(*ap), GFP_KERNEL); if (!ap) goto out; /* initialize the asyncppp structure */ ap->tty = tty; ap->mru = PPP_MRU; spin_lock_init(&ap->xmit_lock); spin_lock_init(&ap->recv_lock); ap->xaccm[0] = ~0U; ap->xaccm[3] = 0x60000000U; ap->raccm = ~0U; ap->optr = ap->obuf; ap->olim = ap->obuf; ap->lcp_fcs = -1; skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_async_process); refcount_set(&ap->refcnt, 1); init_completion(&ap->dead); ap->chan.private = ap; ap->chan.ops = &async_ops; ap->chan.mtu = PPP_MRU; speed = tty_get_baud_rate(tty); ap->chan.speed = speed; err = ppp_register_channel(&ap->chan); if (err) goto out_free; tty->disc_data = ap; tty->receive_room = 65536; return 0; out_free: kfree(ap); out: return err; } /* * Called when the tty is put into another line discipline * or it hangs up. We have to wait for any cpu currently * executing in any of the other ppp_asynctty_* routines to * finish before we can call ppp_unregister_channel and free * the asyncppp struct. This routine must be called from * process context, not interrupt or softirq context. */ static void ppp_asynctty_close(struct tty_struct *tty) { struct asyncppp *ap; write_lock_irq(&disc_data_lock); ap = tty->disc_data; tty->disc_data = NULL; write_unlock_irq(&disc_data_lock); if (!ap) return; /* * We have now ensured that nobody can start using ap from now * on, but we have to wait for all existing users to finish. * Note that ppp_unregister_channel ensures that no calls to * our channel ops (i.e. ppp_async_send/ioctl) are in progress * by the time it returns. */ if (!refcount_dec_and_test(&ap->refcnt)) wait_for_completion(&ap->dead); tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); kfree_skb(ap->rpkt); skb_queue_purge(&ap->rqueue); kfree_skb(ap->tpkt); kfree(ap); } /* * Called on tty hangup in process context. * * Wait for I/O to driver to complete and unregister PPP channel. * This is already done by the close routine, so just call that. */ static void ppp_asynctty_hangup(struct tty_struct *tty) { ppp_asynctty_close(tty); } /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. */ static ssize_t ppp_asynctty_read(struct tty_struct *tty, struct file *file, u8 *buf, size_t count, void **cookie, unsigned long offset) { return -EAGAIN; } /* * Write on the tty does nothing, the packets all come in * from the ppp generic stuff. */ static ssize_t ppp_asynctty_write(struct tty_struct *tty, struct file *file, const u8 *buf, size_t count) { return -EAGAIN; } /* * Called in process context only. May be re-entered by multiple * ioctl calling threads. */ static int ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct asyncppp *ap = ap_get(tty); int err, val; int __user *p = (int __user *)arg; if (!ap) return -ENXIO; err = -EFAULT; switch (cmd) { case PPPIOCGCHAN: err = -EFAULT; if (put_user(ppp_channel_index(&ap->chan), p)) break; err = 0; break; case PPPIOCGUNIT: err = -EFAULT; if (put_user(ppp_unit_number(&ap->chan), p)) break; err = 0; break; case TCFLSH: /* flush our buffers and the serial port's buffer */ if (arg == TCIOFLUSH || arg == TCOFLUSH) ppp_async_flush_output(ap); err = n_tty_ioctl_helper(tty, cmd, arg); break; case FIONREAD: val = 0; if (put_user(val, p)) break; err = 0; break; default: /* Try the various mode ioctls */ err = tty_mode_ioctl(tty, cmd, arg); } ap_put(ap); return err; } /* May sleep, don't call from interrupt level or with interrupts disabled */ static void ppp_asynctty_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { struct asyncppp *ap = ap_get(tty); unsigned long flags; if (!ap) return; spin_lock_irqsave(&ap->recv_lock, flags); ppp_async_input(ap, buf, cflags, count); spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); ap_put(ap); tty_unthrottle(tty); } static void ppp_asynctty_wakeup(struct tty_struct *tty) { struct asyncppp *ap = ap_get(tty); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); ap_put(ap); } static struct tty_ldisc_ops ppp_ldisc = { .owner = THIS_MODULE, .num = N_PPP, .name = "ppp", .open = ppp_asynctty_open, .close = ppp_asynctty_close, .hangup = ppp_asynctty_hangup, .read = ppp_asynctty_read, .write = ppp_asynctty_write, .ioctl = ppp_asynctty_ioctl, .receive_buf = ppp_asynctty_receive, .write_wakeup = ppp_asynctty_wakeup, }; static int __init ppp_async_init(void) { int err; err = tty_register_ldisc(&ppp_ldisc); if (err != 0) printk(KERN_ERR "PPP_async: error %d registering line disc.\n", err); return err; } /* * The following routines provide the PPP channel interface. */ static int ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) { struct asyncppp *ap = chan->private; void __user *argp = (void __user *)arg; int __user *p = argp; int err, val; u32 accm[8]; err = -EFAULT; switch (cmd) { case PPPIOCGFLAGS: val = ap->flags | ap->rbits; if (put_user(val, p)) break; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; ap->flags = val & ~SC_RCV_BITS; spin_lock_irq(&ap->recv_lock); ap->rbits = val & SC_RCV_BITS; spin_unlock_irq(&ap->recv_lock); err = 0; break; case PPPIOCGASYNCMAP: if (put_user(ap->xaccm[0], (u32 __user *)argp)) break; err = 0; break; case PPPIOCSASYNCMAP: if (get_user(ap->xaccm[0], (u32 __user *)argp)) break; err = 0; break; case PPPIOCGRASYNCMAP: if (put_user(ap->raccm, (u32 __user *)argp)) break; err = 0; break; case PPPIOCSRASYNCMAP: if (get_user(ap->raccm, (u32 __user *)argp)) break; err = 0; break; case PPPIOCGXASYNCMAP: if (copy_to_user(argp, ap->xaccm, sizeof(ap->xaccm))) break; err = 0; break; case PPPIOCSXASYNCMAP: if (copy_from_user(accm, argp, sizeof(accm))) break; accm[2] &= ~0x40000000U; /* can't escape 0x5e */ accm[3] |= 0x60000000U; /* must escape 0x7d, 0x7e */ memcpy(ap->xaccm, accm, sizeof(ap->xaccm)); err = 0; break; case PPPIOCGMRU: if (put_user(ap->mru, p)) break; err = 0; break; case PPPIOCSMRU: if (get_user(val, p)) break; if (val > U16_MAX) { err = -EINVAL; break; } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; err = 0; break; default: err = -ENOTTY; } return err; } /* * This is called at softirq level to deliver received packets * to the ppp_generic code, and to tell the ppp_generic code * if we can accept more output now. */ static void ppp_async_process(struct tasklet_struct *t) { struct asyncppp *ap = from_tasklet(ap, t, tsk); struct sk_buff *skb; /* process received packets */ while ((skb = skb_dequeue(&ap->rqueue)) != NULL) { if (skb->cb[0]) ppp_input_error(&ap->chan, 0); ppp_input(&ap->chan, skb); } /* try to push more stuff out */ if (test_bit(XMIT_WAKEUP, &ap->xmit_flags) && ppp_async_push(ap)) ppp_output_wakeup(&ap->chan); } /* * Procedures for encapsulation and framing. */ /* * Procedure to encode the data for async serial transmission. * Does octet stuffing (escaping), puts the address/control bytes * on if A/C compression is disabled, and does protocol compression. * Assumes ap->tpkt != 0 on entry. * Returns 1 if we finished the current frame, 0 otherwise. */ #define PUT_BYTE(ap, buf, c, islcp) do { \ if ((islcp && c < 0x20) || (ap->xaccm[c >> 5] & (1 << (c & 0x1f)))) {\ *buf++ = PPP_ESCAPE; \ *buf++ = c ^ PPP_TRANS; \ } else \ *buf++ = c; \ } while (0) static int ppp_async_encode(struct asyncppp *ap) { int fcs, i, count, c, proto; unsigned char *buf, *buflim; unsigned char *data; int islcp; buf = ap->obuf; ap->olim = buf; ap->optr = buf; i = ap->tpkt_pos; data = ap->tpkt->data; count = ap->tpkt->len; fcs = ap->tfcs; proto = get_unaligned_be16(data); /* * LCP packets with code values between 1 (configure-request) * and 7 (code-reject) must be sent as though no options * had been negotiated. */ islcp = proto == PPP_LCP && count >= 3 && 1 <= data[2] && data[2] <= 7; if (i == 0) { if (islcp) async_lcp_peek(ap, data, count, 0); /* * Start of a new packet - insert the leading FLAG * character if necessary. */ if (islcp || flag_time == 0 || time_after_eq(jiffies, ap->last_xmit + flag_time)) *buf++ = PPP_FLAG; ap->last_xmit = jiffies; fcs = PPP_INITFCS; /* * Put in the address/control bytes if necessary */ if ((ap->flags & SC_COMP_AC) == 0 || islcp) { PUT_BYTE(ap, buf, 0xff, islcp); fcs = PPP_FCS(fcs, 0xff); PUT_BYTE(ap, buf, 0x03, islcp); fcs = PPP_FCS(fcs, 0x03); } } /* * Once we put in the last byte, we need to put in the FCS * and closing flag, so make sure there is at least 7 bytes * of free space in the output buffer. */ buflim = ap->obuf + OBUFSIZE - 6; while (i < count && buf < buflim) { c = data[i++]; if (i == 1 && c == 0 && (ap->flags & SC_COMP_PROT)) continue; /* compress protocol field */ fcs = PPP_FCS(fcs, c); PUT_BYTE(ap, buf, c, islcp); } if (i < count) { /* * Remember where we are up to in this packet. */ ap->olim = buf; ap->tpkt_pos = i; ap->tfcs = fcs; return 0; } /* * We have finished the packet. Add the FCS and flag. */ fcs = ~fcs; c = fcs & 0xff; PUT_BYTE(ap, buf, c, islcp); c = (fcs >> 8) & 0xff; PUT_BYTE(ap, buf, c, islcp); *buf++ = PPP_FLAG; ap->olim = buf; consume_skb(ap->tpkt); ap->tpkt = NULL; return 1; } /* * Transmit-side routines. */ /* * Send a packet to the peer over an async tty line. * Returns 1 iff the packet was accepted. * If the packet was not accepted, we will call ppp_output_wakeup * at some later time. */ static int ppp_async_send(struct ppp_channel *chan, struct sk_buff *skb) { struct asyncppp *ap = chan->private; ppp_async_push(ap); if (test_and_set_bit(XMIT_FULL, &ap->xmit_flags)) return 0; /* already full */ ap->tpkt = skb; ap->tpkt_pos = 0; ppp_async_push(ap); return 1; } /* * Push as much data as possible out to the tty. */ static int ppp_async_push(struct asyncppp *ap) { int avail, sent, done = 0; struct tty_struct *tty = ap->tty; int tty_stuffed = 0; /* * We can get called recursively here if the tty write * function calls our wakeup function. This can happen * for example on a pty with both the master and slave * set to PPP line discipline. * We use the XMIT_BUSY bit to detect this and get out, * leaving the XMIT_WAKEUP bit set to tell the other * instance that it may now be able to write more now. */ if (test_and_set_bit(XMIT_BUSY, &ap->xmit_flags)) return 0; spin_lock_bh(&ap->xmit_lock); for (;;) { if (test_and_clear_bit(XMIT_WAKEUP, &ap->xmit_flags)) tty_stuffed = 0; if (!tty_stuffed && ap->optr < ap->olim) { avail = ap->olim - ap->optr; set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); sent = tty->ops->write(tty, ap->optr, avail); if (sent < 0) goto flush; /* error, e.g. loss of CD */ ap->optr += sent; if (sent < avail) tty_stuffed = 1; continue; } if (ap->optr >= ap->olim && ap->tpkt) { if (ppp_async_encode(ap)) { /* finished processing ap->tpkt */ clear_bit(XMIT_FULL, &ap->xmit_flags); done = 1; } continue; } /* * We haven't made any progress this time around. * Clear XMIT_BUSY to let other callers in, but * after doing so we have to check if anyone set * XMIT_WAKEUP since we last checked it. If they * did, we should try again to set XMIT_BUSY and go * around again in case XMIT_BUSY was still set when * the other caller tried. */ clear_bit(XMIT_BUSY, &ap->xmit_flags); /* any more work to do? if not, exit the loop */ if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) || (!tty_stuffed && ap->tpkt))) break; /* more work to do, see if we can do it now */ if (test_and_set_bit(XMIT_BUSY, &ap->xmit_flags)) break; } spin_unlock_bh(&ap->xmit_lock); return done; flush: clear_bit(XMIT_BUSY, &ap->xmit_flags); if (ap->tpkt) { kfree_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); done = 1; } ap->optr = ap->olim; spin_unlock_bh(&ap->xmit_lock); return done; } /* * Flush output from our internal buffers. * Called for the TCFLSH ioctl. Can be entered in parallel * but this is covered by the xmit_lock. */ static void ppp_async_flush_output(struct asyncppp *ap) { int done = 0; spin_lock_bh(&ap->xmit_lock); ap->optr = ap->olim; if (ap->tpkt != NULL) { kfree_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); done = 1; } spin_unlock_bh(&ap->xmit_lock); if (done) ppp_output_wakeup(&ap->chan); } /* * Receive-side routines. */ /* see how many ordinary chars there are at the start of buf */ static inline int scan_ordinary(struct asyncppp *ap, const unsigned char *buf, int count) { int i, c; for (i = 0; i < count; ++i) { c = buf[i]; if (c == PPP_ESCAPE || c == PPP_FLAG || (c < 0x20 && (ap->raccm & (1 << c)) != 0)) break; } return i; } /* called when a flag is seen - do end-of-packet processing */ static void process_input_packet(struct asyncppp *ap) { struct sk_buff *skb; unsigned char *p; unsigned int len, fcs; skb = ap->rpkt; if (ap->state & (SC_TOSS | SC_ESCAPE)) goto err; if (skb == NULL) return; /* 0-length packet */ /* check the FCS */ p = skb->data; len = skb->len; if (len < 3) goto err; /* too short */ fcs = PPP_INITFCS; for (; len > 0; --len) fcs = PPP_FCS(fcs, *p++); if (fcs != PPP_GOODFCS) goto err; /* bad FCS */ skb_trim(skb, skb->len - 2); /* check for address/control and protocol compression */ p = skb->data; if (p[0] == PPP_ALLSTATIONS) { /* chop off address/control */ if (p[1] != PPP_UI || skb->len < 3) goto err; p = skb_pull(skb, 2); } /* If protocol field is not compressed, it can be LCP packet */ if (!(p[0] & 0x01)) { unsigned int proto; if (skb->len < 2) goto err; proto = (p[0] << 8) + p[1]; if (proto == PPP_LCP) async_lcp_peek(ap, p, skb->len, 1); } /* queue the frame to be processed */ skb->cb[0] = ap->state; skb_queue_tail(&ap->rqueue, skb); ap->rpkt = NULL; ap->state = 0; return; err: /* frame had an error, remember that, reset SC_TOSS & SC_ESCAPE */ ap->state = SC_PREV_ERROR; if (skb) { /* make skb appear as freshly allocated */ skb_trim(skb, 0); skb_reserve(skb, - skb_headroom(skb)); } } /* Called when the tty driver has data for us. Runs parallel with the other ldisc functions but will not be re-entered */ static void ppp_async_input(struct asyncppp *ap, const u8 *buf, const u8 *flags, int count) { struct sk_buff *skb; int c, i, j, n, s, f; unsigned char *sp; /* update bits used for 8-bit cleanness detection */ if (~ap->rbits & SC_RCV_BITS) { s = 0; for (i = 0; i < count; ++i) { c = buf[i]; if (flags && flags[i] != 0) continue; s |= (c & 0x80)? SC_RCV_B7_1: SC_RCV_B7_0; c = ((c >> 4) ^ c) & 0xf; s |= (0x6996 & (1 << c))? SC_RCV_ODDP: SC_RCV_EVNP; } ap->rbits |= s; } while (count > 0) { /* scan through and see how many chars we can do in bulk */ if ((ap->state & SC_ESCAPE) && buf[0] == PPP_ESCAPE) n = 1; else n = scan_ordinary(ap, buf, count); f = 0; if (flags && (ap->state & SC_TOSS) == 0) { /* check the flags to see if any char had an error */ for (j = 0; j < n; ++j) if ((f = flags[j]) != 0) break; } if (f != 0) { /* start tossing */ ap->state |= SC_TOSS; } else if (n > 0 && (ap->state & SC_TOSS) == 0) { /* stuff the chars in the skb */ skb = ap->rpkt; if (!skb) { skb = dev_alloc_skb(ap->mru + PPP_HDRLEN + 2); if (!skb) goto nomem; ap->rpkt = skb; } if (skb->len == 0) { /* Try to get the payload 4-byte aligned. * This should match the * PPP_ALLSTATIONS/PPP_UI/compressed tests in * process_input_packet, but we do not have * enough chars here to test buf[1] and buf[2]. */ if (buf[0] != PPP_ALLSTATIONS) skb_reserve(skb, 2 + (buf[0] & 1)); } if (n > skb_tailroom(skb)) { /* packet overflowed MRU */ ap->state |= SC_TOSS; } else { sp = skb_put_data(skb, buf, n); if (ap->state & SC_ESCAPE) { sp[0] ^= PPP_TRANS; ap->state &= ~SC_ESCAPE; } } } if (n >= count) break; c = buf[n]; if (flags != NULL && flags[n] != 0) { ap->state |= SC_TOSS; } else if (c == PPP_FLAG) { process_input_packet(ap); } else if (c == PPP_ESCAPE) { ap->state |= SC_ESCAPE; } else if (I_IXON(ap->tty)) { if (c == START_CHAR(ap->tty)) start_tty(ap->tty); else if (c == STOP_CHAR(ap->tty)) stop_tty(ap->tty); } /* otherwise it's a char in the recv ACCM */ ++n; buf += n; if (flags) flags += n; count -= n; } return; nomem: printk(KERN_ERR "PPPasync: no memory (input pkt)\n"); ap->state |= SC_TOSS; } /* * We look at LCP frames going past so that we can notice * and react to the LCP configure-ack from the peer. * In the situation where the peer has been sent a configure-ack * already, LCP is up once it has sent its configure-ack * so the immediately following packet can be sent with the * configured LCP options. This allows us to process the following * packet correctly without pppd needing to respond quickly. * * We only respond to the received configure-ack if we have just * sent a configure-request, and the configure-ack contains the * same data (this is checked using a 16-bit crc of the data). */ #define CONFREQ 1 /* LCP code field values */ #define CONFACK 2 #define LCP_MRU 1 /* LCP option numbers */ #define LCP_ASYNCMAP 2 static void async_lcp_peek(struct asyncppp *ap, unsigned char *data, int len, int inbound) { int dlen, fcs, i, code; u32 val; data += 2; /* skip protocol bytes */ len -= 2; if (len < 4) /* 4 = code, ID, length */ return; code = data[0]; if (code != CONFACK && code != CONFREQ) return; dlen = get_unaligned_be16(data + 2); if (len < dlen) return; /* packet got truncated or length is bogus */ if (code == (inbound? CONFACK: CONFREQ)) { /* * sent confreq or received confack: * calculate the crc of the data from the ID field on. */ fcs = PPP_INITFCS; for (i = 1; i < dlen; ++i) fcs = PPP_FCS(fcs, data[i]); if (!inbound) { /* outbound confreq - remember the crc for later */ ap->lcp_fcs = fcs; return; } /* received confack, check the crc */ fcs ^= ap->lcp_fcs; ap->lcp_fcs = -1; if (fcs != 0) return; } else if (inbound) return; /* not interested in received confreq */ /* process the options in the confack */ data += 4; dlen -= 4; /* data[0] is code, data[1] is length */ while (dlen >= 2 && dlen >= data[1] && data[1] >= 2) { switch (data[0]) { case LCP_MRU: val = get_unaligned_be16(data + 2); if (inbound) ap->mru = val; else ap->chan.mtu = val; break; case LCP_ASYNCMAP: val = get_unaligned_be32(data + 2); if (inbound) ap->raccm = val; else ap->xaccm[0] = val; break; } dlen -= data[1]; data += data[1]; } } static void __exit ppp_async_cleanup(void) { tty_unregister_ldisc(&ppp_ldisc); } module_init(ppp_async_init); module_exit(ppp_async_cleanup); |
| 2 5 4 5 4 3 5 2 3 2 3 3 3 3 4 3 3 2 2 5 3 5 5 3 2 3 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP Illinois congestion control. * Home page: * http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html * * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet_diag.h> #include <asm/div64.h> #include <net/tcp.h> #define ALPHA_SHIFT 7 #define ALPHA_SCALE (1u<<ALPHA_SHIFT) #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 #define BETA_SCALE (1u<<BETA_SHIFT) #define BETA_MIN (BETA_SCALE/8) /* 0.125 */ #define BETA_MAX (BETA_SCALE/2) /* 0.5 */ #define BETA_BASE BETA_MAX static int win_thresh __read_mostly = 15; module_param(win_thresh, int, 0); MODULE_PARM_DESC(win_thresh, "Window threshold for starting adaptive sizing"); static int theta __read_mostly = 5; module_param(theta, int, 0); MODULE_PARM_DESC(theta, "# of fast RTT's before full growth"); /* TCP Illinois Parameters */ struct illinois { u64 sum_rtt; /* sum of rtt's measured within last rtt */ u16 cnt_rtt; /* # of rtts measured within last rtt */ u32 base_rtt; /* min of all rtt in usec */ u32 max_rtt; /* max of all rtt in usec */ u32 end_seq; /* right edge of current RTT */ u32 alpha; /* Additive increase */ u32 beta; /* Muliplicative decrease */ u16 acked; /* # packets acked by current ACK */ u8 rtt_above; /* average rtt has gone above threshold */ u8 rtt_low; /* # of rtts measurements below threshold */ }; static void rtt_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); ca->end_seq = tp->snd_nxt; ca->cnt_rtt = 0; ca->sum_rtt = 0; /* TODO: age max_rtt? */ } static void tcp_illinois_init(struct sock *sk) { struct illinois *ca = inet_csk_ca(sk); ca->alpha = ALPHA_MAX; ca->beta = BETA_BASE; ca->base_rtt = 0x7fffffff; ca->max_rtt = 0; ca->acked = 0; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } /* Measure RTT for each ack. */ static void tcp_illinois_acked(struct sock *sk, const struct ack_sample *sample) { struct illinois *ca = inet_csk_ca(sk); s32 rtt_us = sample->rtt_us; ca->acked = sample->pkts_acked; /* dup ack, no rtt sample */ if (rtt_us < 0) return; /* ignore bogus values, this prevents wraparound in alpha math */ if (rtt_us > RTT_MAX) rtt_us = RTT_MAX; /* keep track of minimum RTT seen so far */ if (ca->base_rtt > rtt_us) ca->base_rtt = rtt_us; /* and max */ if (ca->max_rtt < rtt_us) ca->max_rtt = rtt_us; ++ca->cnt_rtt; ca->sum_rtt += rtt_us; } /* Maximum queuing delay */ static inline u32 max_delay(const struct illinois *ca) { return ca->max_rtt - ca->base_rtt; } /* Average queuing delay */ static inline u32 avg_delay(const struct illinois *ca) { u64 t = ca->sum_rtt; do_div(t, ca->cnt_rtt); return t - ca->base_rtt; } /* * Compute value of alpha used for additive increase. * If small window then use 1.0, equivalent to Reno. * * For larger windows, adjust based on average delay. * A. If average delay is at minimum (we are uncongested), * then use large alpha (10.0) to increase faster. * B. If average delay is at maximum (getting congested) * then use small alpha (0.3) * * The result is a convex window growth curve. */ static u32 alpha(struct illinois *ca, u32 da, u32 dm) { u32 d1 = dm / 100; /* Low threshold */ if (da <= d1) { /* If never got out of low delay zone, then use max */ if (!ca->rtt_above) return ALPHA_MAX; /* Wait for 5 good RTT's before allowing alpha to go alpha max. * This prevents one good RTT from causing sudden window increase. */ if (++ca->rtt_low < theta) return ca->alpha; ca->rtt_low = 0; ca->rtt_above = 0; return ALPHA_MAX; } ca->rtt_above = 1; /* * Based on: * * (dm - d1) amin amax * k1 = ------------------- * amax - amin * * (dm - d1) amin * k2 = ---------------- - d1 * amax - amin * * k1 * alpha = ---------- * k2 + da */ dm -= d1; da -= d1; return (dm * ALPHA_MAX) / (dm + (da * (ALPHA_MAX - ALPHA_MIN)) / ALPHA_MIN); } /* * Beta used for multiplicative decrease. * For small window sizes returns same value as Reno (0.5) * * If delay is small (10% of max) then beta = 1/8 * If delay is up to 80% of max then beta = 1/2 * In between is a linear function */ static u32 beta(u32 da, u32 dm) { u32 d2, d3; d2 = dm / 10; if (da <= d2) return BETA_MIN; d3 = (8 * dm) / 10; if (da >= d3 || d3 <= d2) return BETA_MAX; /* * Based on: * * bmin d3 - bmax d2 * k3 = ------------------- * d3 - d2 * * bmax - bmin * k4 = ------------- * d3 - d2 * * b = k3 + k4 da */ return (BETA_MIN * d3 - BETA_MAX * d2 + (BETA_MAX - BETA_MIN) * da) / (d3 - d2); } /* Update alpha and beta values once per RTT */ static void update_params(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (tcp_snd_cwnd(tp) < win_thresh) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; } else if (ca->cnt_rtt > 0) { u32 dm = max_delay(ca); u32 da = avg_delay(ca); ca->alpha = alpha(ca, da, dm); ca->beta = beta(da, dm); } rtt_reset(sk); } /* * In case of loss, reset to default values */ static void tcp_illinois_state(struct sock *sk, u8 new_state) { struct illinois *ca = inet_csk_ca(sk); if (new_state == TCP_CA_Loss) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } } /* * Increase window in response to successful acknowledgment. */ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (after(ack, ca->end_seq)) update_params(sk); /* RFC2861 only increase cwnd if fully utilized */ if (!tcp_is_cwnd_limited(sk)) return; /* In slow start */ if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { u32 delta; /* snd_cwnd_cnt is # of packets since last cwnd increment */ tp->snd_cwnd_cnt += ca->acked; ca->acked = 1; /* This is close approximation of: * tp->snd_cwnd += alpha/tp->snd_cwnd */ delta = (tp->snd_cwnd_cnt * ca->alpha) >> ALPHA_SHIFT; if (delta >= tcp_snd_cwnd(tp)) { tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp) + delta / tcp_snd_cwnd(tp), (u32)tp->snd_cwnd_clamp)); tp->snd_cwnd_cnt = 0; } } } static u32 tcp_illinois_ssthresh(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); u32 decr; /* Multiplicative decrease */ decr = (tcp_snd_cwnd(tp) * ca->beta) >> BETA_SHIFT; return max(tcp_snd_cwnd(tp) - decr, 2U); } /* Extract info for Tcp socket info provided via netlink. */ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct illinois *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = ca->cnt_rtt; info->vegas.tcpv_minrtt = ca->base_rtt; info->vegas.tcpv_rtt = 0; if (info->vegas.tcpv_rttcnt > 0) { u64 t = ca->sum_rtt; do_div(t, info->vegas.tcpv_rttcnt); info->vegas.tcpv_rtt = t; } *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } static struct tcp_congestion_ops tcp_illinois __read_mostly = { .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, .pkts_acked = tcp_illinois_acked, .owner = THIS_MODULE, .name = "illinois", }; static int __init tcp_illinois_register(void) { BUILD_BUG_ON(sizeof(struct illinois) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_illinois); } static void __exit tcp_illinois_unregister(void) { tcp_unregister_congestion_control(&tcp_illinois); } module_init(tcp_illinois_register); module_exit(tcp_illinois_unregister); MODULE_AUTHOR("Stephen Hemminger, Shao Liu"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP Illinois"); MODULE_VERSION("1.0"); |
| 25 25 25 7 7 7 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xt_connmark - Netfilter module to operate on connection marks * * Copyright (C) 2002,2004 MARA Systems AB <https://www.marasystems.com> * by Henrik Nordstrom <hno@marasystems.com> * Copyright © CC Computer Consultants GmbH, 2007 - 2008 * Jan Engelhardt <jengelh@medozas.de> */ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_connmark.h> MODULE_AUTHOR("Henrik Nordstrom <hno@marasystems.com>"); MODULE_DESCRIPTION("Xtables: connection mark operations"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_CONNMARK"); MODULE_ALIAS("ip6t_CONNMARK"); MODULE_ALIAS("ipt_connmark"); MODULE_ALIAS("ip6t_connmark"); static unsigned int connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) { enum ip_conntrack_info ctinfo; u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; u_int32_t oldmark; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) return XT_CONTINUE; switch (info->mode) { case XT_CONNMARK_SET: oldmark = READ_ONCE(ct->mark); newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits; if (READ_ONCE(ct->mark) != newmark) { WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_SAVE: new_targetmark = (skb->mark & info->nfmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else new_targetmark <<= info->shift_bits; newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; if (READ_ONCE(ct->mark) != newmark) { WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else new_targetmark <<= info->shift_bits; newmark = (skb->mark & ~info->nfmask) ^ new_targetmark; skb->mark = newmark; break; } return XT_CONTINUE; } static unsigned int connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo1 *info = par->targinfo; const struct xt_connmark_tginfo2 info2 = { .ctmark = info->ctmark, .ctmask = info->ctmask, .nfmask = info->nfmask, .mode = info->mode, }; return connmark_tg_shift(skb, &info2); } static unsigned int connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo2 *info = par->targinfo; return connmark_tg_shift(skb, info); } static int connmark_tg_check(const struct xt_tgchk_param *par) { int ret; ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) pr_info_ratelimited("cannot load conntrack support for proto=%u\n", par->family); return ret; } static void connmark_tg_destroy(const struct xt_tgdtor_param *par) { nf_ct_netns_put(par->net, par->family); } static bool connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_connmark_mtinfo1 *info = par->matchinfo; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) return false; return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; } static int connmark_mt_check(const struct xt_mtchk_param *par) { int ret; ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) pr_info_ratelimited("cannot load conntrack support for proto=%u\n", par->family); return ret; } static void connmark_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_netns_put(par->net, par->family); } static struct xt_target connmark_tg_reg[] __read_mostly = { { .name = "CONNMARK", .revision = 1, .family = NFPROTO_IPV4, .checkentry = connmark_tg_check, .target = connmark_tg, .targetsize = sizeof(struct xt_connmark_tginfo1), .destroy = connmark_tg_destroy, .me = THIS_MODULE, }, { .name = "CONNMARK", .revision = 2, .family = NFPROTO_IPV4, .checkentry = connmark_tg_check, .target = connmark_tg_v2, .targetsize = sizeof(struct xt_connmark_tginfo2), .destroy = connmark_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "CONNMARK", .revision = 1, .family = NFPROTO_IPV6, .checkentry = connmark_tg_check, .target = connmark_tg, .targetsize = sizeof(struct xt_connmark_tginfo1), .destroy = connmark_tg_destroy, .me = THIS_MODULE, }, { .name = "CONNMARK", .revision = 2, .family = NFPROTO_IPV6, .checkentry = connmark_tg_check, .target = connmark_tg_v2, .targetsize = sizeof(struct xt_connmark_tginfo2), .destroy = connmark_tg_destroy, .me = THIS_MODULE, }, #endif }; static struct xt_match connmark_mt_reg __read_mostly = { .name = "connmark", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = connmark_mt_check, .match = connmark_mt, .matchsize = sizeof(struct xt_connmark_mtinfo1), .destroy = connmark_mt_destroy, .me = THIS_MODULE, }; static int __init connmark_mt_init(void) { int ret; ret = xt_register_targets(connmark_tg_reg, ARRAY_SIZE(connmark_tg_reg)); if (ret < 0) return ret; ret = xt_register_match(&connmark_mt_reg); if (ret < 0) { xt_unregister_targets(connmark_tg_reg, ARRAY_SIZE(connmark_tg_reg)); return ret; } return 0; } static void __exit connmark_mt_exit(void) { xt_unregister_match(&connmark_mt_reg); xt_unregister_targets(connmark_tg_reg, ARRAY_SIZE(connmark_tg_reg)); } module_init(connmark_mt_init); module_exit(connmark_mt_exit); |
| 53 79 53 53 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ #include "hash.h" #include "main.h" #include <linux/gfp.h> #include <linux/lockdep.h> #include <linux/slab.h> /* clears the hash */ static void batadv_hash_init(struct batadv_hashtable *hash) { u32 i; for (i = 0; i < hash->size; i++) { INIT_HLIST_HEAD(&hash->table[i]); spin_lock_init(&hash->list_locks[i]); } atomic_set(&hash->generation, 0); } /** * batadv_hash_destroy() - Free only the hashtable and the hash itself * @hash: hash object to destroy */ void batadv_hash_destroy(struct batadv_hashtable *hash) { kfree(hash->list_locks); kfree(hash->table); kfree(hash); } /** * batadv_hash_new() - Allocates and clears the hashtable * @size: number of hash buckets to allocate * * Return: newly allocated hashtable, NULL on errors */ struct batadv_hashtable *batadv_hash_new(u32 size) { struct batadv_hashtable *hash; hash = kmalloc(sizeof(*hash), GFP_ATOMIC); if (!hash) return NULL; hash->table = kmalloc_array(size, sizeof(*hash->table), GFP_ATOMIC); if (!hash->table) goto free_hash; hash->list_locks = kmalloc_array(size, sizeof(*hash->list_locks), GFP_ATOMIC); if (!hash->list_locks) goto free_table; hash->size = size; batadv_hash_init(hash); return hash; free_table: kfree(hash->table); free_hash: kfree(hash); return NULL; } /** * batadv_hash_set_lock_class() - Set specific lockdep class for hash spinlocks * @hash: hash object to modify * @key: lockdep class key address */ void batadv_hash_set_lock_class(struct batadv_hashtable *hash, struct lock_class_key *key) { u32 i; for (i = 0; i < hash->size; i++) lockdep_set_class(&hash->list_locks[i], key); } |
| 11 6 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSR_H #define _ASM_X86_MSR_H #include "msr-index.h" #ifndef __ASSEMBLER__ #include <asm/asm.h> #include <asm/errno.h> #include <asm/cpumask.h> #include <uapi/asm/msr.h> #include <asm/shared/msr.h> #include <linux/percpu.h> struct msr_info { u32 msr_no; struct msr reg; struct msr __percpu *msrs; int err; }; struct msr_regs_info { u32 *regs; int err; }; struct saved_msr { bool valid; struct msr_info info; }; struct saved_msrs { unsigned int num; struct saved_msr *array; }; /* * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A" * constraint has different meanings. For i386, "A" means exactly * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead, * it means rax *or* rdx. */ #ifdef CONFIG_X86_64 /* Using 64-bit values saves one instruction clearing the high half of low */ #define DECLARE_ARGS(val, low, high) unsigned long low, high #define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32) #define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high) #else #define DECLARE_ARGS(val, low, high) unsigned long long val #define EAX_EDX_VAL(val, low, high) (val) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif /* * Be very careful with includes. This header is prone to include loops. */ #include <asm/atomic.h> #include <linux/tracepoint-defs.h> #ifdef CONFIG_TRACEPOINTS DECLARE_TRACEPOINT(read_msr); DECLARE_TRACEPOINT(write_msr); DECLARE_TRACEPOINT(rdpmc); extern void do_trace_write_msr(unsigned int msr, u64 val, int failed); extern void do_trace_read_msr(unsigned int msr, u64 val, int failed); extern void do_trace_rdpmc(unsigned int msr, u64 val, int failed); #else static inline void do_trace_write_msr(unsigned int msr, u64 val, int failed) {} static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {} static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} #endif /* * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR * accessors and should not have any tracing or other functionality piggybacking * on them - those are *purely* for accessing MSRs and nothing more. So don't even * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); asm volatile("1: rdmsr\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR) : EAX_EDX_RET(val, low, high) : "c" (msr)); return EAX_EDX_VAL(val, low, high); } static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a"(low), "d" (high) : "memory"); } #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ (void)((val1) = (u32)__val); \ (void)((val2) = (u32)(__val >> 32)); \ } while (0) #define native_wrmsr(msr, low, high) \ __wrmsr(msr, low, high) #define native_wrmsrl(msr, val) \ __wrmsr((msr), (u32)((u64)(val)), \ (u32)((u64)(val) >> 32)) static inline unsigned long long native_read_msr(unsigned int msr) { unsigned long long val; val = __rdmsr(msr); if (tracepoint_enabled(read_msr)) do_trace_read_msr(msr, val, 0); return val; } static inline unsigned long long native_read_msr_safe(unsigned int msr, int *err) { DECLARE_ARGS(val, low, high); asm volatile("1: rdmsr ; xor %[err],%[err]\n" "2:\n\t" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err]) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) : "c" (msr)); if (tracepoint_enabled(read_msr)) do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err); return EAX_EDX_VAL(val, low, high); } /* Can be uninlined because referenced by paravirt */ static inline void notrace native_write_msr(unsigned int msr, u32 low, u32 high) { __wrmsr(msr, low, high); if (tracepoint_enabled(write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } /* Can be uninlined because referenced by paravirt */ static inline int notrace native_write_msr_safe(unsigned int msr, u32 low, u32 high) { int err; asm volatile("1: wrmsr ; xor %[err],%[err]\n" "2:\n\t" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err]) : [err] "=a" (err) : "c" (msr), "0" (low), "d" (high) : "memory"); if (tracepoint_enabled(write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } extern int rdmsr_safe_regs(u32 regs[8]); extern int wrmsr_safe_regs(u32 regs[8]); /** * rdtsc() - returns the current TSC without ordering constraints * * rdtsc() returns the result of RDTSC as a 64-bit integer. The * only ordering constraint it supplies is the ordering implied by * "asm volatile": it will put the RDTSC in the place you expect. The * CPU can and will speculatively execute that RDTSC, though, so the * results can be non-monotonic if compared on different CPUs. */ static __always_inline unsigned long long rdtsc(void) { DECLARE_ARGS(val, low, high); asm volatile("rdtsc" : EAX_EDX_RET(val, low, high)); return EAX_EDX_VAL(val, low, high); } /** * rdtsc_ordered() - read the current TSC in program order * * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer. * It is ordered like a load to a global in-memory counter. It should * be impossible to observe non-monotonic rdtsc_unordered() behavior * across multiple CPUs as long as the TSC is synced. */ static __always_inline unsigned long long rdtsc_ordered(void) { DECLARE_ARGS(val, low, high); /* * The RDTSC instruction is not ordered relative to memory * access. The Intel SDM and the AMD APM are both vague on this * point, but empirically an RDTSC instruction can be * speculatively executed before prior loads. An RDTSC * immediately after an appropriate barrier appears to be * ordered as a normal load, that is, it provides the same * ordering guarantees as reading from a global memory location * that some other imaginary CPU is updating continuously with a * time stamp. * * Thus, use the preferred barrier on the respective CPU, aiming for * RDTSCP as the default. */ asm volatile(ALTERNATIVE_2("rdtsc", "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC, "rdtscp", X86_FEATURE_RDTSCP) : EAX_EDX_RET(val, low, high) /* RDTSCP clobbers ECX with MSR_TSC_AUX. */ :: "ecx"); return EAX_EDX_VAL(val, low, high); } static inline unsigned long long native_read_pmc(int counter) { DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); if (tracepoint_enabled(rdpmc)) do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #include <linux/errno.h> /* * Access to machine-specific registers (available on 586 and better only) * Note: the rd* operations modify the parameters directly (without using * pointer indirection), this allows gcc to optimize better */ #define rdmsr(msr, low, high) \ do { \ u64 __val = native_read_msr((msr)); \ (void)((low) = (u32)__val); \ (void)((high) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(unsigned int msr, u32 low, u32 high) { native_write_msr(msr, low, high); } #define rdmsrl(msr, val) \ ((val) = native_read_msr((msr))) static inline void wrmsrl(unsigned int msr, u64 val) { native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); } /* wrmsr with exception handling */ static inline int wrmsr_safe(unsigned int msr, u32 low, u32 high) { return native_write_msr_safe(msr, low, high); } /* rdmsr with exception handling */ #define rdmsr_safe(msr, low, high) \ ({ \ int __err; \ u64 __val = native_read_msr_safe((msr), &__err); \ (*low) = (u32)__val; \ (*high) = (u32)(__val >> 32); \ __err; \ }) static inline int rdmsrl_safe(unsigned int msr, unsigned long long *p) { int err; *p = native_read_msr_safe(msr, &err); return err; } #define rdpmc(counter, low, high) \ do { \ u64 _l = native_read_pmc((counter)); \ (low) = (u32)_l; \ (high) = (u32)(_l >> 32); \ } while (0) #define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) #endif /* !CONFIG_PARAVIRT_XXL */ /* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */ #define WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) /* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */ static __always_inline void wrmsrns(u32 msr, u64 val) { /* * WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant * DS prefix to avoid a trailing NOP. */ asm volatile("1: " ALTERNATIVE("ds wrmsr", WRMSRNS, X86_FEATURE_WRMSRNS) "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32))); } /* * 64-bit version of wrmsr_safe(): */ static inline int wrmsrl_safe(u32 msr, u64 val) { return wrmsr_safe(msr, (u32)val, (u32)(val >> 32)); } struct msr __percpu *msrs_alloc(void); void msrs_free(struct msr __percpu *msrs); int msr_set_bit(u32 msr, u8 bit); int msr_clear_bit(u32 msr, u8 bit); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q); void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { rdmsr(msr_no, *l, *h); return 0; } static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { wrmsr(msr_no, l, h); return 0; } static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { rdmsrl(msr_no, *q); return 0; } static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { wrmsrl(msr_no, q); return 0; } static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr __percpu *msrs) { rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h)); } static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr __percpu *msrs) { wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h)); } static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { return rdmsr_safe(msr_no, l, h); } static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { return rdmsrl_safe(msr_no, q); } static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { return wrmsrl_safe(msr_no, q); } static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return rdmsr_safe_regs(regs); } static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return wrmsr_safe_regs(regs); } #endif /* CONFIG_SMP */ #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_MSR_H */ |
| 2 2 33 33 33 33 2 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 | /* * Copyright (c) 2004, 2005 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004, 2005 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2005 Intel Corporation. All rights reserved. * Copyright (c) 2004, 2005 Topspin Corporation. All rights reserved. * Copyright (c) 2004-2007 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/slab.h> #include <linux/string.h> #include "agent.h" #include "smi.h" #include "mad_priv.h" #define SPFX "ib_agent: " struct ib_agent_port_private { struct list_head port_list; struct ib_mad_agent *agent[2]; }; static DEFINE_SPINLOCK(ib_agent_port_list_lock); static LIST_HEAD(ib_agent_port_list); static struct ib_agent_port_private * __ib_get_agent_port(const struct ib_device *device, int port_num) { struct ib_agent_port_private *entry; list_for_each_entry(entry, &ib_agent_port_list, port_list) { /* Need to check both agent[0] and agent[1], as an agent port * may only have one of them */ if (entry->agent[0] && entry->agent[0]->device == device && entry->agent[0]->port_num == port_num) return entry; if (entry->agent[1] && entry->agent[1]->device == device && entry->agent[1]->port_num == port_num) return entry; } return NULL; } static struct ib_agent_port_private * ib_get_agent_port(const struct ib_device *device, int port_num) { struct ib_agent_port_private *entry; unsigned long flags; spin_lock_irqsave(&ib_agent_port_list_lock, flags); entry = __ib_get_agent_port(device, port_num); spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); return entry; } void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh, const struct ib_wc *wc, const struct ib_device *device, int port_num, int qpn, size_t resp_mad_len, bool opa) { struct ib_agent_port_private *port_priv; struct ib_mad_agent *agent; struct ib_mad_send_buf *send_buf; struct ib_ah *ah; struct ib_mad_send_wr_private *mad_send_wr; if (rdma_cap_ib_switch(device)) port_priv = ib_get_agent_port(device, 0); else port_priv = ib_get_agent_port(device, port_num); if (!port_priv) { dev_err(&device->dev, "Unable to find port agent\n"); return; } agent = port_priv->agent[qpn]; ah = ib_create_ah_from_wc(agent->qp->pd, wc, grh, port_num); if (IS_ERR(ah)) { dev_err(&device->dev, "ib_create_ah_from_wc error %ld\n", PTR_ERR(ah)); return; } if (opa && mad_hdr->base_version != OPA_MGMT_BASE_VERSION) resp_mad_len = IB_MGMT_MAD_SIZE; send_buf = ib_create_send_mad(agent, wc->src_qp, wc->pkey_index, 0, IB_MGMT_MAD_HDR, resp_mad_len - IB_MGMT_MAD_HDR, GFP_KERNEL, mad_hdr->base_version); if (IS_ERR(send_buf)) { dev_err(&device->dev, "ib_create_send_mad error\n"); goto err1; } memcpy(send_buf->mad, mad_hdr, resp_mad_len); send_buf->ah = ah; if (rdma_cap_ib_switch(device)) { mad_send_wr = container_of(send_buf, struct ib_mad_send_wr_private, send_buf); mad_send_wr->send_wr.port_num = port_num; } if (ib_post_send_mad(send_buf, NULL)) { dev_err(&device->dev, "ib_post_send_mad error\n"); goto err2; } return; err2: ib_free_send_mad(send_buf); err1: rdma_destroy_ah(ah, RDMA_DESTROY_AH_SLEEPABLE); } static void agent_send_handler(struct ib_mad_agent *mad_agent, struct ib_mad_send_wc *mad_send_wc) { rdma_destroy_ah(mad_send_wc->send_buf->ah, RDMA_DESTROY_AH_SLEEPABLE); ib_free_send_mad(mad_send_wc->send_buf); } int ib_agent_port_open(struct ib_device *device, int port_num) { struct ib_agent_port_private *port_priv; unsigned long flags; int ret; /* Create new device info */ port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL); if (!port_priv) { ret = -ENOMEM; goto error1; } if (rdma_cap_ib_smi(device, port_num)) { /* Obtain send only MAD agent for SMI QP */ port_priv->agent[0] = ib_register_mad_agent(device, port_num, IB_QPT_SMI, NULL, 0, &agent_send_handler, NULL, NULL, 0); if (IS_ERR(port_priv->agent[0])) { ret = PTR_ERR(port_priv->agent[0]); goto error2; } } if (rdma_cap_ib_cm(device, port_num)) { /* Obtain send only MAD agent for GSI QP */ port_priv->agent[1] = ib_register_mad_agent(device, port_num, IB_QPT_GSI, NULL, 0, &agent_send_handler, NULL, NULL, 0); if (IS_ERR(port_priv->agent[1])) { ret = PTR_ERR(port_priv->agent[1]); goto error3; } } spin_lock_irqsave(&ib_agent_port_list_lock, flags); list_add_tail(&port_priv->port_list, &ib_agent_port_list); spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); return 0; error3: if (port_priv->agent[0]) ib_unregister_mad_agent(port_priv->agent[0]); error2: kfree(port_priv); error1: return ret; } int ib_agent_port_close(struct ib_device *device, int port_num) { struct ib_agent_port_private *port_priv; unsigned long flags; spin_lock_irqsave(&ib_agent_port_list_lock, flags); port_priv = __ib_get_agent_port(device, port_num); if (port_priv == NULL) { spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); dev_err(&device->dev, "Port %d not found\n", port_num); return -ENODEV; } list_del(&port_priv->port_list); spin_unlock_irqrestore(&ib_agent_port_list_lock, flags); if (port_priv->agent[1]) ib_unregister_mad_agent(port_priv->agent[1]); if (port_priv->agent[0]) ib_unregister_mad_agent(port_priv->agent[0]); kfree(port_priv); return 0; } |
| 3422 2371 3405 3420 3422 194 3313 3425 3425 3420 2371 2371 2370 253 3103 3110 2371 1121 2275 2275 2371 253 253 253 253 253 215 1137 1136 106 1222 317 1000 1222 1013 1224 319 1213 1224 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * klist.c - Routines for manipulating klists. * * Copyright (C) 2005 Patrick Mochel * * This klist interface provides a couple of structures that wrap around * struct list_head to provide explicit list "head" (struct klist) and list * "node" (struct klist_node) objects. For struct klist, a spinlock is * included that protects access to the actual list itself. struct * klist_node provides a pointer to the klist that owns it and a kref * reference count that indicates the number of current users of that node * in the list. * * The entire point is to provide an interface for iterating over a list * that is safe and allows for modification of the list during the * iteration (e.g. insertion and removal), including modification of the * current node on the list. * * It works using a 3rd object type - struct klist_iter - that is declared * and initialized before an iteration. klist_next() is used to acquire the * next element in the list. It returns NULL if there are no more items. * Internally, that routine takes the klist's lock, decrements the * reference count of the previous klist_node and increments the count of * the next klist_node. It then drops the lock and returns. * * There are primitives for adding and removing nodes to/from a klist. * When deleting, klist_del() will simply decrement the reference count. * Only when the count goes to 0 is the node removed from the list. * klist_remove() will try to delete the node from the list and block until * it is actually removed. This is useful for objects (like devices) that * have been removed from the system and must be freed (but must wait until * all accessors have finished). */ #include <linux/klist.h> #include <linux/export.h> #include <linux/sched.h> /* * Use the lowest bit of n_klist to mark deleted nodes and exclude * dead ones from iteration. */ #define KNODE_DEAD 1LU #define KNODE_KLIST_MASK ~KNODE_DEAD static struct klist *knode_klist(struct klist_node *knode) { return (struct klist *) ((unsigned long)knode->n_klist & KNODE_KLIST_MASK); } static bool knode_dead(struct klist_node *knode) { return (unsigned long)knode->n_klist & KNODE_DEAD; } static void knode_set_klist(struct klist_node *knode, struct klist *klist) { knode->n_klist = klist; /* no knode deserves to start its life dead */ WARN_ON(knode_dead(knode)); } static void knode_kill(struct klist_node *knode) { /* and no knode should die twice ever either, see we're very humane */ WARN_ON(knode_dead(knode)); *(unsigned long *)&knode->n_klist |= KNODE_DEAD; } /** * klist_init - Initialize a klist structure. * @k: The klist we're initializing. * @get: The get function for the embedding object (NULL if none) * @put: The put function for the embedding object (NULL if none) * * Initialises the klist structure. If the klist_node structures are * going to be embedded in refcounted objects (necessary for safe * deletion) then the get/put arguments are used to initialise * functions that take and release references on the embedding * objects. */ void klist_init(struct klist *k, void (*get)(struct klist_node *), void (*put)(struct klist_node *)) { INIT_LIST_HEAD(&k->k_list); spin_lock_init(&k->k_lock); k->get = get; k->put = put; } EXPORT_SYMBOL_GPL(klist_init); static void add_head(struct klist *k, struct klist_node *n) { spin_lock(&k->k_lock); list_add(&n->n_node, &k->k_list); spin_unlock(&k->k_lock); } static void add_tail(struct klist *k, struct klist_node *n) { spin_lock(&k->k_lock); list_add_tail(&n->n_node, &k->k_list); spin_unlock(&k->k_lock); } static void klist_node_init(struct klist *k, struct klist_node *n) { INIT_LIST_HEAD(&n->n_node); kref_init(&n->n_ref); knode_set_klist(n, k); if (k->get) k->get(n); } /** * klist_add_head - Initialize a klist_node and add it to front. * @n: node we're adding. * @k: klist it's going on. */ void klist_add_head(struct klist_node *n, struct klist *k) { klist_node_init(k, n); add_head(k, n); } EXPORT_SYMBOL_GPL(klist_add_head); /** * klist_add_tail - Initialize a klist_node and add it to back. * @n: node we're adding. * @k: klist it's going on. */ void klist_add_tail(struct klist_node *n, struct klist *k) { klist_node_init(k, n); add_tail(k, n); } EXPORT_SYMBOL_GPL(klist_add_tail); /** * klist_add_behind - Init a klist_node and add it after an existing node * @n: node we're adding. * @pos: node to put @n after */ void klist_add_behind(struct klist_node *n, struct klist_node *pos) { struct klist *k = knode_klist(pos); klist_node_init(k, n); spin_lock(&k->k_lock); list_add(&n->n_node, &pos->n_node); spin_unlock(&k->k_lock); } EXPORT_SYMBOL_GPL(klist_add_behind); /** * klist_add_before - Init a klist_node and add it before an existing node * @n: node we're adding. * @pos: node to put @n after */ void klist_add_before(struct klist_node *n, struct klist_node *pos) { struct klist *k = knode_klist(pos); klist_node_init(k, n); spin_lock(&k->k_lock); list_add_tail(&n->n_node, &pos->n_node); spin_unlock(&k->k_lock); } EXPORT_SYMBOL_GPL(klist_add_before); struct klist_waiter { struct list_head list; struct klist_node *node; struct task_struct *process; int woken; }; static DEFINE_SPINLOCK(klist_remove_lock); static LIST_HEAD(klist_remove_waiters); static void klist_release(struct kref *kref) { struct klist_waiter *waiter, *tmp; struct klist_node *n = container_of(kref, struct klist_node, n_ref); WARN_ON(!knode_dead(n)); list_del(&n->n_node); spin_lock(&klist_remove_lock); list_for_each_entry_safe(waiter, tmp, &klist_remove_waiters, list) { if (waiter->node != n) continue; list_del(&waiter->list); waiter->woken = 1; mb(); wake_up_process(waiter->process); } spin_unlock(&klist_remove_lock); knode_set_klist(n, NULL); } static int klist_dec_and_del(struct klist_node *n) { return kref_put(&n->n_ref, klist_release); } static void klist_put(struct klist_node *n, bool kill) { struct klist *k = knode_klist(n); void (*put)(struct klist_node *) = k->put; spin_lock(&k->k_lock); if (kill) knode_kill(n); if (!klist_dec_and_del(n)) put = NULL; spin_unlock(&k->k_lock); if (put) put(n); } /** * klist_del - Decrement the reference count of node and try to remove. * @n: node we're deleting. */ void klist_del(struct klist_node *n) { klist_put(n, true); } EXPORT_SYMBOL_GPL(klist_del); /** * klist_remove - Decrement the refcount of node and wait for it to go away. * @n: node we're removing. */ void klist_remove(struct klist_node *n) { struct klist_waiter waiter; waiter.node = n; waiter.process = current; waiter.woken = 0; spin_lock(&klist_remove_lock); list_add(&waiter.list, &klist_remove_waiters); spin_unlock(&klist_remove_lock); klist_del(n); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (waiter.woken) break; schedule(); } __set_current_state(TASK_RUNNING); } EXPORT_SYMBOL_GPL(klist_remove); /** * klist_node_attached - Say whether a node is bound to a list or not. * @n: Node that we're testing. */ int klist_node_attached(struct klist_node *n) { return (n->n_klist != NULL); } EXPORT_SYMBOL_GPL(klist_node_attached); /** * klist_iter_init_node - Initialize a klist_iter structure. * @k: klist we're iterating. * @i: klist_iter we're filling. * @n: node to start with. * * Similar to klist_iter_init(), but starts the action off with @n, * instead of with the list head. */ void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n) { i->i_klist = k; i->i_cur = NULL; if (n && kref_get_unless_zero(&n->n_ref)) i->i_cur = n; } EXPORT_SYMBOL_GPL(klist_iter_init_node); /** * klist_iter_init - Iniitalize a klist_iter structure. * @k: klist we're iterating. * @i: klist_iter structure we're filling. * * Similar to klist_iter_init_node(), but start with the list head. */ void klist_iter_init(struct klist *k, struct klist_iter *i) { klist_iter_init_node(k, i, NULL); } EXPORT_SYMBOL_GPL(klist_iter_init); /** * klist_iter_exit - Finish a list iteration. * @i: Iterator structure. * * Must be called when done iterating over list, as it decrements the * refcount of the current node. Necessary in case iteration exited before * the end of the list was reached, and always good form. */ void klist_iter_exit(struct klist_iter *i) { if (i->i_cur) { klist_put(i->i_cur, false); i->i_cur = NULL; } } EXPORT_SYMBOL_GPL(klist_iter_exit); static struct klist_node *to_klist_node(struct list_head *n) { return container_of(n, struct klist_node, n_node); } /** * klist_prev - Ante up prev node in list. * @i: Iterator structure. * * First grab list lock. Decrement the reference count of the previous * node, if there was one. Grab the prev node, increment its reference * count, drop the lock, and return that prev node. */ struct klist_node *klist_prev(struct klist_iter *i) { void (*put)(struct klist_node *) = i->i_klist->put; struct klist_node *last = i->i_cur; struct klist_node *prev; unsigned long flags; spin_lock_irqsave(&i->i_klist->k_lock, flags); if (last) { prev = to_klist_node(last->n_node.prev); if (!klist_dec_and_del(last)) put = NULL; } else prev = to_klist_node(i->i_klist->k_list.prev); i->i_cur = NULL; while (prev != to_klist_node(&i->i_klist->k_list)) { if (likely(!knode_dead(prev))) { kref_get(&prev->n_ref); i->i_cur = prev; break; } prev = to_klist_node(prev->n_node.prev); } spin_unlock_irqrestore(&i->i_klist->k_lock, flags); if (put && last) put(last); return i->i_cur; } EXPORT_SYMBOL_GPL(klist_prev); /** * klist_next - Ante up next node in list. * @i: Iterator structure. * * First grab list lock. Decrement the reference count of the previous * node, if there was one. Grab the next node, increment its reference * count, drop the lock, and return that next node. */ struct klist_node *klist_next(struct klist_iter *i) { void (*put)(struct klist_node *) = i->i_klist->put; struct klist_node *last = i->i_cur; struct klist_node *next; unsigned long flags; spin_lock_irqsave(&i->i_klist->k_lock, flags); if (last) { next = to_klist_node(last->n_node.next); if (!klist_dec_and_del(last)) put = NULL; } else next = to_klist_node(i->i_klist->k_list.next); i->i_cur = NULL; while (next != to_klist_node(&i->i_klist->k_list)) { if (likely(!knode_dead(next))) { kref_get(&next->n_ref); i->i_cur = next; break; } next = to_klist_node(next->n_node.next); } spin_unlock_irqrestore(&i->i_klist->k_lock, flags); if (put && last) put(last); return i->i_cur; } EXPORT_SYMBOL_GPL(klist_next); |
| 17 17 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 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 | /* inflate.c -- zlib decompression * Copyright (C) 1995-2005 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h * * Based on zlib 1.2.3 but modified for the Linux Kernel by * Richard Purdie <richard@openedhand.com> * * Changes mainly for static instead of dynamic memory allocation * */ #include <linux/zutil.h> #include "inftrees.h" #include "inflate.h" #include "inffast.h" #include "infutil.h" /* architecture-specific bits */ #ifdef CONFIG_ZLIB_DFLTCC # include "../zlib_dfltcc/dfltcc_inflate.h" #else #define INFLATE_RESET_HOOK(strm) do {} while (0) #define INFLATE_TYPEDO_HOOK(strm, flush) do {} while (0) #define INFLATE_NEED_UPDATEWINDOW(strm) 1 #define INFLATE_NEED_CHECKSUM(strm) 1 #endif int zlib_inflate_workspacesize(void) { return sizeof(struct inflate_workspace); } int zlib_inflateReset(z_streamp strm) { struct inflate_state *state; if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR; state = (struct inflate_state *)strm->state; strm->total_in = strm->total_out = state->total = 0; strm->msg = NULL; strm->adler = 1; /* to support ill-conceived Java test suite */ state->mode = HEAD; state->last = 0; state->havedict = 0; state->dmax = 32768U; state->hold = 0; state->bits = 0; state->lencode = state->distcode = state->next = state->codes; /* Initialise Window */ state->wsize = 1U << state->wbits; state->write = 0; state->whave = 0; INFLATE_RESET_HOOK(strm); return Z_OK; } int zlib_inflateInit2(z_streamp strm, int windowBits) { struct inflate_state *state; if (strm == NULL) return Z_STREAM_ERROR; strm->msg = NULL; /* in case we return an error */ state = &WS(strm)->inflate_state; strm->state = (struct internal_state *)state; if (windowBits < 0) { state->wrap = 0; windowBits = -windowBits; } else { state->wrap = (windowBits >> 4) + 1; } if (windowBits < 8 || windowBits > 15) { return Z_STREAM_ERROR; } state->wbits = (unsigned)windowBits; #ifdef CONFIG_ZLIB_DFLTCC /* * DFLTCC requires the window to be page aligned. * Thus, we overallocate and take the aligned portion of the buffer. */ state->window = PTR_ALIGN(&WS(strm)->working_window[0], PAGE_SIZE); #else state->window = &WS(strm)->working_window[0]; #endif return zlib_inflateReset(strm); } /* Return state with length and distance decoding tables and index sizes set to fixed code decoding. This returns fixed tables from inffixed.h. */ static void zlib_fixedtables(struct inflate_state *state) { # include "inffixed.h" state->lencode = lenfix; state->lenbits = 9; state->distcode = distfix; state->distbits = 5; } /* Update the window with the last wsize (normally 32K) bytes written before returning. This is only called when a window is already in use, or when output has been written during this inflate call, but the end of the deflate stream has not been reached yet. It is also called to window dictionary data when a dictionary is loaded. Providing output buffers larger than 32K to inflate() should provide a speed advantage, since only the last 32K of output is copied to the sliding window upon return from inflate(), and since all distances after the first 32K of output will fall in the output data, making match copies simpler and faster. The advantage may be dependent on the size of the processor's data caches. */ static void zlib_updatewindow(z_streamp strm, unsigned out) { struct inflate_state *state; unsigned copy, dist; state = (struct inflate_state *)strm->state; /* copy state->wsize or less output bytes into the circular window */ copy = out - strm->avail_out; if (copy >= state->wsize) { memcpy(state->window, strm->next_out - state->wsize, state->wsize); state->write = 0; state->whave = state->wsize; } else { dist = state->wsize - state->write; if (dist > copy) dist = copy; memcpy(state->window + state->write, strm->next_out - copy, dist); copy -= dist; if (copy) { memcpy(state->window, strm->next_out - copy, copy); state->write = copy; state->whave = state->wsize; } else { state->write += dist; if (state->write == state->wsize) state->write = 0; if (state->whave < state->wsize) state->whave += dist; } } } /* * At the end of a Deflate-compressed PPP packet, we expect to have seen * a `stored' block type value but not the (zero) length bytes. */ /* Returns true if inflate is currently at the end of a block generated by Z_SYNC_FLUSH or Z_FULL_FLUSH. This function is used by one PPP implementation to provide an additional safety check. PPP uses Z_SYNC_FLUSH but removes the length bytes of the resulting empty stored block. When decompressing, PPP checks that at the end of input packet, inflate is waiting for these length bytes. */ static int zlib_inflateSyncPacket(z_streamp strm) { struct inflate_state *state; if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR; state = (struct inflate_state *)strm->state; if (state->mode == STORED && state->bits == 0) { state->mode = TYPE; return Z_OK; } return Z_DATA_ERROR; } /* Macros for inflate(): */ /* check function to use adler32() for zlib or crc32() for gzip */ #define UPDATE(check, buf, len) zlib_adler32(check, buf, len) /* Load registers with state in inflate() for speed */ #define LOAD() \ do { \ put = strm->next_out; \ left = strm->avail_out; \ next = strm->next_in; \ have = strm->avail_in; \ hold = state->hold; \ bits = state->bits; \ } while (0) /* Restore state from registers in inflate() */ #define RESTORE() \ do { \ strm->next_out = put; \ strm->avail_out = left; \ strm->next_in = next; \ strm->avail_in = have; \ state->hold = hold; \ state->bits = bits; \ } while (0) /* Clear the input bit accumulator */ #define INITBITS() \ do { \ hold = 0; \ bits = 0; \ } while (0) /* Get a byte of input into the bit accumulator, or return from inflate() if there is no input available. */ #define PULLBYTE() \ do { \ if (have == 0) goto inf_leave; \ have--; \ hold += (unsigned long)(*next++) << bits; \ bits += 8; \ } while (0) /* Assure that there are at least n bits in the bit accumulator. If there is not enough available input to do that, then return from inflate(). */ #define NEEDBITS(n) \ do { \ while (bits < (unsigned)(n)) \ PULLBYTE(); \ } while (0) /* Return the low n bits of the bit accumulator (n < 16) */ #define BITS(n) \ ((unsigned)hold & ((1U << (n)) - 1)) /* Remove n bits from the bit accumulator */ #define DROPBITS(n) \ do { \ hold >>= (n); \ bits -= (unsigned)(n); \ } while (0) /* Remove zero to seven bits as needed to go to a byte boundary */ #define BYTEBITS() \ do { \ hold >>= bits & 7; \ bits -= bits & 7; \ } while (0) /* inflate() uses a state machine to process as much input data and generate as much output data as possible before returning. The state machine is structured roughly as follows: for (;;) switch (state) { ... case STATEn: if (not enough input data or output space to make progress) return; ... make progress ... state = STATEm; break; ... } so when inflate() is called again, the same case is attempted again, and if the appropriate resources are provided, the machine proceeds to the next state. The NEEDBITS() macro is usually the way the state evaluates whether it can proceed or should return. NEEDBITS() does the return if the requested bits are not available. The typical use of the BITS macros is: NEEDBITS(n); ... do something with BITS(n) ... DROPBITS(n); where NEEDBITS(n) either returns from inflate() if there isn't enough input left to load n bits into the accumulator, or it continues. BITS(n) gives the low n bits in the accumulator. When done, DROPBITS(n) drops the low n bits off the accumulator. INITBITS() clears the accumulator and sets the number of available bits to zero. BYTEBITS() discards just enough bits to put the accumulator on a byte boundary. After BYTEBITS() and a NEEDBITS(8), then BITS(8) would return the next byte in the stream. NEEDBITS(n) uses PULLBYTE() to get an available byte of input, or to return if there is no input available. The decoding of variable length codes uses PULLBYTE() directly in order to pull just enough bytes to decode the next code, and no more. Some states loop until they get enough input, making sure that enough state information is maintained to continue the loop where it left off if NEEDBITS() returns in the loop. For example, want, need, and keep would all have to actually be part of the saved state in case NEEDBITS() returns: case STATEw: while (want < need) { NEEDBITS(n); keep[want++] = BITS(n); DROPBITS(n); } state = STATEx; case STATEx: As shown above, if the next state is also the next case, then the break is omitted. A state may also return if there is not enough output space available to complete that state. Those states are copying stored data, writing a literal byte, and copying a matching string. When returning, a "goto inf_leave" is used to update the total counters, update the check value, and determine whether any progress has been made during that inflate() call in order to return the proper return code. Progress is defined as a change in either strm->avail_in or strm->avail_out. When there is a window, goto inf_leave will update the window with the last output written. If a goto inf_leave occurs in the middle of decompression and there is no window currently, goto inf_leave will create one and copy output to the window for the next call of inflate(). In this implementation, the flush parameter of inflate() only affects the return code (per zlib.h). inflate() always writes as much as possible to strm->next_out, given the space available and the provided input--the effect documented in zlib.h of Z_SYNC_FLUSH. Furthermore, inflate() always defers the allocation of and copying into a sliding window until necessary, which provides the effect documented in zlib.h for Z_FINISH when the entire input stream available. So the only thing the flush parameter actually does is: when flush is set to Z_FINISH, inflate() cannot return Z_OK. Instead it will return Z_BUF_ERROR if it has not reached the end of the stream. */ int zlib_inflate(z_streamp strm, int flush) { struct inflate_state *state; const unsigned char *next; /* next input */ unsigned char *put; /* next output */ unsigned have, left; /* available input and output */ unsigned long hold; /* bit buffer */ unsigned bits; /* bits in bit buffer */ unsigned in, out; /* save starting available input and output */ unsigned copy; /* number of stored or match bytes to copy */ unsigned char *from; /* where to copy match bytes from */ code this; /* current decoding table entry */ code last; /* parent table entry */ unsigned len; /* length to copy for repeats, bits to drop */ int ret; /* return code */ static const unsigned short order[19] = /* permutation of code lengths */ {16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; /* Do not check for strm->next_out == NULL here as ppc zImage inflates to strm->next_out = 0 */ if (strm == NULL || strm->state == NULL || (strm->next_in == NULL && strm->avail_in != 0)) return Z_STREAM_ERROR; state = (struct inflate_state *)strm->state; if (state->mode == TYPE) state->mode = TYPEDO; /* skip check */ LOAD(); in = have; out = left; ret = Z_OK; for (;;) switch (state->mode) { case HEAD: if (state->wrap == 0) { state->mode = TYPEDO; break; } NEEDBITS(16); if ( ((BITS(8) << 8) + (hold >> 8)) % 31) { strm->msg = (char *)"incorrect header check"; state->mode = BAD; break; } if (BITS(4) != Z_DEFLATED) { strm->msg = (char *)"unknown compression method"; state->mode = BAD; break; } DROPBITS(4); len = BITS(4) + 8; if (len > state->wbits) { strm->msg = (char *)"invalid window size"; state->mode = BAD; break; } state->dmax = 1U << len; strm->adler = state->check = zlib_adler32(0L, NULL, 0); state->mode = hold & 0x200 ? DICTID : TYPE; INITBITS(); break; case DICTID: NEEDBITS(32); strm->adler = state->check = REVERSE(hold); INITBITS(); state->mode = DICT; fallthrough; case DICT: if (state->havedict == 0) { RESTORE(); return Z_NEED_DICT; } strm->adler = state->check = zlib_adler32(0L, NULL, 0); state->mode = TYPE; fallthrough; case TYPE: if (flush == Z_BLOCK) goto inf_leave; fallthrough; case TYPEDO: INFLATE_TYPEDO_HOOK(strm, flush); if (state->last) { BYTEBITS(); state->mode = CHECK; break; } NEEDBITS(3); state->last = BITS(1); DROPBITS(1); switch (BITS(2)) { case 0: /* stored block */ state->mode = STORED; break; case 1: /* fixed block */ zlib_fixedtables(state); state->mode = LEN; /* decode codes */ break; case 2: /* dynamic block */ state->mode = TABLE; break; case 3: strm->msg = (char *)"invalid block type"; state->mode = BAD; } DROPBITS(2); break; case STORED: BYTEBITS(); /* go to byte boundary */ NEEDBITS(32); if ((hold & 0xffff) != ((hold >> 16) ^ 0xffff)) { strm->msg = (char *)"invalid stored block lengths"; state->mode = BAD; break; } state->length = (unsigned)hold & 0xffff; INITBITS(); state->mode = COPY; fallthrough; case COPY: copy = state->length; if (copy) { if (copy > have) copy = have; if (copy > left) copy = left; if (copy == 0) goto inf_leave; memcpy(put, next, copy); have -= copy; next += copy; left -= copy; put += copy; state->length -= copy; break; } state->mode = TYPE; break; case TABLE: NEEDBITS(14); state->nlen = BITS(5) + 257; DROPBITS(5); state->ndist = BITS(5) + 1; DROPBITS(5); state->ncode = BITS(4) + 4; DROPBITS(4); #ifndef PKZIP_BUG_WORKAROUND if (state->nlen > 286 || state->ndist > 30) { strm->msg = (char *)"too many length or distance symbols"; state->mode = BAD; break; } #endif state->have = 0; state->mode = LENLENS; fallthrough; case LENLENS: while (state->have < state->ncode) { NEEDBITS(3); state->lens[order[state->have++]] = (unsigned short)BITS(3); DROPBITS(3); } while (state->have < 19) state->lens[order[state->have++]] = 0; state->next = state->codes; state->lencode = (code const *)(state->next); state->lenbits = 7; ret = zlib_inflate_table(CODES, state->lens, 19, &(state->next), &(state->lenbits), state->work); if (ret) { strm->msg = (char *)"invalid code lengths set"; state->mode = BAD; break; } state->have = 0; state->mode = CODELENS; fallthrough; case CODELENS: while (state->have < state->nlen + state->ndist) { for (;;) { this = state->lencode[BITS(state->lenbits)]; if ((unsigned)(this.bits) <= bits) break; PULLBYTE(); } if (this.val < 16) { NEEDBITS(this.bits); DROPBITS(this.bits); state->lens[state->have++] = this.val; } else { if (this.val == 16) { NEEDBITS(this.bits + 2); DROPBITS(this.bits); if (state->have == 0) { strm->msg = (char *)"invalid bit length repeat"; state->mode = BAD; break; } len = state->lens[state->have - 1]; copy = 3 + BITS(2); DROPBITS(2); } else if (this.val == 17) { NEEDBITS(this.bits + 3); DROPBITS(this.bits); len = 0; copy = 3 + BITS(3); DROPBITS(3); } else { NEEDBITS(this.bits + 7); DROPBITS(this.bits); len = 0; copy = 11 + BITS(7); DROPBITS(7); } if (state->have + copy > state->nlen + state->ndist) { strm->msg = (char *)"invalid bit length repeat"; state->mode = BAD; break; } while (copy--) state->lens[state->have++] = (unsigned short)len; } } /* handle error breaks in while */ if (state->mode == BAD) break; /* build code tables */ state->next = state->codes; state->lencode = (code const *)(state->next); state->lenbits = 9; ret = zlib_inflate_table(LENS, state->lens, state->nlen, &(state->next), &(state->lenbits), state->work); if (ret) { strm->msg = (char *)"invalid literal/lengths set"; state->mode = BAD; break; } state->distcode = (code const *)(state->next); state->distbits = 6; ret = zlib_inflate_table(DISTS, state->lens + state->nlen, state->ndist, &(state->next), &(state->distbits), state->work); if (ret) { strm->msg = (char *)"invalid distances set"; state->mode = BAD; break; } state->mode = LEN; fallthrough; case LEN: if (have >= 6 && left >= 258) { RESTORE(); inflate_fast(strm, out); LOAD(); break; } for (;;) { this = state->lencode[BITS(state->lenbits)]; if ((unsigned)(this.bits) <= bits) break; PULLBYTE(); } if (this.op && (this.op & 0xf0) == 0) { last = this; for (;;) { this = state->lencode[last.val + (BITS(last.bits + last.op) >> last.bits)]; if ((unsigned)(last.bits + this.bits) <= bits) break; PULLBYTE(); } DROPBITS(last.bits); } DROPBITS(this.bits); state->length = (unsigned)this.val; if ((int)(this.op) == 0) { state->mode = LIT; break; } if (this.op & 32) { state->mode = TYPE; break; } if (this.op & 64) { strm->msg = (char *)"invalid literal/length code"; state->mode = BAD; break; } state->extra = (unsigned)(this.op) & 15; state->mode = LENEXT; fallthrough; case LENEXT: if (state->extra) { NEEDBITS(state->extra); state->length += BITS(state->extra); DROPBITS(state->extra); } state->mode = DIST; fallthrough; case DIST: for (;;) { this = state->distcode[BITS(state->distbits)]; if ((unsigned)(this.bits) <= bits) break; PULLBYTE(); } if ((this.op & 0xf0) == 0) { last = this; for (;;) { this = state->distcode[last.val + (BITS(last.bits + last.op) >> last.bits)]; if ((unsigned)(last.bits + this.bits) <= bits) break; PULLBYTE(); } DROPBITS(last.bits); } DROPBITS(this.bits); if (this.op & 64) { strm->msg = (char *)"invalid distance code"; state->mode = BAD; break; } state->offset = (unsigned)this.val; state->extra = (unsigned)(this.op) & 15; state->mode = DISTEXT; fallthrough; case DISTEXT: if (state->extra) { NEEDBITS(state->extra); state->offset += BITS(state->extra); DROPBITS(state->extra); } #ifdef INFLATE_STRICT if (state->offset > state->dmax) { strm->msg = (char *)"invalid distance too far back"; state->mode = BAD; break; } #endif if (state->offset > state->whave + out - left) { strm->msg = (char *)"invalid distance too far back"; state->mode = BAD; break; } state->mode = MATCH; fallthrough; case MATCH: if (left == 0) goto inf_leave; copy = out - left; if (state->offset > copy) { /* copy from window */ copy = state->offset - copy; if (copy > state->write) { copy -= state->write; from = state->window + (state->wsize - copy); } else from = state->window + (state->write - copy); if (copy > state->length) copy = state->length; } else { /* copy from output */ from = put - state->offset; copy = state->length; } if (copy > left) copy = left; left -= copy; state->length -= copy; do { *put++ = *from++; } while (--copy); if (state->length == 0) state->mode = LEN; break; case LIT: if (left == 0) goto inf_leave; *put++ = (unsigned char)(state->length); left--; state->mode = LEN; break; case CHECK: if (state->wrap) { NEEDBITS(32); out -= left; strm->total_out += out; state->total += out; if (INFLATE_NEED_CHECKSUM(strm) && out) strm->adler = state->check = UPDATE(state->check, put - out, out); out = left; if (( REVERSE(hold)) != state->check) { strm->msg = (char *)"incorrect data check"; state->mode = BAD; break; } INITBITS(); } state->mode = DONE; fallthrough; case DONE: ret = Z_STREAM_END; goto inf_leave; case BAD: ret = Z_DATA_ERROR; goto inf_leave; case MEM: return Z_MEM_ERROR; case SYNC: default: return Z_STREAM_ERROR; } /* Return from inflate(), updating the total counts and the check value. If there was no progress during the inflate() call, return a buffer error. Call zlib_updatewindow() to create and/or update the window state. */ inf_leave: RESTORE(); if (INFLATE_NEED_UPDATEWINDOW(strm) && (state->wsize || (state->mode < CHECK && out != strm->avail_out))) zlib_updatewindow(strm, out); in -= strm->avail_in; out -= strm->avail_out; strm->total_in += in; strm->total_out += out; state->total += out; if (INFLATE_NEED_CHECKSUM(strm) && state->wrap && out) strm->adler = state->check = UPDATE(state->check, strm->next_out - out, out); strm->data_type = state->bits + (state->last ? 64 : 0) + (state->mode == TYPE ? 128 : 0); if (flush == Z_PACKET_FLUSH && ret == Z_OK && strm->avail_out != 0 && strm->avail_in == 0) return zlib_inflateSyncPacket(strm); if (((in == 0 && out == 0) || flush == Z_FINISH) && ret == Z_OK) ret = Z_BUF_ERROR; return ret; } int zlib_inflateEnd(z_streamp strm) { if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR; return Z_OK; } /* * This subroutine adds the data at next_in/avail_in to the output history * without performing any output. The output buffer must be "caught up"; * i.e. no pending output but this should always be the case. The state must * be waiting on the start of a block (i.e. mode == TYPE or HEAD). On exit, * the output will also be caught up, and the checksum will have been updated * if need be. */ int zlib_inflateIncomp(z_stream *z) { struct inflate_state *state = (struct inflate_state *)z->state; Byte *saved_no = z->next_out; uInt saved_ao = z->avail_out; if (state->mode != TYPE && state->mode != HEAD) return Z_DATA_ERROR; /* Setup some variables to allow misuse of updateWindow */ z->avail_out = 0; z->next_out = (unsigned char*)z->next_in + z->avail_in; zlib_updatewindow(z, z->avail_in); /* Restore saved variables */ z->avail_out = saved_ao; z->next_out = saved_no; z->adler = state->check = UPDATE(state->check, z->next_in, z->avail_in); z->total_out += z->avail_in; z->total_in += z->avail_in; z->next_in += z->avail_in; state->total += z->avail_in; z->avail_in = 0; return Z_OK; } |
| 2229 2238 2020 630 260 282 23 76 812 | 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 | // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) /* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ * * This implementation is specifically for SipHash2-4 for a secure PRF * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for * hashtables. */ #include <linux/siphash.h> #include <linux/unaligned.h> #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 #include <linux/dcache.h> #include <asm/word-at-a-time.h> #endif #define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3) #define PREAMBLE(len) \ u64 v0 = SIPHASH_CONST_0; \ u64 v1 = SIPHASH_CONST_1; \ u64 v2 = SIPHASH_CONST_2; \ u64 v3 = SIPHASH_CONST_3; \ u64 b = ((u64)(len)) << 56; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ v1 ^= key->key[1]; \ v0 ^= key->key[0]; #define POSTAMBLE \ v3 ^= b; \ SIPROUND; \ SIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ SIPROUND; \ SIPROUND; \ SIPROUND; \ SIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; PREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = le64_to_cpup(data); v3 ^= m; SIPROUND; SIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= le32_to_cpup(data); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } #endif POSTAMBLE } EXPORT_SYMBOL(__siphash_aligned); #endif u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; PREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = get_unaligned_le64(data); v3 ^= m; SIPROUND; SIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= get_unaligned_le32(end); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } #endif POSTAMBLE } EXPORT_SYMBOL(__siphash_unaligned); /** * siphash_1u64 - compute 64-bit siphash PRF value of a u64 * @first: first u64 * @key: the siphash key */ u64 siphash_1u64(const u64 first, const siphash_key_t *key) { PREAMBLE(8) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; POSTAMBLE } EXPORT_SYMBOL(siphash_1u64); /** * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64 * @first: first u64 * @second: second u64 * @key: the siphash key */ u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key) { PREAMBLE(16) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; POSTAMBLE } EXPORT_SYMBOL(siphash_2u64); /** * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64 * @first: first u64 * @second: second u64 * @third: third u64 * @key: the siphash key */ u64 siphash_3u64(const u64 first, const u64 second, const u64 third, const siphash_key_t *key) { PREAMBLE(24) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; v3 ^= third; SIPROUND; SIPROUND; v0 ^= third; POSTAMBLE } EXPORT_SYMBOL(siphash_3u64); /** * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64 * @first: first u64 * @second: second u64 * @third: third u64 * @forth: forth u64 * @key: the siphash key */ u64 siphash_4u64(const u64 first, const u64 second, const u64 third, const u64 forth, const siphash_key_t *key) { PREAMBLE(32) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; v3 ^= third; SIPROUND; SIPROUND; v0 ^= third; v3 ^= forth; SIPROUND; SIPROUND; v0 ^= forth; POSTAMBLE } EXPORT_SYMBOL(siphash_4u64); u64 siphash_1u32(const u32 first, const siphash_key_t *key) { PREAMBLE(4) b |= first; POSTAMBLE } EXPORT_SYMBOL(siphash_1u32); u64 siphash_3u32(const u32 first, const u32 second, const u32 third, const siphash_key_t *key) { u64 combined = (u64)second << 32 | first; PREAMBLE(12) v3 ^= combined; SIPROUND; SIPROUND; v0 ^= combined; b |= third; POSTAMBLE } EXPORT_SYMBOL(siphash_3u32); #if BITS_PER_LONG == 64 /* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for * performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3. */ #define HSIPROUND SIPROUND #define HPREAMBLE(len) PREAMBLE(len) #define HPOSTAMBLE \ v3 ^= b; \ HSIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ HSIPROUND; \ HSIPROUND; \ HSIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; HPREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = le64_to_cpup(data); v3 ^= m; HSIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= le32_to_cpup(data); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } #endif HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); #endif u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; HPREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = get_unaligned_le64(data); v3 ^= m; HSIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= get_unaligned_le32(end); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } #endif HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); /** * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32 * @first: first u32 * @key: the hsiphash key */ u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key) { HPREAMBLE(4) b |= first; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_1u32); /** * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32 * @first: first u32 * @second: second u32 * @key: the hsiphash key */ u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(8) v3 ^= combined; HSIPROUND; v0 ^= combined; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_2u32); /** * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @key: the hsiphash key */ u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(12) v3 ^= combined; HSIPROUND; v0 ^= combined; b |= third; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_3u32); /** * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @forth: forth u32 * @key: the hsiphash key */ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, const u32 forth, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(16) v3 ^= combined; HSIPROUND; v0 ^= combined; combined = (u64)forth << 32 | third; v3 ^= combined; HSIPROUND; v0 ^= combined; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_4u32); #else #define HSIPROUND HSIPHASH_PERMUTATION(v0, v1, v2, v3) #define HPREAMBLE(len) \ u32 v0 = HSIPHASH_CONST_0; \ u32 v1 = HSIPHASH_CONST_1; \ u32 v2 = HSIPHASH_CONST_2; \ u32 v3 = HSIPHASH_CONST_3; \ u32 b = ((u32)(len)) << 24; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ v1 ^= key->key[1]; \ v0 ^= key->key[0]; #define HPOSTAMBLE \ v3 ^= b; \ HSIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ HSIPROUND; \ HSIPROUND; \ HSIPROUND; \ return v1 ^ v3; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); const u8 left = len & (sizeof(u32) - 1); u32 m; HPREAMBLE(len) for (; data != end; data += sizeof(u32)) { m = le32_to_cpup(data); v3 ^= m; HSIPROUND; v0 ^= m; } switch (left) { case 3: b |= ((u32)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); #endif u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); const u8 left = len & (sizeof(u32) - 1); u32 m; HPREAMBLE(len) for (; data != end; data += sizeof(u32)) { m = get_unaligned_le32(data); v3 ^= m; HSIPROUND; v0 ^= m; } switch (left) { case 3: b |= ((u32)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); /** * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32 * @first: first u32 * @key: the hsiphash key */ u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key) { HPREAMBLE(4) v3 ^= first; HSIPROUND; v0 ^= first; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_1u32); /** * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32 * @first: first u32 * @second: second u32 * @key: the hsiphash key */ u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key) { HPREAMBLE(8) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_2u32); /** * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @key: the hsiphash key */ u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third, const hsiphash_key_t *key) { HPREAMBLE(12) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; v3 ^= third; HSIPROUND; v0 ^= third; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_3u32); /** * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @forth: forth u32 * @key: the hsiphash key */ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, const u32 forth, const hsiphash_key_t *key) { HPREAMBLE(16) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; v3 ^= third; HSIPROUND; v0 ^= third; v3 ^= forth; HSIPROUND; v0 ^= forth; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_4u32); #endif |
| 342 22 336 336 143 17 16 142 335 139 336 336 340 342 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Create default crypto algorithm instances. * * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/aead.h> #include <linux/completion.h> #include <linux/ctype.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/string.h> #include "internal.h" struct cryptomgr_param { struct rtattr *tb[CRYPTO_MAX_ATTRS + 2]; struct { struct rtattr attr; struct crypto_attr_type data; } type; struct { struct rtattr attr; struct crypto_attr_alg data; } attrs[CRYPTO_MAX_ATTRS]; char template[CRYPTO_MAX_ALG_NAME]; struct crypto_larval *larval; u32 otype; u32 omask; }; struct crypto_test_param { char driver[CRYPTO_MAX_ALG_NAME]; char alg[CRYPTO_MAX_ALG_NAME]; u32 type; }; static int cryptomgr_probe(void *data) { struct cryptomgr_param *param = data; struct crypto_template *tmpl; int err = -ENOENT; tmpl = crypto_lookup_template(param->template); if (!tmpl) goto out; do { err = tmpl->create(tmpl, param->tb); } while (err == -EAGAIN && !signal_pending(current)); crypto_tmpl_put(tmpl); out: param->larval->adult = ERR_PTR(err); param->larval->alg.cra_flags |= CRYPTO_ALG_DEAD; complete_all(¶m->larval->completion); crypto_alg_put(¶m->larval->alg); kfree(param); module_put_and_kthread_exit(0); } static int cryptomgr_schedule_probe(struct crypto_larval *larval) { struct task_struct *thread; struct cryptomgr_param *param; const char *name = larval->alg.cra_name; const char *p; unsigned int len; int i; if (!try_module_get(THIS_MODULE)) goto err; param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) goto err_put_module; for (p = name; isalnum(*p) || *p == '-' || *p == '_'; p++) ; len = p - name; if (!len || *p != '(') goto err_free_param; memcpy(param->template, name, len); i = 0; for (;;) { name = ++p; for (; isalnum(*p) || *p == '-' || *p == '_'; p++) ; if (*p == '(') { int recursion = 0; for (;;) { if (!*++p) goto err_free_param; if (*p == '(') recursion++; else if (*p == ')' && !recursion--) break; } p++; } len = p - name; if (!len) goto err_free_param; param->attrs[i].attr.rta_len = sizeof(param->attrs[i]); param->attrs[i].attr.rta_type = CRYPTOA_ALG; memcpy(param->attrs[i].data.name, name, len); param->tb[i + 1] = ¶m->attrs[i].attr; i++; if (i >= CRYPTO_MAX_ATTRS) goto err_free_param; if (*p == ')') break; if (*p != ',') goto err_free_param; } param->tb[i + 1] = NULL; param->type.attr.rta_len = sizeof(param->type); param->type.attr.rta_type = CRYPTOA_TYPE; param->type.data.type = larval->alg.cra_flags & ~CRYPTO_ALG_TESTED; param->type.data.mask = larval->mask & ~CRYPTO_ALG_TESTED; param->tb[0] = ¶m->type.attr; param->otype = larval->alg.cra_flags; param->omask = larval->mask; crypto_alg_get(&larval->alg); param->larval = larval; thread = kthread_run(cryptomgr_probe, param, "cryptomgr_probe"); if (IS_ERR(thread)) goto err_put_larval; return NOTIFY_STOP; err_put_larval: crypto_alg_put(&larval->alg); err_free_param: kfree(param); err_put_module: module_put(THIS_MODULE); err: return NOTIFY_OK; } static int cryptomgr_test(void *data) { struct crypto_test_param *param = data; u32 type = param->type; int err; err = alg_test(param->driver, param->alg, type, CRYPTO_ALG_TESTED); crypto_alg_tested(param->driver, err); kfree(param); module_put_and_kthread_exit(0); } static int cryptomgr_schedule_test(struct crypto_alg *alg) { struct task_struct *thread; struct crypto_test_param *param; if (IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS)) return NOTIFY_DONE; if (!try_module_get(THIS_MODULE)) goto err; param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) goto err_put_module; memcpy(param->driver, alg->cra_driver_name, sizeof(param->driver)); memcpy(param->alg, alg->cra_name, sizeof(param->alg)); param->type = alg->cra_flags; thread = kthread_run(cryptomgr_test, param, "cryptomgr_test"); if (IS_ERR(thread)) goto err_free_param; return NOTIFY_STOP; err_free_param: kfree(param); err_put_module: module_put(THIS_MODULE); err: return NOTIFY_OK; } static int cryptomgr_notify(struct notifier_block *this, unsigned long msg, void *data) { switch (msg) { case CRYPTO_MSG_ALG_REQUEST: return cryptomgr_schedule_probe(data); case CRYPTO_MSG_ALG_REGISTER: return cryptomgr_schedule_test(data); case CRYPTO_MSG_ALG_LOADED: break; } return NOTIFY_DONE; } static struct notifier_block cryptomgr_notifier = { .notifier_call = cryptomgr_notify, }; static int __init cryptomgr_init(void) { return crypto_register_notifier(&cryptomgr_notifier); } static void __exit cryptomgr_exit(void) { int err = crypto_unregister_notifier(&cryptomgr_notifier); BUG_ON(err); } /* * This is arch_initcall() so that the crypto self-tests are run on algorithms * registered early by subsys_initcall(). subsys_initcall() is needed for * generic implementations so that they're available for comparison tests when * other implementations are registered later by module_init(). */ arch_initcall(cryptomgr_init); module_exit(cryptomgr_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Crypto Algorithm Manager"); |
| 727 1240 15 2 1 1 12 11 11 1 10 1 1434 1435 1371 43 40 20 1436 1378 1378 968 431 4 413 20 1378 1004 1205 456 193 2563 1039 1611 1613 1171 82 66 720 93 1613 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 | // 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], }; |
| 1 1 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 | /* * Copyright (c) 2006 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/export.h> #include "rds.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); EXPORT_PER_CPU_SYMBOL_GPL(rds_stats); /* :.,$s/unsigned long\>.*\<s_\(.*\);/"\1",/g */ static const char *const rds_stat_names[] = { "conn_reset", "recv_drop_bad_checksum", "recv_drop_old_seq", "recv_drop_no_sock", "recv_drop_dead_sock", "recv_deliver_raced", "recv_delivered", "recv_queued", "recv_immediate_retry", "recv_delayed_retry", "recv_ack_required", "recv_rdma_bytes", "recv_ping", "send_queue_empty", "send_queue_full", "send_lock_contention", "send_lock_queue_raced", "send_immediate_retry", "send_delayed_retry", "send_drop_acked", "send_ack_required", "send_queued", "send_rdma", "send_rdma_bytes", "send_pong", "page_remainder_hit", "page_remainder_miss", "copy_to_user", "copy_from_user", "cong_update_queued", "cong_update_received", "cong_send_error", "cong_send_blocked", "recv_bytes_added_to_sock", "recv_bytes_freed_fromsock", "send_stuck_rm", }; void rds_stats_info_copy(struct rds_info_iterator *iter, uint64_t *values, const char *const *names, size_t nr) { struct rds_info_counter ctr; size_t i; for (i = 0; i < nr; i++) { BUG_ON(strlen(names[i]) >= sizeof(ctr.name)); strscpy_pad(ctr.name, names[i]); ctr.value = values[i]; rds_info_copy(iter, &ctr, sizeof(ctr)); } } EXPORT_SYMBOL_GPL(rds_stats_info_copy); /* * This gives global counters across all the transports. The strings * are copied in so that the tool doesn't need knowledge of the specific * stats that we're exporting. Some are pretty implementation dependent * and may change over time. That doesn't stop them from being useful. * * This is the only function in the chain that knows about the byte granular * length in userspace. It converts it to number of stat entries that the * rest of the functions operate in. */ static void rds_stats_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_statistics stats = {0, }; uint64_t *src; uint64_t *sum; size_t i; int cpu; unsigned int avail; avail = len / sizeof(struct rds_info_counter); if (avail < ARRAY_SIZE(rds_stat_names)) { avail = 0; goto trans; } for_each_online_cpu(cpu) { src = (uint64_t *)&(per_cpu(rds_stats, cpu)); sum = (uint64_t *)&stats; for (i = 0; i < sizeof(stats) / sizeof(uint64_t); i++) *(sum++) += *(src++); } rds_stats_info_copy(iter, (uint64_t *)&stats, rds_stat_names, ARRAY_SIZE(rds_stat_names)); avail -= ARRAY_SIZE(rds_stat_names); trans: lens->each = sizeof(struct rds_info_counter); lens->nr = rds_trans_stats_info_copy(iter, avail) + ARRAY_SIZE(rds_stat_names); } void rds_stats_exit(void) { rds_info_deregister_func(RDS_INFO_COUNTERS, rds_stats_info); } int rds_stats_init(void) { rds_info_register_func(RDS_INFO_COUNTERS, rds_stats_info); return 0; } |
| 26 21 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 | // SPDX-License-Identifier: GPL-2.0 /* File: fs/ext4/acl.h (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #include <linux/posix_acl_xattr.h> #define EXT4_ACL_VERSION 0x0001 typedef struct { __le16 e_tag; __le16 e_perm; __le32 e_id; } ext4_acl_entry; typedef struct { __le16 e_tag; __le16 e_perm; } ext4_acl_entry_short; typedef struct { __le32 a_version; } ext4_acl_header; static inline size_t ext4_acl_size(int count) { if (count <= 4) { return sizeof(ext4_acl_header) + count * sizeof(ext4_acl_entry_short); } else { return sizeof(ext4_acl_header) + 4 * sizeof(ext4_acl_entry_short) + (count - 4) * sizeof(ext4_acl_entry); } } static inline int ext4_acl_count(size_t size) { ssize_t s; size -= sizeof(ext4_acl_header); s = size - 4 * sizeof(ext4_acl_entry_short); if (s < 0) { if (size % sizeof(ext4_acl_entry_short)) return -1; return size / sizeof(ext4_acl_entry_short); } else { if (s % sizeof(ext4_acl_entry)) return -1; return s / sizeof(ext4_acl_entry) + 4; } } #ifdef CONFIG_EXT4_FS_POSIX_ACL /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu); int ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); #else /* CONFIG_EXT4_FS_POSIX_ACL */ #include <linux/sched.h> #define ext4_get_acl NULL #define ext4_set_acl NULL static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ |
| 15 15 15 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_EXPORTFS_H #define LINUX_EXPORTFS_H 1 #include <linux/types.h> #include <linux/path.h> struct dentry; struct iattr; struct inode; struct iomap; struct super_block; struct vfsmount; /* limit the handle size to NFSv4 handle size now */ #define MAX_HANDLE_SZ 128 /* * The fileid_type identifies how the file within the filesystem is encoded. * In theory this is freely set and parsed by the filesystem, but we try to * stick to conventions so we can share some generic code and don't confuse * sniffers like ethereal/wireshark. * * The filesystem must not use the value '0' or '0xff'. */ enum fid_type { /* * The root, or export point, of the filesystem. * (Never actually passed down to the filesystem. */ FILEID_ROOT = 0, /* * 32bit inode number, 32 bit generation number. */ FILEID_INO32_GEN = 1, /* * 32bit inode number, 32 bit generation number, * 32 bit parent directory inode number. */ FILEID_INO32_GEN_PARENT = 2, /* * 64 bit object ID, 64 bit root object ID, * 32 bit generation number. */ FILEID_BTRFS_WITHOUT_PARENT = 0x4d, /* * 64 bit object ID, 64 bit root object ID, * 32 bit generation number, * 64 bit parent object ID, 32 bit parent generation. */ FILEID_BTRFS_WITH_PARENT = 0x4e, /* * 64 bit object ID, 64 bit root object ID, * 32 bit generation number, * 64 bit parent object ID, 32 bit parent generation, * 64 bit parent root object ID. */ FILEID_BTRFS_WITH_PARENT_ROOT = 0x4f, /* * 32 bit block number, 16 bit partition reference, * 16 bit unused, 32 bit generation number. */ FILEID_UDF_WITHOUT_PARENT = 0x51, /* * 32 bit block number, 16 bit partition reference, * 16 bit unused, 32 bit generation number, * 32 bit parent block number, 32 bit parent generation number */ FILEID_UDF_WITH_PARENT = 0x52, /* * 64 bit checkpoint number, 64 bit inode number, * 32 bit generation number. */ FILEID_NILFS_WITHOUT_PARENT = 0x61, /* * 64 bit checkpoint number, 64 bit inode number, * 32 bit generation number, 32 bit parent generation. * 64 bit parent inode number. */ FILEID_NILFS_WITH_PARENT = 0x62, /* * 32 bit generation number, 40 bit i_pos. */ FILEID_FAT_WITHOUT_PARENT = 0x71, /* * 32 bit generation number, 40 bit i_pos, * 32 bit parent generation number, 40 bit parent i_pos */ FILEID_FAT_WITH_PARENT = 0x72, /* * 64 bit inode number, 32 bit generation number. */ FILEID_INO64_GEN = 0x81, /* * 64 bit inode number, 32 bit generation number, * 64 bit parent inode number, 32 bit parent generation. */ FILEID_INO64_GEN_PARENT = 0x82, /* * 128 bit child FID (struct lu_fid) * 128 bit parent FID (struct lu_fid) */ FILEID_LUSTRE = 0x97, /* * 64 bit inode number, 32 bit subvolume, 32 bit generation number: */ FILEID_BCACHEFS_WITHOUT_PARENT = 0xb1, FILEID_BCACHEFS_WITH_PARENT = 0xb2, /* * 64 bit unique kernfs id */ FILEID_KERNFS = 0xfe, /* * Filesystems must not use 0xff file ID. */ FILEID_INVALID = 0xff, }; struct fid { union { struct { u32 ino; u32 gen; u32 parent_ino; u32 parent_gen; } i32; struct { u64 ino; u32 gen; } __packed i64; struct { u32 block; u16 partref; u16 parent_partref; u32 generation; u32 parent_block; u32 parent_generation; } udf; DECLARE_FLEX_ARRAY(__u32, raw); }; }; enum handle_to_path_flags { HANDLE_CHECK_PERMS = (1 << 0), HANDLE_CHECK_SUBTREE = (1 << 1), }; struct handle_to_path_ctx { struct path root; enum handle_to_path_flags flags; unsigned int fh_flags; }; #define EXPORT_FH_CONNECTABLE 0x1 /* Encode file handle with parent */ #define EXPORT_FH_FID 0x2 /* File handle may be non-decodeable */ #define EXPORT_FH_DIR_ONLY 0x4 /* Only decode file handle for a directory */ /* * Filesystems use only lower 8 bits of file_handle type for fid_type. * name_to_handle_at() uses upper 16 bits of type as user flags to be * interpreted by open_by_handle_at(). */ #define FILEID_USER_FLAGS_MASK 0xffff0000 #define FILEID_USER_FLAGS(type) ((type) & FILEID_USER_FLAGS_MASK) /* Flags supported in encoded handle_type that is exported to user */ #define FILEID_IS_CONNECTABLE 0x10000 #define FILEID_IS_DIR 0x20000 #define FILEID_VALID_USER_FLAGS (FILEID_IS_CONNECTABLE | FILEID_IS_DIR) /** * struct export_operations - for nfsd to communicate with file systems * @encode_fh: encode a file handle fragment from a dentry * @fh_to_dentry: find the implied object and get a dentry for it * @fh_to_parent: find the implied object's parent and get a dentry for it * @get_name: find the name for a given inode in a given directory * @get_parent: find the parent of a given directory * @commit_metadata: commit metadata changes to stable storage * * See Documentation/filesystems/nfs/exporting.rst for details on how to use * this interface correctly. * * encode_fh: * @encode_fh should store in the file handle fragment @fh (using at most * @max_len bytes) information that can be used by @decode_fh to recover the * file referred to by the &struct dentry @de. If @flag has CONNECTABLE bit * set, the encode_fh() should store sufficient information so that a good * attempt can be made to find not only the file but also it's place in the * filesystem. This typically means storing a reference to de->d_parent in * the filehandle fragment. encode_fh() should return the fileid_type on * success and on error returns 255 (if the space needed to encode fh is * greater than @max_len*4 bytes). On error @max_len contains the minimum * size(in 4 byte unit) needed to encode the file handle. * * fh_to_dentry: * @fh_to_dentry is given a &struct super_block (@sb) and a file handle * fragment (@fh, @fh_len). It should return a &struct dentry which refers * to the same file that the file handle fragment refers to. If it cannot, * it should return a %NULL pointer if the file cannot be found, or an * %ERR_PTR error code of %ENOMEM if a memory allocation failure occurred. * Any other error code is treated like %NULL, and will cause an %ESTALE error * for callers of exportfs_decode_fh(). * Any suitable dentry can be returned including, if necessary, a new dentry * created with d_alloc_root. The caller can then find any other extant * dentries by following the d_alias links. * * fh_to_parent: * Same as @fh_to_dentry, except that it returns a pointer to the parent * dentry if it was encoded into the filehandle fragment by @encode_fh. * * get_name: * @get_name should find a name for the given @child in the given @parent * directory. The name should be stored in the @name (with the * understanding that it is already pointing to a %NAME_MAX+1 sized * buffer. get_name() should return %0 on success, a negative error code * or error. @get_name will be called without @parent->i_mutex held. * * get_parent: * @get_parent should find the parent directory for the given @child which * is also a directory. In the event that it cannot be found, or storage * space cannot be allocated, a %ERR_PTR should be returned. * * permission: * Allow filesystems to specify a custom permission function. * * open: * Allow filesystems to specify a custom open function. * * commit_metadata: * @commit_metadata should commit metadata changes to stable storage. * * Locking rules: * get_parent is called with child->d_inode->i_mutex down * get_name is not (which is possibly inconsistent) */ struct export_operations { int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent); struct dentry * (*fh_to_dentry)(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); struct dentry * (*fh_to_parent)(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); int (*get_name)(struct dentry *parent, char *name, struct dentry *child); struct dentry * (*get_parent)(struct dentry *child); int (*commit_metadata)(struct inode *inode); int (*get_uuid)(struct super_block *sb, u8 *buf, u32 *len, u64 *offset); int (*map_blocks)(struct inode *inode, loff_t offset, u64 len, struct iomap *iomap, bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); int (*permission)(struct handle_to_path_ctx *ctx, unsigned int oflags); struct file * (*open)(struct path *path, unsigned int oflags); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ #define EXPORT_OP_REMOTE_FS (0x8) /* Filesystem is remote */ #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ #define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ #define EXPORT_OP_NOLOCKS (0x40) /* no file locking support */ unsigned long flags; }; /** * exportfs_cannot_lock() - check if export implements file locking * @export_ops: the nfs export operations to check * * Returns true if the export does not support file locking. */ static inline bool exportfs_cannot_lock(const struct export_operations *export_ops) { return export_ops->flags & EXPORT_OP_NOLOCKS; } extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len, int flags); static inline bool exportfs_can_encode_fid(const struct export_operations *nop) { return !nop || nop->encode_fh; } static inline bool exportfs_can_decode_fh(const struct export_operations *nop) { return nop && nop->fh_to_dentry; } static inline bool exportfs_can_encode_fh(const struct export_operations *nop, int fh_flags) { /* * If a non-decodeable file handle was requested, we only need to make * sure that filesystem did not opt-out of encoding fid. */ if (fh_flags & EXPORT_FH_FID) return exportfs_can_encode_fid(nop); /* * If a decodeable file handle was requested, we need to make sure that * filesystem can also decode file handles. */ return exportfs_can_decode_fh(nop); } static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid, int *max_len) { return exportfs_encode_inode_fh(inode, fid, max_len, NULL, EXPORT_FH_FID); } extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, unsigned int flags, int (*acceptable)(void *, struct dentry *), void *context); extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *), void *context); /* * Generic helpers for filesystems. */ int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent); struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)); struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)); #endif /* LINUX_EXPORTFS_H */ |
| 12 1 1 4 6 1 4 4 1 1 1 2 2 390 389 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Stateless NAT actions * * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/tc_act/tc_nat.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <net/icmp.h> #include <net/ip.h> #include <net/netlink.h> #include <net/tc_act/tc_nat.h> #include <net/tcp.h> #include <net/udp.h> #include <net/tc_wrapper.h> static struct tc_action_ops act_nat_ops; static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, }; static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_nat_parms *nparm, *oparm; struct nlattr *tb[TCA_NAT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_NAT_MAX, nla, nat_policy, NULL); if (err < 0) return err; if (tb[TCA_NAT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_nat_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } else { return err; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; nparm = kzalloc(sizeof(*nparm), GFP_KERNEL); if (!nparm) { err = -ENOMEM; goto release_idr; } nparm->old_addr = parm->old_addr; nparm->new_addr = parm->new_addr; nparm->mask = parm->mask; nparm->flags = parm->flags; p = to_tcf_nat(*a); spin_lock_bh(&p->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); oparm = rcu_replace_pointer(p->parms, nparm, lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (oparm) kfree_rcu(oparm, rcu); return ret; release_idr: tcf_idr_release(*a, bind); return err; } TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_nat *p = to_tcf_nat(a); struct tcf_nat_parms *parms; struct iphdr *iph; __be32 old_addr; __be32 new_addr; __be32 mask; __be32 addr; int egress; int action; int ihl; int noff; tcf_lastuse_update(&p->tcf_tm); tcf_action_update_bstats(&p->common, skb); action = READ_ONCE(p->tcf_action); parms = rcu_dereference_bh(p->parms); old_addr = parms->old_addr; new_addr = parms->new_addr; mask = parms->mask; egress = parms->flags & TCA_NAT_FLAG_EGRESS; if (unlikely(action == TC_ACT_SHOT)) goto drop; noff = skb_network_offset(skb); if (!pskb_may_pull(skb, sizeof(*iph) + noff)) goto drop; iph = ip_hdr(skb); if (egress) addr = iph->saddr; else addr = iph->daddr; if (!((old_addr ^ addr) & mask)) { if (skb_try_make_writable(skb, sizeof(*iph) + noff)) goto drop; new_addr &= mask; new_addr |= addr & ~mask; /* Rewrite IP header */ iph = ip_hdr(skb); if (egress) iph->saddr = new_addr; else iph->daddr = new_addr; csum_replace4(&iph->check, addr, new_addr); } else if ((iph->frag_off & htons(IP_OFFSET)) || iph->protocol != IPPROTO_ICMP) { goto out; } ihl = iph->ihl * 4; /* It would be nice to share code with stateful NAT. */ switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) { case IPPROTO_TCP: { struct tcphdr *tcph; if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) || skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff)) goto drop; tcph = (void *)(skb_network_header(skb) + ihl); inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); break; } case IPPROTO_UDP: { struct udphdr *udph; if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) || skb_try_make_writable(skb, ihl + sizeof(*udph) + noff)) goto drop; udph = (void *)(skb_network_header(skb) + ihl); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&udph->check, skb, addr, new_addr, true); if (!udph->check) udph->check = CSUM_MANGLED_0; } break; } case IPPROTO_ICMP: { struct icmphdr *icmph; if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff)) goto drop; icmph = (void *)(skb_network_header(skb) + ihl); if (!icmp_is_err(icmph->type)) break; if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) + noff)) goto drop; icmph = (void *)(skb_network_header(skb) + ihl); iph = (void *)(icmph + 1); if (egress) addr = iph->daddr; else addr = iph->saddr; if ((old_addr ^ addr) & mask) break; if (skb_try_make_writable(skb, ihl + sizeof(*icmph) + sizeof(*iph) + noff)) goto drop; icmph = (void *)(skb_network_header(skb) + ihl); iph = (void *)(icmph + 1); new_addr &= mask; new_addr |= addr & ~mask; /* XXX Fix up the inner checksums. */ if (egress) iph->daddr = new_addr; else iph->saddr = new_addr; inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr, false); break; } default: break; } out: return action; drop: tcf_action_inc_drop_qstats(&p->common); return TC_ACT_SHOT; } static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_nat *p = to_tcf_nat(a); struct tc_nat opt = { .index = p->tcf_index, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_nat_parms *parms; struct tcf_t t; spin_lock_bh(&p->tcf_lock); opt.action = p->tcf_action; parms = rcu_dereference_protected(p->parms, lockdep_is_held(&p->tcf_lock)); opt.old_addr = parms->old_addr; opt.new_addr = parms->new_addr; opt.mask = parms->mask; opt.flags = parms->flags; if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_nat_cleanup(struct tc_action *a) { struct tcf_nat *p = to_tcf_nat(a); struct tcf_nat_parms *parms; parms = rcu_dereference_protected(p->parms, 1); if (parms) kfree_rcu(parms, rcu); } static struct tc_action_ops act_nat_ops = { .kind = "nat", .id = TCA_ID_NAT, .owner = THIS_MODULE, .act = tcf_nat_act, .dump = tcf_nat_dump, .init = tcf_nat_init, .cleanup = tcf_nat_cleanup, .size = sizeof(struct tcf_nat), }; MODULE_ALIAS_NET_ACT("nat"); static __net_init int nat_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id); return tc_action_net_init(net, tn, &act_nat_ops); } static void __net_exit nat_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_nat_ops.net_id); } static struct pernet_operations nat_net_ops = { .init = nat_init_net, .exit_batch = nat_exit_net, .id = &act_nat_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_DESCRIPTION("Stateless NAT actions"); MODULE_LICENSE("GPL"); static int __init nat_init_module(void) { return tcf_register_action(&act_nat_ops, &nat_net_ops); } static void __exit nat_cleanup_module(void) { tcf_unregister_action(&act_nat_ops, &nat_net_ops); } module_init(nat_init_module); module_exit(nat_cleanup_module); |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_output.c - Common IPsec encapsulation code. * * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/icmp.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_route.h> #include <net/ipv6_stubs.h> #endif #include "xfrm_inout.h" static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb); static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); static int xfrm_skb_check_space(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev) - skb_headroom(skb); int ntail = dst->dev->needed_tailroom - skb_tailroom(skb); if (nhead <= 0) { if (ntail <= 0) return 0; nhead = 0; } else if (ntail < 0) ntail = 0; return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC); } /* Children define the path of the packet through the * Linux networking. Thus, destinations are stackable. */ static struct dst_entry *skb_dst_pop(struct sk_buff *skb) { struct dst_entry *child = dst_clone(xfrm_dst_child(skb_dst(skb))); skb_dst_drop(skb); return child; } /* Add encapsulation header. * * The IP header will be moved forward to make space for the encapsulation * header. */ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); int ihl = iph->ihl * 4; skb_set_inner_transport_header(skb, skb_transport_offset(skb)); skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); skb->transport_header = skb->network_header + ihl; __skb_pull(skb, ihl); memmove(skb_network_header(skb), iph, ihl); return 0; } #if IS_ENABLED(CONFIG_IPV6_MIP6) static int mip6_rthdr_offset(struct sk_buff *skb, u8 **nexthdr, int type) { const unsigned char *nh = skb_network_header(skb); unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len; int found_rhdr = 0; packet_len = skb_tail_pointer(skb) - nh; *nexthdr = &ipv6_hdr(skb)->nexthdr; while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { case NEXTHDR_HOP: break; case NEXTHDR_ROUTING: if (type == IPPROTO_ROUTING && offset + 3 <= packet_len) { struct ipv6_rt_hdr *rt; rt = (struct ipv6_rt_hdr *)(nh + offset); if (rt->type != 0) return offset; } found_rhdr = 1; break; case NEXTHDR_DEST: /* HAO MUST NOT appear more than once. * XXX: It is better to try to find by the end of * XXX: packet if HAO exists. */ if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { net_dbg_ratelimited("mip6: hao exists already, override\n"); return offset; } if (found_rhdr) return offset; break; default: return offset; } if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) return -EINVAL; exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); offset += ipv6_optlen(exthdr); if (offset > IPV6_MAXPLEN) return -EINVAL; *nexthdr = &exthdr->nexthdr; } return -EINVAL; } #endif #if IS_ENABLED(CONFIG_IPV6) static int xfrm6_hdr_offset(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr) { switch (x->type->proto) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_DSTOPTS: case IPPROTO_ROUTING: return mip6_rthdr_offset(skb, prevhdr, x->type->proto); #endif default: break; } return ip6_find_1stfragopt(skb, prevhdr); } #endif /* Add encapsulation header. * * The IP header and mutable extension headers will be moved forward to make * space for the encapsulation header. */ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *iph; u8 *prevhdr; int hdr_len; iph = ipv6_hdr(skb); skb_set_inner_transport_header(skb, skb_transport_offset(skb)); hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; __skb_pull(skb, hdr_len); memmove(ipv6_hdr(skb), iph, hdr_len); return 0; #else WARN_ON_ONCE(1); return -EAFNOSUPPORT; #endif } /* Add route optimization header space. * * The IP header and mutable extension headers will be moved forward to make * space for the route optimization header. */ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *iph; u8 *prevhdr; int hdr_len; iph = ipv6_hdr(skb); hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; __skb_pull(skb, hdr_len); memmove(ipv6_hdr(skb), iph, hdr_len); return 0; #else WARN_ON_ONCE(1); return -EAFNOSUPPORT; #endif } /* Add encapsulation header. * * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt. */ static int xfrm4_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb) { struct ip_beet_phdr *ph; struct iphdr *top_iph; int hdrlen, optlen; hdrlen = 0; optlen = XFRM_MODE_SKB_CB(skb)->optlen; if (unlikely(optlen)) hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); skb_set_network_header(skb, -x->props.header_len - hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph))); if (x->sel.family != AF_INET6) skb->network_header += IPV4_BEET_PHMAXLEN; skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); skb->transport_header = skb->network_header + sizeof(*top_iph); xfrm4_beet_make_header(skb); ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); top_iph = ip_hdr(skb); if (unlikely(optlen)) { if (WARN_ON(optlen < 0)) return -EINVAL; ph->padlen = 4 - (optlen & 4); ph->hdrlen = optlen / 8; ph->nexthdr = top_iph->protocol; if (ph->padlen) memset(ph + 1, IPOPT_NOP, ph->padlen); top_iph->protocol = IPPROTO_BEETPH; top_iph->ihl = sizeof(struct iphdr) / 4; } top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; return 0; } /* Add encapsulation header. * * The top IP header will be constructed per RFC 2401. */ static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb) { bool small_ipv6 = (skb->protocol == htons(ETH_P_IPV6)) && (skb->len <= IPV6_MIN_MTU); struct dst_entry *dst = skb_dst(skb); struct iphdr *top_iph; int flags; skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_transport_header(skb, skb_transport_offset(skb)); skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); skb->transport_header = skb->network_header + sizeof(*top_iph); top_iph = ip_hdr(skb); top_iph->ihl = 5; top_iph->version = 4; top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family); /* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */ if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP) top_iph->tos = 0; else top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos; top_iph->tos = INET_ECN_encapsulate(top_iph->tos, XFRM_MODE_SKB_CB(skb)->tos); flags = x->props.flags; if (flags & XFRM_STATE_NOECN) IP_ECN_clear(top_iph); top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) || small_ipv6 ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst)); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; ip_select_ident(dev_net(dst->dev), skb, NULL); return 0; } #if IS_ENABLED(CONFIG_IPV6) static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *top_iph; int dsfield; skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_transport_header(skb, skb_transport_offset(skb)); skb_set_network_header(skb, -x->props.header_len); skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); top_iph = ipv6_hdr(skb); top_iph->version = 6; memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, sizeof(top_iph->flow_lbl)); top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family); if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP) dsfield = 0; else dsfield = XFRM_MODE_SKB_CB(skb)->tos; dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos); if (x->props.flags & XFRM_STATE_NOECN) dsfield &= ~INET_ECN_MASK; ipv6_change_dsfield(top_iph, 0, dsfield); top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst)); top_iph->saddr = *(struct in6_addr *)&x->props.saddr; top_iph->daddr = *(struct in6_addr *)&x->id.daddr; return 0; } static int xfrm6_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *top_iph; struct ip_beet_phdr *ph; int optlen, hdr_len; hdr_len = 0; optlen = XFRM_MODE_SKB_CB(skb)->optlen; if (unlikely(optlen)) hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4); skb_set_network_header(skb, -x->props.header_len - hdr_len); if (x->sel.family != AF_INET6) skb->network_header += IPV4_BEET_PHMAXLEN; skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len); xfrm6_beet_make_header(skb); top_iph = ipv6_hdr(skb); if (unlikely(optlen)) { if (WARN_ON(optlen < 0)) return -EINVAL; ph->padlen = 4 - (optlen & 4); ph->hdrlen = optlen / 8; ph->nexthdr = top_iph->nexthdr; if (ph->padlen) memset(ph + 1, IPOPT_NOP, ph->padlen); top_iph->nexthdr = IPPROTO_BEETPH; } top_iph->saddr = *(struct in6_addr *)&x->props.saddr; top_iph->daddr = *(struct in6_addr *)&x->id.daddr; return 0; } #endif /* Add encapsulation header. * * On exit, the transport header will be set to the start of the * encapsulation header to be filled in by x->type->output and the mac * header will be set to the nextheader (protocol for IPv4) field of the * extension header directly preceding the encapsulation header, or in * its absence, that of the top IP header. * The value of the network header will always point to the top IP header * while skb->data will point to the payload. */ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { int err; err = xfrm_inner_extract_output(x, skb); if (err) return err; IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; skb->protocol = htons(ETH_P_IP); switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm4_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: return xfrm4_tunnel_encap_add(x, skb); } WARN_ON_ONCE(1); return -EOPNOTSUPP; } static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) int err; err = xfrm_inner_extract_output(x, skb); if (err) return err; skb->ignore_df = 1; skb->protocol = htons(ETH_P_IPV6); switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm6_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: return xfrm6_tunnel_encap_add(x, skb); default: WARN_ON_ONCE(1); return -EOPNOTSUPP; } #endif WARN_ON_ONCE(1); return -EAFNOSUPPORT; } static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: if (x->props.family == AF_INET) return xfrm4_prepare_output(x, skb); if (x->props.family == AF_INET6) return xfrm6_prepare_output(x, skb); break; case XFRM_MODE_TRANSPORT: if (x->props.family == AF_INET) return xfrm4_transport_output(x, skb); if (x->props.family == AF_INET6) return xfrm6_transport_output(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: if (x->props.family == AF_INET6) return xfrm6_ro_output(x, skb); WARN_ON_ONCE(1); break; default: if (x->mode_cbs && x->mode_cbs->prepare_output) return x->mode_cbs->prepare_output(x, skb); WARN_ON_ONCE(1); break; } return -EOPNOTSUPP; } #if IS_ENABLED(CONFIG_NET_PKTGEN) int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb) { return xfrm_outer_mode_output(x, skb); } EXPORT_SYMBOL_GPL(pktgen_xfrm_outer_mode_output); #endif static int xfrm_output_one(struct sk_buff *skb, int err) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; struct net *net = xs_net(x); if (err <= 0 || x->xso.type == XFRM_DEV_OFFLOAD_PACKET) goto resume; do { err = xfrm_skb_check_space(skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); goto error_nolock; } skb->mark = xfrm_smark_get(skb->mark, x); err = xfrm_outer_mode_output(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error_nolock; } spin_lock_bh(&x->lock); if (unlikely(x->km.state != XFRM_STATE_VALID)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID); err = -EINVAL; goto error; } err = xfrm_state_check_expire(x); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED); goto error; } err = xfrm_replay_overflow(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR); goto error; } x->curlft.bytes += skb->len; x->curlft.packets++; x->lastused = ktime_get_real_seconds(); spin_unlock_bh(&x->lock); skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } if (xfrm_offload(skb)) { x->type_offload->encap(x, skb); } else { /* Inner headers are invalid now. */ skb->encapsulation = 0; err = x->type->output(x, skb); if (err == -EINPROGRESS) goto out; } resume: if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error_nolock; } dst = skb_dst_pop(skb); if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } skb_dst_set(skb, dst); x = dst->xfrm; } while (x && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL)); return 0; error: spin_unlock_bh(&x->lock); error_nolock: kfree_skb(skb); out: return err; } int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err) { struct net *net = xs_net(skb_dst(skb)->xfrm); while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset_ct(skb); err = skb_dst(skb)->ops->local_out(net, sk, skb); if (unlikely(err != 1)) goto out; if (!skb_dst(skb)->xfrm) return dst_output(net, sk, skb); err = nf_hook(skb_dst(skb)->ops->family, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; } if (err == -EINPROGRESS) err = 0; out: return err; } EXPORT_SYMBOL_GPL(xfrm_output_resume); static int xfrm_dev_direct_output(struct sock *sk, struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net *net = xs_net(x); int err; dst = skb_dst_pop(skb); if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); kfree_skb(skb); return -EHOSTUNREACH; } skb_dst_set(skb, dst); nf_reset_ct(skb); err = skb_dst(skb)->ops->local_out(net, sk, skb); if (unlikely(err != 1)) { kfree_skb(skb); return err; } /* In transport mode, network destination is * directly reachable, while in tunnel mode, * inner packet network may not be. In packet * offload type, HW is responsible for hard * header packet mangling so directly xmit skb * to netdevice. */ skb->dev = x->xso.dev; __skb_push(skb, skb->dev->hard_header_len); return dev_queue_xmit(skb); } static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { return xfrm_output_resume(sk, skb, 1); } static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) { struct sk_buff *segs, *nskb; BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) return -EINVAL; skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); err = xfrm_output2(net, sk, segs); if (unlikely(err)) { kfree_skb_list(nskb); return err; } } return 0; } /* For partial checksum offload, the outer header checksum is calculated * by software and the inner header checksum is calculated by hardware. * This requires hardware to know the inner packet type to calculate * the inner header checksum. Save inner ip protocol here to avoid * traversing the packet in the vendor's xmit code. * For IPsec tunnel mode save the ip protocol from the IP header of the * plain text packet. Otherwise If the encap type is IPIP, just save * skb->inner_ipproto in any other case get the ip protocol from the IP * header. */ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x) { struct xfrm_offload *xo = xfrm_offload(skb); const struct ethhdr *eth; if (!xo) return; if (x->outer_mode.encap == XFRM_MODE_TUNNEL) { switch (x->outer_mode.family) { case AF_INET: xo->inner_ipproto = ip_hdr(skb)->protocol; break; case AF_INET6: xo->inner_ipproto = ipv6_hdr(skb)->nexthdr; break; default: break; } return; } if (x->outer_mode.encap == XFRM_MODE_IPTFS) { xo->inner_ipproto = IPPROTO_AGGFRAG; return; } /* non-Tunnel Mode */ if (!skb->encapsulation) return; if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) { xo->inner_ipproto = skb->inner_ipproto; return; } if (skb->inner_protocol_type != ENCAP_TYPE_ETHER) return; eth = (struct ethhdr *)skb_inner_mac_header(skb); switch (ntohs(eth->h_proto)) { case ETH_P_IPV6: xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr; break; case ETH_P_IP: xo->inner_ipproto = inner_ip_hdr(skb)->protocol; break; } } int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct xfrm_state *x = skb_dst(skb)->xfrm; int family; int err; family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family : skb_dst(skb)->ops->family; switch (family) { case AF_INET: memset(IPCB(skb), 0, sizeof(*IPCB(skb))); IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; break; case AF_INET6: memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; break; } if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { if (!xfrm_dev_offload_ok(skb, x)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); kfree_skb(skb); return -EHOSTUNREACH; } /* Exclusive direct xmit for tunnel mode, as * some filtering or matching rules may apply * in transport mode. */ if (x->props.mode == XFRM_MODE_TUNNEL) return xfrm_dev_direct_output(sk, x, skb); return xfrm_output_resume(sk, skb, 0); } secpath_reset(skb); if (xfrm_dev_offload_ok(skb, x)) { struct sec_path *sp; sp = secpath_set(skb); if (!sp) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); kfree_skb(skb); return -ENOMEM; } sp->olen++; sp->xvec[sp->len++] = x; xfrm_state_hold(x); xfrm_get_inner_ipproto(skb, x); skb->encapsulation = 1; if (skb_is_gso(skb)) { if (skb->inner_protocol && x->props.mode == XFRM_MODE_TUNNEL) return xfrm_output_gso(net, sk, skb); skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; goto out; } if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM) goto out; } else { if (skb_is_gso(skb)) return xfrm_output_gso(net, sk, skb); } if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); kfree_skb(skb); return err; } } out: return xfrm_output2(net, sk, skb); } EXPORT_SYMBOL_GPL(xfrm_output); int xfrm4_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE) goto out; if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df) goto out; mtu = dst_mtu(skb_dst(skb)); if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); if (skb->sk && sk_fullsock(skb->sk)) xfrm_local_error(skb, mtu); else icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); ret = -EMSGSIZE; } out: return ret; } EXPORT_SYMBOL_GPL(xfrm4_tunnel_check_size); static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb) { int err; if (x->outer_mode.encap == XFRM_MODE_BEET && ip_is_fragment(ip_hdr(skb))) { net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n"); return -EAFNOSUPPORT; } err = xfrm4_tunnel_check_size(skb); if (err) return err; XFRM_MODE_SKB_CB(skb)->protocol = ip_hdr(skb)->protocol; xfrm4_extract_header(skb); return 0; } #if IS_ENABLED(CONFIG_IPV6) int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; struct dst_entry *dst = skb_dst(skb); struct sock *sk = skb_to_full_sk(skb); if (skb->ignore_df) goto out; mtu = dst_mtu(dst); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); if (xfrm6_local_dontfrag(sk)) ipv6_stub->xfrm6_local_rxpmtu(skb, mtu); else if (sk) xfrm_local_error(skb, mtu); else icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; } out: return ret; } EXPORT_SYMBOL_GPL(xfrm6_tunnel_check_size); #endif static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) int err; err = xfrm6_tunnel_check_size(skb); if (err) return err; XFRM_MODE_SKB_CB(skb)->protocol = ipv6_hdr(skb)->nexthdr; xfrm6_extract_header(skb); return 0; #else WARN_ON_ONCE(1); return -EAFNOSUPPORT; #endif } static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): return xfrm4_extract_output(x, skb); case htons(ETH_P_IPV6): return xfrm6_extract_output(x, skb); } return -EAFNOSUPPORT; } void xfrm_local_error(struct sk_buff *skb, int mtu) { unsigned int proto; struct xfrm_state_afinfo *afinfo; if (skb->protocol == htons(ETH_P_IP)) proto = AF_INET; else if (skb->protocol == htons(ETH_P_IPV6) && skb->sk->sk_family == AF_INET6) proto = AF_INET6; else return; afinfo = xfrm_state_get_afinfo(proto); if (afinfo) { afinfo->local_error(skb, mtu); rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xfrm_local_error); |
| 947 1723 2133 2135 3010 3012 54 2954 2333 1722 2954 2134 2137 2138 92 2819 1 2821 1778 1779 1778 1946 1947 107 2 1941 1946 1946 2 1947 1945 1947 1944 1946 1947 3208 3206 11 61 1946 209 14 1966 351 125 125 6 6 264 264 716 2228 452 716 719 719 719 10 10 61 61 61 1 1 3132 2815 1813 299 1975 3135 39 39 428 402 29 419 56 335 363 94 4265 4272 4269 4269 4267 4257 14 39 39 39 299 3978 4266 14 3976 3972 14 3972 3964 38 3970 3973 153 17 83 73 149 184 200 1007 1139 749 485 16 1139 1139 1124 68 1137 1138 1011 12 199 1130 16 8 8 8 8 8 8 8 8 750 21 7 7917 9432 180 482 482 7 174 173 8 7 174 174 174 174 173 141 53 21 21 21 2 34 34 30 9 58 4 58 57 6707 5585 152 5158 5166 1 5262 4517 4411 1488 1489 1473 3630 4513 455 4119 3632 3632 672 3385 3630 9 9 3627 14 4832 3635 3369 2393 3618 17 3202 3204 2833 108 2831 106 6 2916 2919 2827 89 7 14 2823 7 94 776 2757 2757 948 172 77 200 192 45 183 184 6 156 29 113 55 15 243 243 379 25 77 74 46 28 2 154 147 1 61 147 1 118 50 50 47 2 47 3 32 200 200 138 164 2 166 163 2 124 47 3 184 32 108 156 156 103 141 47 47 16 98 71 70 117 2 116 116 10 42 71 71 65 71 71 70 71 71 116 85 4 81 280 4 7 272 206 165 3 107 56 55 37 31 31 162 162 160 162 96 97 86 6 4 54 86 11 97 97 13 4 6 6 4 4 6 2 20 31 1 15 5 21 21 11 11 1 11 8 2 22 100 30 2 63 1 1 61 16 68 17 53 31 63 43 6 18 130 56 103 38 77 49 54 63 2 67 67 103 1 6 55 24 2 25 54 23 1 22 98 29 90 98 2080 241 2348 2345 2330 33 2178 35 2179 83 7 2175 20 114 126 423 1889 2344 526 2172 2176 2173 2177 2176 1583 2172 12 12 12 12 12 12 18 19 1 1 311 312 287 1 1 245 7 29 289 40 40 246 15 50 65 65 115 115 73 2 9 4 62 1802 1802 215 1778 1782 1782 283 282 525 1773 1774 76 1701 176 35 44 104 179 4 46 118 2141 2139 1736 637 31 1 1 5 2 6 7 3 28 3 57 2 1 34 1 31 56 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> #include <linux/sysctl.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } void filemap_free_folio(struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); folio_put_refs(folio, folio_nr_pages(folio)); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @wbc: the writeback_control controlling the writeout * * Call writepages on the mapping using the provided wbc to control the * writeout. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(wbc, mapping->host); ret = do_writepages(mapping, wbc); wbc_detach_inode(wbc); return ret; } EXPORT_SYMBOL(filemap_fdatawrite_wbc); /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_fdatawrite_range_kick - start writeback on a range * @mapping: target address_space * @start: index to start writeback on * @end: last (inclusive) index for writeback * * This is a non-integrity writeback helper, to start writing back folios * for the indicated range. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE); } EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) __lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) __lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) __lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) __lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); bool huge; long nr; unsigned int forder = folio_order(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } if (old) { if (order > 0 && order > forder) { unsigned int split_order = max(forder, xas_try_split_min_order(order)); /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); while (order > forder) { xas_set_order(&xas, index, split_order); xas_try_split(&xas, old, order); if (xas_error(&xas)) goto unlock; order = split_order; split_order = max(xas_try_split_min_order( split_order), forder); } xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; ret = mem_cgroup_charge(folio, NULL, gfp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { int n; struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } /* How many times do we accept lock stealing from under a waiter? */ static int sysctl_page_lock_unfairness = 5; static const struct ctl_table filemap_sysctl_table[] = { { .procname = "page_lock_unfairness", .data = &sysctl_page_lock_unfairness, .maxlen = sizeof(sysctl_page_lock_unfairness), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, } }; void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); register_sysctl_init("vm", filemap_sysctl_table); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags)) return false; } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * migration_entry_wait_on_locked - Wait for a migration entry to be removed * @entry: migration swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page to be removed. This is * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for the migration entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = pfn_swap_entry_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); /* * If folio was marked as dropbehind, then pages should be dropped when writeback * completes. Do that now. If we fail, it's likely because of a big folio - * just reset dropbehind for that case and latter completions should invalidate. */ static void folio_end_dropbehind_write(struct folio *folio) { /* * Hitting !in_task() should not happen off RWF_DONTCACHE writeback, * but can happen if normal writeback just happens to find dirty folios * that were created as part of uncached writeback, and that writeback * would otherwise not need non-IRQ handling. Just skip the * invalidation in that case. */ if (in_task() && folio_trylock(folio)) { if (folio->mapping) folio_unmap_invalidate(folio->mapping, folio, 0); folio_unlock(folio); } } /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { bool folio_dropbehind = false; VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); if (!folio_test_dirty(folio)) folio_dropbehind = folio_test_clear_dropbehind(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); if (folio_dropbehind) folio_end_dropbehind_write(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } return index + max_scan; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned int min_order = mapping_min_folio_order(mapping); unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT | __GFP_NOWARN; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (order > mapping_max_folio_order(mapping)) order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); if (fgp_flags & FGP_DONTCACHE) __folio_set_dropbehind(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > min_order); if (err == -EEXIST) goto repeat; if (err) { /* * When NOWAIT I/O fails to allocate folios this could * be due to a nonblocking memory allocation and not * because the system actually is out of memory. * Return -EAGAIN so that there caller retries in a * blocking fashion instead of propagating -ENOMEM * to the application. */ if ((fgp_flags & FGP_NOWAIT) && err == -ENOMEM) err = -EAGAIN; return ERR_PTR(err); } /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); /* not an uncached lookup, clear uncached if set */ if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE)) folio_clear_dropbehind(folio); return folio; } EXPORT_SYMBOL(__filemap_get_folio); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } if (folio_batch_count(fbatch)) { unsigned long nr; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); else nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]); *start = round_down(indices[idx] + nr, nr); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { unsigned long base; unsigned long nr; if (!xa_is_value(folio)) { nr = folio_nr_pages(folio); base = folio->index; /* Omit large folio which begins before the start */ if (base < *start) goto put; /* Omit large folio which extends beyond the end */ if (base + nr - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } else { nr = 1 << xas_get_order(&xas); base = xas.xa_index & ~(nr - 1); /* Omit order>0 value which begins before the start */ if (base < *start) continue; /* Omit order>0 value which extends beyond the end */ if (base + nr - 1 > end) break; } /* Update start now so that last update is correct on return */ *start = base + nr; indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; /* If we landed in the middle of a THP, continue at its end. */ if (xa_is_sibling(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; if (iocb->ki_flags & IOCB_DONTCACHE) __folio_set_dropbehind(folio); /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_DONTCACHE) ractl.dropbehind = 1; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; unsigned int flags; int err = 0; /* "last_index" is the index of the page beyond the end of the read */ last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE); retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); if (iocb->ki_flags & IOCB_DONTCACHE) ractl.dropbehind = 1; page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { err = filemap_create_folio(iocb, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if ((iocb->ki_flags & IOCB_WAITQ) && folio_batch_count(fbatch) > 1) iocb->ki_flags |= IOCB_NOWAIT; err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } trace_mm_filemap_get_pages(mapping, index, last_index - 1); return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } static void filemap_end_dropbehind_read(struct address_space *mapping, struct folio *folio) { if (!folio_test_dropbehind(folio)) return; if (folio_test_writeback(folio) || folio_test_dirty(folio)) return; if (folio_trylock(folio)) { if (folio_test_clear_dropbehind(folio)) folio_unmap_invalidate(mapping, folio, 0); folio_unlock(folio); } } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos < 0)) return -EINVAL; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; filemap_end_dropbehind_read(mapping, folio); folio_put(folio); } folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait) { int ret; if (nowait) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; return filemap_invalidate_pages(mapping, iocb->ki_pos, iocb->ki_pos + count - 1, iocb->ki_flags & IOCB_NOWAIT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_is_full(pipe)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_is_full(pipe)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xas_get_order(xas); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; /* * Fetch two PMD folios, so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = HPAGE_PMD_NR; page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER); return fpin; } #endif /* If we don't want any read-ahead, don't bother */ if (vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; page_cache_ra_order(&ractl, ra, 0); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_ro_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; trace_mm_filemap_fault(mapping, index); /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (!folio_try_get(folio)) continue; if (folio_test_locked(folio)) goto skip; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; do { if (PageHWPoison(page + count)) goto skip; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) return ret; /* See comment of filemap_map_folio_range() */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) return ret; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; folio_ref_inc(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t file_end, last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; if (filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; if (end_pgoff > file_end) end_pgoff = file_end; folio_type = mm_counter_file(folio); do { unsigned long end; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages, &rss, &mmap_miss); folio_unlock(folio); folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff); out: rcu_read_unlock(); mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss >= mmap_miss_saved) WRITE_ONCE(file->f_ra.mmap_miss, 0); else WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty folio and writeprotect it again. */ folio_mark_dirty(folio); folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct folio *do_read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; if (!filler) filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, mapping_min_folio_order(mapping)); if (!folio) return ERR_PTR(-ENOMEM); index = mapping_align_index(mapping, index); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } goto filler; } if (folio_test_uptodate(folio)) goto out; if (!folio_trylock(folio)) { folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); goto repeat; } /* Folio was truncated from mapping */ if (!folio->mapping) { folio_unlock(folio); folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (folio_test_uptodate(folio)) { folio_unlock(folio); goto out; } filler: err = filemap_read_folio(file, filler, folio); if (err) { folio_put(folio); if (err == AOP_TRUNCATED_PAGE) goto repeat; return ERR_PTR(err); } out: folio_mark_accessed(folio); return folio; } /** * read_cache_folio - Read into page cache, fill it if needed. * @mapping: The address_space to read from. * @index: The index to read. * @filler: Function to perform the read, or NULL to use aops->read_folio(). * @file: Passed to filler function, may be NULL if not required. * * Read one page into the page cache. If it succeeds, the folio returned * will contain @index, but it may not be the first page of the folio. * * If the filler function returns an error, it will be returned to the * caller. * * Context: May sleep. Expects mapping->invalidate_lock to be held. * Return: An uptodate folio on success, ERR_PTR() on failure. */ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file) { return do_read_cache_folio(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_folio); /** * mapping_read_folio_gfp - Read into page cache, using specified allocation flags. * @mapping: The address_space for the folio. * @index: The index that the allocated folio will contain. * @gfp: The page allocator flags to use if allocating. * * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with * any new memory allocations done using the specified allocation flags. * * The most likely error from this function is EIO, but ENOMEM is * possible and so is EINTR. If ->read_folio returns another error, * that will be returned to the caller. * * The function expects mapping->invalidate_lock to be already held. * * Return: Uptodate folio on success, ERR_PTR() on failure. */ struct folio *mapping_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_folio(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(mapping_read_folio_gfp); static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { struct folio *folio; folio = do_read_cache_folio(mapping, index, filler, file, gfp); if (IS_ERR(folio)) return &folio->page; return folio_file_page(folio, index); } struct page *read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file) { return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * The function expects mapping->invalidate_lock to be already held. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); /* * Warn about a page cache invalidation failure during a direct I/O write. */ static void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; char *path; errseq_set(&filp->f_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; if (mapping->nrpages && invalidate_inode_pages2_range(mapping, iocb->ki_pos >> PAGE_SHIFT, (iocb->ki_pos + count - 1) >> PAGE_SHIFT)) dio_warn_stale_pagecache(iocb->ki_filp); } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct address_space *mapping = iocb->ki_filp->f_mapping; size_t write_len = iov_iter_count(from); ssize_t written; /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ written = kiocb_invalidate_pages(iocb, write_len); if (written) { if (written == -EBUSY) return 0; return written; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0) { struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; kiocb_invalidate_post_direct_write(iocb, written); pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } if (written != -EIOCBQUEUED) iov_iter_revert(from, write_len - iov_iter_count(from)); return written; } EXPORT_SYMBOL(generic_file_direct_write); ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; size_t chunk = mapping_max_folio_size(mapping); long status = 0; ssize_t written = 0; do { struct folio *folio; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; bytes = iov_iter_count(i); retry: offset = pos & (chunk - 1); bytes = min(chunk - offset, bytes); balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, &folio, &fsdata); if (unlikely(status < 0)) break; offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); /* * Faults here on mmap()s can recurse into arbitrary * filesystem code. Lots of locks are held that can * deadlock. Use an atomic copy to avoid deadlocking * in page fault handling. */ copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); flush_dcache_folio(folio); status = a_ops->write_end(file, mapping, pos, bytes, copied, folio, fsdata); if (unlikely(status != copied)) { iov_iter_revert(i, copied - max(status, 0L)); if (unlikely(status < 0)) break; } cond_resched(); if (unlikely(status == 0)) { /* * A short copy made ->write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { bytes = copied; goto retry; } /* * 'folio' is now unlocked and faults on it can be * handled. Ensure forward progress by trying to * fault it in now. */ if (fault_in_iov_iter_readable(i, bytes) == bytes) { status = -EFAULT; break; } } else { pos += status; written += status; } } while (iov_iter_count(i)); if (!written) return status; iocb->ki_pos += written; return written; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_rwsem to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_rwsem. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; ret = file_remove_privs(file); if (ret) return ret; ret = file_update_time(file); if (ret) return ret; if (iocb->ki_flags & IOCB_DIRECT) { ret = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode)) return ret; return direct_write_fallback(iocb, from, ret, generic_perform_write(iocb, from)); } return generic_perform_write(iocb, from); } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_rwsem as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * filemap_release_folio() - Release fs-specific metadata on a folio. * @folio: The folio which the kernel is trying to free. * @gfp: Memory allocation flags (and I/O mode). * * The address_space is trying to release any data attached to a folio * (presumably at folio->private). * * This will also be called if the private_2 flag is set on a page, * indicating that the folio has other metadata associated with it. * * The @gfp argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block * (__GFP_RECLAIM & __GFP_FS). * * Return: %true if the release was successful, otherwise %false. */ bool filemap_release_folio(struct folio *folio, gfp_t gfp) { struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); if (!folio_needs_release(folio)) return true; if (folio_test_writeback(folio)) return false; if (mapping && mapping->a_ops->release_folio) return mapping->a_ops->release_folio(folio, gfp); return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); /** * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache * @inode: The inode to flush * @flush: Set to write back rather than simply invalidate. * @start: First byte to in range. * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start * onwards. * * Invalidate all the folios on an inode that contribute to the specified * range, possibly writing them back first. Whilst the operation is * undertaken, the invalidate lock is held to prevent new folios from being * installed. */ int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end) { struct address_space *mapping = inode->i_mapping; pgoff_t first = start >> PAGE_SHIFT; pgoff_t last = end >> PAGE_SHIFT; pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1; if (!mapping || !mapping->nrpages || end < start) goto out; /* Prevent new folios from being added to the inode. */ filemap_invalidate_lock(mapping); if (!mapping->nrpages) goto unlock; unmap_mapping_pages(mapping, first, nr, false); /* Write back the data if we're asked to. */ if (flush) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; filemap_fdatawrite_wbc(mapping, &wbc); } /* Wait for writeback to complete on all folios and discard. */ invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE); unlock: filemap_invalidate_unlock(mapping); out: return filemap_check_errors(mapping); } EXPORT_SYMBOL_GPL(filemap_invalidate_inode); #ifdef CONFIG_CACHESTAT_SYSCALL /** * filemap_cachestat() - compute the page cache statistics of a mapping * @mapping: The mapping to compute the statistics for. * @first_index: The starting page cache index. * @last_index: The final page index (inclusive). * @cs: the cachestat struct to write the result to. * * This will query the page cache statistics of a mapping in the * page range of [first_index, last_index] (inclusive). The statistics * queried include: number of dirty pages, number of pages marked for * writeback, and the number of (recently) evicted pages. */ static void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, pgoff_t last_index, struct cachestat *cs) { XA_STATE(xas, &mapping->i_pages, first_index); struct folio *folio; /* Flush stats (and potentially sleep) outside the RCU read section. */ mem_cgroup_flush_stats_ratelimited(NULL); rcu_read_lock(); xas_for_each(&xas, folio, last_index) { int order; unsigned long nr_pages; pgoff_t folio_first_index, folio_last_index; /* * Don't deref the folio. It is not pinned, and might * get freed (and reused) underneath us. * * We *could* pin it, but that would be expensive for * what should be a fast and lightweight syscall. * * Instead, derive all information of interest from * the rcu-protected xarray. */ if (xas_retry(&xas, folio)) continue; order = xas_get_order(&xas); nr_pages = 1 << order; folio_first_index = round_down(xas.xa_index, 1 << order); folio_last_index = folio_first_index + nr_pages - 1; /* Folios might straddle the range boundaries, only count covered pages */ if (folio_first_index < first_index) nr_pages -= first_index - folio_first_index; if (folio_last_index > last_index) nr_pages -= folio_last_index - last_index; if (xa_is_value(folio)) { /* page is evicted */ void *shadow = (void *)folio; bool workingset; /* not used */ cs->nr_evicted += nr_pages; #ifdef CONFIG_SWAP /* implies CONFIG_MMU */ if (shmem_mapping(mapping)) { /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); /* swapin error results in poisoned entry */ if (non_swap_entry(swp)) goto resched; /* * Getting a swap entry from the shmem * inode means we beat * shmem_unuse(). rcu_read_lock() * ensures swapoff waits for us before * freeing the swapper space. However, * we can race with swapping and * invalidation, so there might not be * a shadow in the swapcache (yet). */ shadow = get_shadow_from_swap_cache(swp); if (!shadow) goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset, false)) cs->nr_recently_evicted += nr_pages; goto resched; } /* page is in cache */ cs->nr_cache += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY)) cs->nr_dirty += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK)) cs->nr_writeback += nr_pages; resched: if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); } /* * See mincore: reveal pagecache information only for files * that the calling process has write access to, or could (if * tried) open for writing. */ static inline bool can_do_cachestat(struct file *f) { if (f->f_mode & FMODE_WRITE) return true; if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f))) return true; return file_permission(f, MAY_WRITE) == 0; } /* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the * bytes range specified by `off` and `len`: number of cached pages, * number of dirty pages, number of pages marked for writeback, * number of evicted pages, and number of recently evicted pages. * * An evicted page is a page that is previously in the page cache * but has been evicted since. A page is recently evicted if its last * eviction was recent enough that its reentry to the cache would * indicate that it is actively being used by the system, and that * there is memory pressure on the system. * * `off` and `len` must be non-negative integers. If `len` > 0, * the queried range is [`off`, `off` + `len`]. If `len` == 0, * we will query in the range from `off` to the end of the file. * * The `flags` argument is unused for now, but is included for future * extensibility. User should pass 0 (i.e no flag specified). * * Currently, hugetlbfs is not supported. * * Because the status of a page can change after cachestat() checks it * but before it returns to the application, the returned values may * contain stale information. * * return values: * zero - success * -EFAULT - cstat or cstat_range points to an illegal address * -EINVAL - invalid flags * -EBADF - invalid file descriptor * -EOPNOTSUPP - file descriptor is of a hugetlbfs file */ SYSCALL_DEFINE4(cachestat, unsigned int, fd, struct cachestat_range __user *, cstat_range, struct cachestat __user *, cstat, unsigned int, flags) { CLASS(fd, f)(fd); struct address_space *mapping; struct cachestat_range csr; struct cachestat cs; pgoff_t first_index, last_index; if (fd_empty(f)) return -EBADF; if (copy_from_user(&csr, cstat_range, sizeof(struct cachestat_range))) return -EFAULT; /* hugetlbfs is not supported */ if (is_file_hugepages(fd_file(f))) return -EOPNOTSUPP; if (!can_do_cachestat(fd_file(f))) return -EPERM; if (flags != 0) return -EINVAL; first_index = csr.off >> PAGE_SHIFT; last_index = csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; memset(&cs, 0, sizeof(struct cachestat)); mapping = fd_file(f)->f_mapping; filemap_cachestat(mapping, first_index, last_index, &cs); if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) return -EFAULT; return 0; } #endif /* CONFIG_CACHESTAT_SYSCALL */ |
| 12 12 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Released under the GPLv2 only. */ #include <linux/usb.h> #include <linux/usb/ch9.h> #include <linux/usb/hcd.h> #include <linux/usb/quirks.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/string_choices.h> #include <linux/device.h> #include <asm/byteorder.h> #include "usb.h" #define USB_MAXALTSETTING 128 /* Hard limit */ #define USB_MAXCONFIG 8 /* Arbitrary limit */ static int find_next_descriptor(unsigned char *buffer, int size, int dt1, int dt2, int *num_skipped) { struct usb_descriptor_header *h; int n = 0; unsigned char *buffer0 = buffer; /* Find the next descriptor of type dt1 or dt2 */ while (size > 0) { h = (struct usb_descriptor_header *) buffer; if (h->bDescriptorType == dt1 || h->bDescriptorType == dt2) break; buffer += h->bLength; size -= h->bLength; ++n; } /* Store the number of descriptors skipped and return the * number of bytes skipped */ if (num_skipped) *num_skipped = n; return buffer - buffer0; } static void usb_parse_ssp_isoc_endpoint_companion(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_endpoint *ep, unsigned char *buffer, int size) { struct usb_ssp_isoc_ep_comp_descriptor *desc; /* * The SuperSpeedPlus Isoc endpoint companion descriptor immediately * follows the SuperSpeed Endpoint Companion descriptor */ desc = (struct usb_ssp_isoc_ep_comp_descriptor *) buffer; if (desc->bDescriptorType != USB_DT_SSP_ISOC_ENDPOINT_COMP || size < USB_DT_SSP_ISOC_EP_COMP_SIZE) { dev_notice(ddev, "Invalid SuperSpeedPlus isoc endpoint companion" "for config %d interface %d altsetting %d ep %d.\n", cfgno, inum, asnum, ep->desc.bEndpointAddress); return; } memcpy(&ep->ssp_isoc_ep_comp, desc, USB_DT_SSP_ISOC_EP_COMP_SIZE); } static void usb_parse_eusb2_isoc_endpoint_companion(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_endpoint *ep, unsigned char *buffer, int size) { struct usb_eusb2_isoc_ep_comp_descriptor *desc; struct usb_descriptor_header *h; /* * eUSB2 isochronous endpoint companion descriptor for this endpoint * shall be declared before the next endpoint or interface descriptor */ while (size >= USB_DT_EUSB2_ISOC_EP_COMP_SIZE) { h = (struct usb_descriptor_header *)buffer; if (h->bDescriptorType == USB_DT_EUSB2_ISOC_ENDPOINT_COMP) { desc = (struct usb_eusb2_isoc_ep_comp_descriptor *)buffer; ep->eusb2_isoc_ep_comp = *desc; return; } if (h->bDescriptorType == USB_DT_ENDPOINT || h->bDescriptorType == USB_DT_INTERFACE) break; buffer += h->bLength; size -= h->bLength; } dev_notice(ddev, "No eUSB2 isoc ep %d companion for config %d interface %d altsetting %d\n", ep->desc.bEndpointAddress, cfgno, inum, asnum); } static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_endpoint *ep, unsigned char *buffer, int size) { struct usb_ss_ep_comp_descriptor *desc; int max_tx; /* The SuperSpeed endpoint companion descriptor is supposed to * be the first thing immediately following the endpoint descriptor. */ desc = (struct usb_ss_ep_comp_descriptor *) buffer; if (desc->bDescriptorType != USB_DT_SS_ENDPOINT_COMP || size < USB_DT_SS_EP_COMP_SIZE) { dev_notice(ddev, "No SuperSpeed endpoint companion for config %d " " interface %d altsetting %d ep %d: " "using minimum values\n", cfgno, inum, asnum, ep->desc.bEndpointAddress); /* Fill in some default values. * Leave bmAttributes as zero, which will mean no streams for * bulk, and isoc won't support multiple bursts of packets. * With bursts of only one packet, and a Mult of 1, the max * amount of data moved per endpoint service interval is one * packet. */ ep->ss_ep_comp.bLength = USB_DT_SS_EP_COMP_SIZE; ep->ss_ep_comp.bDescriptorType = USB_DT_SS_ENDPOINT_COMP; if (usb_endpoint_xfer_isoc(&ep->desc) || usb_endpoint_xfer_int(&ep->desc)) ep->ss_ep_comp.wBytesPerInterval = ep->desc.wMaxPacketSize; return; } buffer += desc->bLength; size -= desc->bLength; memcpy(&ep->ss_ep_comp, desc, USB_DT_SS_EP_COMP_SIZE); /* Check the various values */ if (usb_endpoint_xfer_control(&ep->desc) && desc->bMaxBurst != 0) { dev_notice(ddev, "Control endpoint with bMaxBurst = %d in " "config %d interface %d altsetting %d ep %d: " "setting to zero\n", desc->bMaxBurst, cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bMaxBurst = 0; } else if (desc->bMaxBurst > 15) { dev_notice(ddev, "Endpoint with bMaxBurst = %d in " "config %d interface %d altsetting %d ep %d: " "setting to 15\n", desc->bMaxBurst, cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bMaxBurst = 15; } if ((usb_endpoint_xfer_control(&ep->desc) || usb_endpoint_xfer_int(&ep->desc)) && desc->bmAttributes != 0) { dev_notice(ddev, "%s endpoint with bmAttributes = %d in " "config %d interface %d altsetting %d ep %d: " "setting to zero\n", usb_endpoint_xfer_control(&ep->desc) ? "Control" : "Bulk", desc->bmAttributes, cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 0; } else if (usb_endpoint_xfer_bulk(&ep->desc) && desc->bmAttributes > 16) { dev_notice(ddev, "Bulk endpoint with more than 65536 streams in " "config %d interface %d altsetting %d ep %d: " "setting to max\n", cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 16; } else if (usb_endpoint_xfer_isoc(&ep->desc) && !USB_SS_SSP_ISOC_COMP(desc->bmAttributes) && USB_SS_MULT(desc->bmAttributes) > 3) { dev_notice(ddev, "Isoc endpoint has Mult of %d in " "config %d interface %d altsetting %d ep %d: " "setting to 3\n", USB_SS_MULT(desc->bmAttributes), cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 2; } if (usb_endpoint_xfer_isoc(&ep->desc)) max_tx = (desc->bMaxBurst + 1) * (USB_SS_MULT(desc->bmAttributes)) * usb_endpoint_maxp(&ep->desc); else if (usb_endpoint_xfer_int(&ep->desc)) max_tx = usb_endpoint_maxp(&ep->desc) * (desc->bMaxBurst + 1); else max_tx = 999999; if (le16_to_cpu(desc->wBytesPerInterval) > max_tx) { dev_notice(ddev, "%s endpoint with wBytesPerInterval of %d in " "config %d interface %d altsetting %d ep %d: " "setting to %d\n", usb_endpoint_xfer_isoc(&ep->desc) ? "Isoc" : "Int", le16_to_cpu(desc->wBytesPerInterval), cfgno, inum, asnum, ep->desc.bEndpointAddress, max_tx); ep->ss_ep_comp.wBytesPerInterval = cpu_to_le16(max_tx); } /* Parse a possible SuperSpeedPlus isoc ep companion descriptor */ if (usb_endpoint_xfer_isoc(&ep->desc) && USB_SS_SSP_ISOC_COMP(desc->bmAttributes)) usb_parse_ssp_isoc_endpoint_companion(ddev, cfgno, inum, asnum, ep, buffer, size); } static const unsigned short low_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 8, [USB_ENDPOINT_XFER_ISOC] = 0, [USB_ENDPOINT_XFER_BULK] = 0, [USB_ENDPOINT_XFER_INT] = 8, }; static const unsigned short full_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 64, [USB_ENDPOINT_XFER_ISOC] = 1023, [USB_ENDPOINT_XFER_BULK] = 64, [USB_ENDPOINT_XFER_INT] = 64, }; static const unsigned short high_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 64, [USB_ENDPOINT_XFER_ISOC] = 1024, /* Bulk should be 512, but some devices use 1024: we will warn below */ [USB_ENDPOINT_XFER_BULK] = 1024, [USB_ENDPOINT_XFER_INT] = 1024, }; static const unsigned short super_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 512, [USB_ENDPOINT_XFER_ISOC] = 1024, [USB_ENDPOINT_XFER_BULK] = 1024, [USB_ENDPOINT_XFER_INT] = 1024, }; static bool endpoint_is_duplicate(struct usb_endpoint_descriptor *e1, struct usb_endpoint_descriptor *e2) { if (e1->bEndpointAddress == e2->bEndpointAddress) return true; if (usb_endpoint_xfer_control(e1) || usb_endpoint_xfer_control(e2)) { if (usb_endpoint_num(e1) == usb_endpoint_num(e2)) return true; } return false; } /* * Check for duplicate endpoint addresses in other interfaces and in the * altsetting currently being parsed. */ static bool config_endpoint_is_duplicate(struct usb_host_config *config, int inum, int asnum, struct usb_endpoint_descriptor *d) { struct usb_endpoint_descriptor *epd; struct usb_interface_cache *intfc; struct usb_host_interface *alt; int i, j, k; for (i = 0; i < config->desc.bNumInterfaces; ++i) { intfc = config->intf_cache[i]; for (j = 0; j < intfc->num_altsetting; ++j) { alt = &intfc->altsetting[j]; if (alt->desc.bInterfaceNumber == inum && alt->desc.bAlternateSetting != asnum) continue; for (k = 0; k < alt->desc.bNumEndpoints; ++k) { epd = &alt->endpoint[k].desc; if (endpoint_is_duplicate(epd, d)) return true; } } } return false; } static int usb_parse_endpoint(struct device *ddev, int cfgno, struct usb_host_config *config, int inum, int asnum, struct usb_host_interface *ifp, int num_ep, unsigned char *buffer, int size) { struct usb_device *udev = to_usb_device(ddev); unsigned char *buffer0 = buffer; struct usb_endpoint_descriptor *d; struct usb_host_endpoint *endpoint; int n, i, j, retval; unsigned int maxp; const unsigned short *maxpacket_maxes; u16 bcdUSB; d = (struct usb_endpoint_descriptor *) buffer; bcdUSB = le16_to_cpu(udev->descriptor.bcdUSB); buffer += d->bLength; size -= d->bLength; if (d->bLength >= USB_DT_ENDPOINT_AUDIO_SIZE) n = USB_DT_ENDPOINT_AUDIO_SIZE; else if (d->bLength >= USB_DT_ENDPOINT_SIZE) n = USB_DT_ENDPOINT_SIZE; else { dev_notice(ddev, "config %d interface %d altsetting %d has an " "invalid endpoint descriptor of length %d, skipping\n", cfgno, inum, asnum, d->bLength); goto skip_to_next_endpoint_or_interface_descriptor; } i = d->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK; if (i == 0) { dev_notice(ddev, "config %d interface %d altsetting %d has an " "invalid descriptor for endpoint zero, skipping\n", cfgno, inum, asnum); goto skip_to_next_endpoint_or_interface_descriptor; } /* Only store as many endpoints as we have room for */ if (ifp->desc.bNumEndpoints >= num_ep) goto skip_to_next_endpoint_or_interface_descriptor; /* Save a copy of the descriptor and use it instead of the original */ endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints]; memcpy(&endpoint->desc, d, n); d = &endpoint->desc; /* Clear the reserved bits in bEndpointAddress */ i = d->bEndpointAddress & (USB_ENDPOINT_DIR_MASK | USB_ENDPOINT_NUMBER_MASK); if (i != d->bEndpointAddress) { dev_notice(ddev, "config %d interface %d altsetting %d has an endpoint descriptor with address 0x%X, changing to 0x%X\n", cfgno, inum, asnum, d->bEndpointAddress, i); endpoint->desc.bEndpointAddress = i; } /* Check for duplicate endpoint addresses */ if (config_endpoint_is_duplicate(config, inum, asnum, d)) { dev_notice(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n", cfgno, inum, asnum, d->bEndpointAddress); goto skip_to_next_endpoint_or_interface_descriptor; } /* Ignore some endpoints */ if (udev->quirks & USB_QUIRK_ENDPOINT_IGNORE) { if (usb_endpoint_is_ignored(udev, ifp, d)) { dev_notice(ddev, "config %d interface %d altsetting %d has an ignored endpoint with address 0x%X, skipping\n", cfgno, inum, asnum, d->bEndpointAddress); goto skip_to_next_endpoint_or_interface_descriptor; } } /* Accept this endpoint */ ++ifp->desc.bNumEndpoints; INIT_LIST_HEAD(&endpoint->urb_list); /* * Fix up bInterval values outside the legal range. * Use 10 or 8 ms if no proper value can be guessed. */ i = 0; /* i = min, j = max, n = default */ j = 255; if (usb_endpoint_xfer_int(d)) { i = 1; switch (udev->speed) { case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: case USB_SPEED_HIGH: /* * Many device manufacturers are using full-speed * bInterval values in high-speed interrupt endpoint * descriptors. Try to fix those and fall back to an * 8-ms default value otherwise. */ n = fls(d->bInterval*8); if (n == 0) n = 7; /* 8 ms = 2^(7-1) uframes */ j = 16; /* * Adjust bInterval for quirked devices. */ /* * This quirk fixes bIntervals reported in ms. */ if (udev->quirks & USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval) + 3, i, j); i = j = n; } /* * This quirk fixes bIntervals reported in * linear microframes. */ if (udev->quirks & USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval), i, j); i = j = n; } break; default: /* USB_SPEED_FULL or _LOW */ /* * For low-speed, 10 ms is the official minimum. * But some "overclocked" devices might want faster * polling so we'll allow it. */ n = 10; break; } } else if (usb_endpoint_xfer_isoc(d)) { i = 1; j = 16; switch (udev->speed) { case USB_SPEED_HIGH: n = 7; /* 8 ms = 2^(7-1) uframes */ break; default: /* USB_SPEED_FULL */ n = 4; /* 8 ms = 2^(4-1) frames */ break; } } if (d->bInterval < i || d->bInterval > j) { dev_notice(ddev, "config %d interface %d altsetting %d " "endpoint 0x%X has an invalid bInterval %d, " "changing to %d\n", cfgno, inum, asnum, d->bEndpointAddress, d->bInterval, n); endpoint->desc.bInterval = n; } /* Some buggy low-speed devices have Bulk endpoints, which is * explicitly forbidden by the USB spec. In an attempt to make * them usable, we will try treating them as Interrupt endpoints. */ if (udev->speed == USB_SPEED_LOW && usb_endpoint_xfer_bulk(d)) { dev_notice(ddev, "config %d interface %d altsetting %d " "endpoint 0x%X is Bulk; changing to Interrupt\n", cfgno, inum, asnum, d->bEndpointAddress); endpoint->desc.bmAttributes = USB_ENDPOINT_XFER_INT; endpoint->desc.bInterval = 1; if (usb_endpoint_maxp(&endpoint->desc) > 8) endpoint->desc.wMaxPacketSize = cpu_to_le16(8); } /* * Validate the wMaxPacketSize field. * eUSB2 devices (see USB 2.0 Double Isochronous IN ECN 9.6.6 Endpoint) * and devices with isochronous endpoints in altsetting 0 (see USB 2.0 * end of section 5.6.3) have wMaxPacketSize = 0. * So don't warn about those. */ maxp = le16_to_cpu(endpoint->desc.wMaxPacketSize); if (maxp == 0 && bcdUSB != 0x0220 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) dev_notice(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n", cfgno, inum, asnum, d->bEndpointAddress); /* Find the highest legal maxpacket size for this endpoint */ i = 0; /* additional transactions per microframe */ switch (udev->speed) { case USB_SPEED_LOW: maxpacket_maxes = low_speed_maxpacket_maxes; break; case USB_SPEED_FULL: maxpacket_maxes = full_speed_maxpacket_maxes; break; case USB_SPEED_HIGH: /* Multiple-transactions bits are allowed only for HS periodic endpoints */ if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) { i = maxp & USB_EP_MAXP_MULT_MASK; maxp &= ~i; } fallthrough; default: maxpacket_maxes = high_speed_maxpacket_maxes; break; case USB_SPEED_SUPER: case USB_SPEED_SUPER_PLUS: maxpacket_maxes = super_speed_maxpacket_maxes; break; } j = maxpacket_maxes[usb_endpoint_type(&endpoint->desc)]; if (maxp > j) { dev_notice(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid maxpacket %d, setting to %d\n", cfgno, inum, asnum, d->bEndpointAddress, maxp, j); maxp = j; endpoint->desc.wMaxPacketSize = cpu_to_le16(i | maxp); } /* * Some buggy high speed devices have bulk endpoints using * maxpacket sizes other than 512. High speed HCDs may not * be able to handle that particular bug, so let's warn... */ if (udev->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) { if (maxp != 512) dev_notice(ddev, "config %d interface %d altsetting %d " "bulk endpoint 0x%X has invalid maxpacket %d\n", cfgno, inum, asnum, d->bEndpointAddress, maxp); } /* Parse a possible eUSB2 periodic endpoint companion descriptor */ if (bcdUSB == 0x0220 && d->wMaxPacketSize == 0 && (usb_endpoint_xfer_isoc(d) || usb_endpoint_xfer_int(d))) usb_parse_eusb2_isoc_endpoint_companion(ddev, cfgno, inum, asnum, endpoint, buffer, size); /* Parse a possible SuperSpeed endpoint companion descriptor */ if (udev->speed >= USB_SPEED_SUPER) usb_parse_ss_endpoint_companion(ddev, cfgno, inum, asnum, endpoint, buffer, size); /* Skip over any Class Specific or Vendor Specific descriptors; * find the next endpoint or interface descriptor */ endpoint->extra = buffer; i = find_next_descriptor(buffer, size, USB_DT_ENDPOINT, USB_DT_INTERFACE, &n); endpoint->extralen = i; retval = buffer - buffer0 + i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", n, str_plural(n), "endpoint"); return retval; skip_to_next_endpoint_or_interface_descriptor: i = find_next_descriptor(buffer, size, USB_DT_ENDPOINT, USB_DT_INTERFACE, NULL); return buffer - buffer0 + i; } void usb_release_interface_cache(struct kref *ref) { struct usb_interface_cache *intfc = ref_to_usb_interface_cache(ref); int j; for (j = 0; j < intfc->num_altsetting; j++) { struct usb_host_interface *alt = &intfc->altsetting[j]; kfree(alt->endpoint); kfree(alt->string); } kfree(intfc); } static int usb_parse_interface(struct device *ddev, int cfgno, struct usb_host_config *config, unsigned char *buffer, int size, u8 inums[], u8 nalts[]) { unsigned char *buffer0 = buffer; struct usb_interface_descriptor *d; int inum, asnum; struct usb_interface_cache *intfc; struct usb_host_interface *alt; int i, n; int len, retval; int num_ep, num_ep_orig; d = (struct usb_interface_descriptor *) buffer; buffer += d->bLength; size -= d->bLength; if (d->bLength < USB_DT_INTERFACE_SIZE) goto skip_to_next_interface_descriptor; /* Which interface entry is this? */ intfc = NULL; inum = d->bInterfaceNumber; for (i = 0; i < config->desc.bNumInterfaces; ++i) { if (inums[i] == inum) { intfc = config->intf_cache[i]; break; } } if (!intfc || intfc->num_altsetting >= nalts[i]) goto skip_to_next_interface_descriptor; /* Check for duplicate altsetting entries */ asnum = d->bAlternateSetting; for ((i = 0, alt = &intfc->altsetting[0]); i < intfc->num_altsetting; (++i, ++alt)) { if (alt->desc.bAlternateSetting == asnum) { dev_notice(ddev, "Duplicate descriptor for config %d " "interface %d altsetting %d, skipping\n", cfgno, inum, asnum); goto skip_to_next_interface_descriptor; } } ++intfc->num_altsetting; memcpy(&alt->desc, d, USB_DT_INTERFACE_SIZE); /* Skip over any Class Specific or Vendor Specific descriptors; * find the first endpoint or interface descriptor */ alt->extra = buffer; i = find_next_descriptor(buffer, size, USB_DT_ENDPOINT, USB_DT_INTERFACE, &n); alt->extralen = i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", n, str_plural(n), "interface"); buffer += i; size -= i; /* Allocate space for the right(?) number of endpoints */ num_ep = num_ep_orig = alt->desc.bNumEndpoints; alt->desc.bNumEndpoints = 0; /* Use as a counter */ if (num_ep > USB_MAXENDPOINTS) { dev_notice(ddev, "too many endpoints for config %d interface %d " "altsetting %d: %d, using maximum allowed: %d\n", cfgno, inum, asnum, num_ep, USB_MAXENDPOINTS); num_ep = USB_MAXENDPOINTS; } if (num_ep > 0) { /* Can't allocate 0 bytes */ len = sizeof(struct usb_host_endpoint) * num_ep; alt->endpoint = kzalloc(len, GFP_KERNEL); if (!alt->endpoint) return -ENOMEM; } /* Parse all the endpoint descriptors */ n = 0; while (size > 0) { if (((struct usb_descriptor_header *) buffer)->bDescriptorType == USB_DT_INTERFACE) break; retval = usb_parse_endpoint(ddev, cfgno, config, inum, asnum, alt, num_ep, buffer, size); if (retval < 0) return retval; ++n; buffer += retval; size -= retval; } if (n != num_ep_orig) dev_notice(ddev, "config %d interface %d altsetting %d has %d " "endpoint descriptor%s, different from the interface " "descriptor's value: %d\n", cfgno, inum, asnum, n, str_plural(n), num_ep_orig); return buffer - buffer0; skip_to_next_interface_descriptor: i = find_next_descriptor(buffer, size, USB_DT_INTERFACE, USB_DT_INTERFACE, NULL); return buffer - buffer0 + i; } static int usb_parse_configuration(struct usb_device *dev, int cfgidx, struct usb_host_config *config, unsigned char *buffer, int size) { struct device *ddev = &dev->dev; unsigned char *buffer0 = buffer; int cfgno; int nintf, nintf_orig; int i, j, n; struct usb_interface_cache *intfc; unsigned char *buffer2; int size2; struct usb_descriptor_header *header; int retval; u8 inums[USB_MAXINTERFACES], nalts[USB_MAXINTERFACES]; unsigned iad_num = 0; memcpy(&config->desc, buffer, USB_DT_CONFIG_SIZE); nintf = nintf_orig = config->desc.bNumInterfaces; config->desc.bNumInterfaces = 0; // Adjusted later if (config->desc.bDescriptorType != USB_DT_CONFIG || config->desc.bLength < USB_DT_CONFIG_SIZE || config->desc.bLength > size) { dev_notice(ddev, "invalid descriptor for config index %d: " "type = 0x%X, length = %d\n", cfgidx, config->desc.bDescriptorType, config->desc.bLength); return -EINVAL; } cfgno = config->desc.bConfigurationValue; buffer += config->desc.bLength; size -= config->desc.bLength; if (nintf > USB_MAXINTERFACES) { dev_notice(ddev, "config %d has too many interfaces: %d, " "using maximum allowed: %d\n", cfgno, nintf, USB_MAXINTERFACES); nintf = USB_MAXINTERFACES; } /* Go through the descriptors, checking their length and counting the * number of altsettings for each interface */ n = 0; for ((buffer2 = buffer, size2 = size); size2 > 0; (buffer2 += header->bLength, size2 -= header->bLength)) { if (size2 < sizeof(struct usb_descriptor_header)) { dev_notice(ddev, "config %d descriptor has %d excess " "byte%s, ignoring\n", cfgno, size2, str_plural(size2)); break; } header = (struct usb_descriptor_header *) buffer2; if ((header->bLength > size2) || (header->bLength < 2)) { dev_notice(ddev, "config %d has an invalid descriptor " "of length %d, skipping remainder of the config\n", cfgno, header->bLength); break; } if (header->bDescriptorType == USB_DT_INTERFACE) { struct usb_interface_descriptor *d; int inum; d = (struct usb_interface_descriptor *) header; if (d->bLength < USB_DT_INTERFACE_SIZE) { dev_notice(ddev, "config %d has an invalid " "interface descriptor of length %d, " "skipping\n", cfgno, d->bLength); continue; } inum = d->bInterfaceNumber; if ((dev->quirks & USB_QUIRK_HONOR_BNUMINTERFACES) && n >= nintf_orig) { dev_notice(ddev, "config %d has more interface " "descriptors, than it declares in " "bNumInterfaces, ignoring interface " "number: %d\n", cfgno, inum); continue; } if (inum >= nintf_orig) dev_notice(ddev, "config %d has an invalid " "interface number: %d but max is %d\n", cfgno, inum, nintf_orig - 1); /* Have we already encountered this interface? * Count its altsettings */ for (i = 0; i < n; ++i) { if (inums[i] == inum) break; } if (i < n) { if (nalts[i] < 255) ++nalts[i]; } else if (n < USB_MAXINTERFACES) { inums[n] = inum; nalts[n] = 1; ++n; } } else if (header->bDescriptorType == USB_DT_INTERFACE_ASSOCIATION) { struct usb_interface_assoc_descriptor *d; d = (struct usb_interface_assoc_descriptor *)header; if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) { dev_notice(ddev, "config %d has an invalid interface association descriptor of length %d, skipping\n", cfgno, d->bLength); continue; } if (iad_num == USB_MAXIADS) { dev_notice(ddev, "found more Interface " "Association Descriptors " "than allocated for in " "configuration %d\n", cfgno); } else { config->intf_assoc[iad_num] = d; iad_num++; } } else if (header->bDescriptorType == USB_DT_DEVICE || header->bDescriptorType == USB_DT_CONFIG) dev_notice(ddev, "config %d contains an unexpected " "descriptor of type 0x%X, skipping\n", cfgno, header->bDescriptorType); } /* for ((buffer2 = buffer, size2 = size); ...) */ size = buffer2 - buffer; config->desc.wTotalLength = cpu_to_le16(buffer2 - buffer0); if (n != nintf) dev_notice(ddev, "config %d has %d interface%s, different from " "the descriptor's value: %d\n", cfgno, n, str_plural(n), nintf_orig); else if (n == 0) dev_notice(ddev, "config %d has no interfaces?\n", cfgno); config->desc.bNumInterfaces = nintf = n; /* Check for missing interface numbers */ for (i = 0; i < nintf; ++i) { for (j = 0; j < nintf; ++j) { if (inums[j] == i) break; } if (j >= nintf) dev_notice(ddev, "config %d has no interface number " "%d\n", cfgno, i); } /* Allocate the usb_interface_caches and altsetting arrays */ for (i = 0; i < nintf; ++i) { j = nalts[i]; if (j > USB_MAXALTSETTING) { dev_notice(ddev, "too many alternate settings for " "config %d interface %d: %d, " "using maximum allowed: %d\n", cfgno, inums[i], j, USB_MAXALTSETTING); nalts[i] = j = USB_MAXALTSETTING; } intfc = kzalloc(struct_size(intfc, altsetting, j), GFP_KERNEL); config->intf_cache[i] = intfc; if (!intfc) return -ENOMEM; kref_init(&intfc->ref); } /* FIXME: parse the BOS descriptor */ /* Skip over any Class Specific or Vendor Specific descriptors; * find the first interface descriptor */ config->extra = buffer; i = find_next_descriptor(buffer, size, USB_DT_INTERFACE, USB_DT_INTERFACE, &n); config->extralen = i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", n, str_plural(n), "configuration"); buffer += i; size -= i; /* Parse all the interface/altsetting descriptors */ while (size > 0) { retval = usb_parse_interface(ddev, cfgno, config, buffer, size, inums, nalts); if (retval < 0) return retval; buffer += retval; size -= retval; } /* Check for missing altsettings */ for (i = 0; i < nintf; ++i) { intfc = config->intf_cache[i]; for (j = 0; j < intfc->num_altsetting; ++j) { for (n = 0; n < intfc->num_altsetting; ++n) { if (intfc->altsetting[n].desc. bAlternateSetting == j) break; } if (n >= intfc->num_altsetting) dev_notice(ddev, "config %d interface %d has no " "altsetting %d\n", cfgno, inums[i], j); } } return 0; } /* hub-only!! ... and only exported for reset/reinit path. * otherwise used internally on disconnect/destroy path */ void usb_destroy_configuration(struct usb_device *dev) { int c, i; if (!dev->config) return; if (dev->rawdescriptors) { for (i = 0; i < dev->descriptor.bNumConfigurations; i++) kfree(dev->rawdescriptors[i]); kfree(dev->rawdescriptors); dev->rawdescriptors = NULL; } for (c = 0; c < dev->descriptor.bNumConfigurations; c++) { struct usb_host_config *cf = &dev->config[c]; kfree(cf->string); for (i = 0; i < cf->desc.bNumInterfaces; i++) { if (cf->intf_cache[i]) kref_put(&cf->intf_cache[i]->ref, usb_release_interface_cache); } } kfree(dev->config); dev->config = NULL; } /* * Get the USB config descriptors, cache and parse'em * * hub-only!! ... and only in reset path, or usb_new_device() * (used by real hubs and virtual root hubs) */ int usb_get_configuration(struct usb_device *dev) { struct device *ddev = &dev->dev; int ncfg = dev->descriptor.bNumConfigurations; unsigned int cfgno, length; unsigned char *bigbuffer; struct usb_config_descriptor *desc; int result; if (ncfg > USB_MAXCONFIG) { dev_notice(ddev, "too many configurations: %d, " "using maximum allowed: %d\n", ncfg, USB_MAXCONFIG); dev->descriptor.bNumConfigurations = ncfg = USB_MAXCONFIG; } if (ncfg < 1) { dev_err(ddev, "no configurations\n"); return -EINVAL; } length = ncfg * sizeof(struct usb_host_config); dev->config = kzalloc(length, GFP_KERNEL); if (!dev->config) return -ENOMEM; length = ncfg * sizeof(char *); dev->rawdescriptors = kzalloc(length, GFP_KERNEL); if (!dev->rawdescriptors) return -ENOMEM; desc = kmalloc(USB_DT_CONFIG_SIZE, GFP_KERNEL); if (!desc) return -ENOMEM; for (cfgno = 0; cfgno < ncfg; cfgno++) { /* We grab just the first descriptor so we know how long * the whole configuration is */ result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, desc, USB_DT_CONFIG_SIZE); if (result < 0) { dev_err(ddev, "unable to read config index %d " "descriptor/%s: %d\n", cfgno, "start", result); if (result != -EPIPE) goto err; dev_notice(ddev, "chopping to %d config(s)\n", cfgno); dev->descriptor.bNumConfigurations = cfgno; break; } else if (result < 4) { dev_err(ddev, "config index %d descriptor too short " "(expected %i, got %i)\n", cfgno, USB_DT_CONFIG_SIZE, result); result = -EINVAL; goto err; } length = max_t(int, le16_to_cpu(desc->wTotalLength), USB_DT_CONFIG_SIZE); /* Now that we know the length, get the whole thing */ bigbuffer = kmalloc(length, GFP_KERNEL); if (!bigbuffer) { result = -ENOMEM; goto err; } if (dev->quirks & USB_QUIRK_DELAY_INIT) msleep(200); result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); if (result < 0) { dev_err(ddev, "unable to read config index %d " "descriptor/%s\n", cfgno, "all"); kfree(bigbuffer); goto err; } if (result < length) { dev_notice(ddev, "config index %d descriptor too short " "(expected %i, got %i)\n", cfgno, length, result); length = result; } dev->rawdescriptors[cfgno] = bigbuffer; result = usb_parse_configuration(dev, cfgno, &dev->config[cfgno], bigbuffer, length); if (result < 0) { ++cfgno; goto err; } } err: kfree(desc); dev->descriptor.bNumConfigurations = cfgno; return result; } void usb_release_bos_descriptor(struct usb_device *dev) { if (dev->bos) { kfree(dev->bos->desc); kfree(dev->bos); dev->bos = NULL; } } static const __u8 bos_desc_len[256] = { [USB_CAP_TYPE_WIRELESS_USB] = USB_DT_USB_WIRELESS_CAP_SIZE, [USB_CAP_TYPE_EXT] = USB_DT_USB_EXT_CAP_SIZE, [USB_SS_CAP_TYPE] = USB_DT_USB_SS_CAP_SIZE, [USB_SSP_CAP_TYPE] = USB_DT_USB_SSP_CAP_SIZE(1), [CONTAINER_ID_TYPE] = USB_DT_USB_SS_CONTN_ID_SIZE, [USB_PTM_CAP_TYPE] = USB_DT_USB_PTM_ID_SIZE, }; /* Get BOS descriptor set */ int usb_get_bos_descriptor(struct usb_device *dev) { struct device *ddev = &dev->dev; struct usb_bos_descriptor *bos; struct usb_dev_cap_header *cap; struct usb_ssp_cap_descriptor *ssp_cap; unsigned char *buffer, *buffer0; int length, total_len, num, i, ssac; __u8 cap_type; int ret; bos = kzalloc(sizeof(*bos), GFP_KERNEL); if (!bos) return -ENOMEM; /* Get BOS descriptor */ ret = usb_get_descriptor(dev, USB_DT_BOS, 0, bos, USB_DT_BOS_SIZE); if (ret < USB_DT_BOS_SIZE || bos->bLength < USB_DT_BOS_SIZE) { dev_notice(ddev, "unable to get BOS descriptor or descriptor too short\n"); if (ret >= 0) ret = -ENOMSG; kfree(bos); return ret; } length = bos->bLength; total_len = le16_to_cpu(bos->wTotalLength); num = bos->bNumDeviceCaps; kfree(bos); if (total_len < length) return -EINVAL; dev->bos = kzalloc(sizeof(*dev->bos), GFP_KERNEL); if (!dev->bos) return -ENOMEM; /* Now let's get the whole BOS descriptor set */ buffer = kzalloc(total_len, GFP_KERNEL); if (!buffer) { ret = -ENOMEM; goto err; } dev->bos->desc = (struct usb_bos_descriptor *)buffer; ret = usb_get_descriptor(dev, USB_DT_BOS, 0, buffer, total_len); if (ret < total_len) { dev_notice(ddev, "unable to get BOS descriptor set\n"); if (ret >= 0) ret = -ENOMSG; goto err; } buffer0 = buffer; total_len -= length; buffer += length; for (i = 0; i < num; i++) { cap = (struct usb_dev_cap_header *)buffer; if (total_len < sizeof(*cap) || total_len < cap->bLength) { dev->bos->desc->bNumDeviceCaps = i; break; } cap_type = cap->bDevCapabilityType; length = cap->bLength; if (bos_desc_len[cap_type] && length < bos_desc_len[cap_type]) { dev->bos->desc->bNumDeviceCaps = i; break; } if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) { dev_notice(ddev, "descriptor type invalid, skip\n"); goto skip_to_next_descriptor; } switch (cap_type) { case USB_CAP_TYPE_EXT: dev->bos->ext_cap = (struct usb_ext_cap_descriptor *)buffer; break; case USB_SS_CAP_TYPE: dev->bos->ss_cap = (struct usb_ss_cap_descriptor *)buffer; break; case USB_SSP_CAP_TYPE: ssp_cap = (struct usb_ssp_cap_descriptor *)buffer; ssac = (le32_to_cpu(ssp_cap->bmAttributes) & USB_SSP_SUBLINK_SPEED_ATTRIBS); if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac)) dev->bos->ssp_cap = ssp_cap; break; case CONTAINER_ID_TYPE: dev->bos->ss_id = (struct usb_ss_container_id_descriptor *)buffer; break; case USB_PTM_CAP_TYPE: dev->bos->ptm_cap = (struct usb_ptm_cap_descriptor *)buffer; break; default: break; } skip_to_next_descriptor: total_len -= length; buffer += length; } dev->bos->desc->wTotalLength = cpu_to_le16(buffer - buffer0); return 0; err: usb_release_bos_descriptor(dev); return ret; } |
| 43 43 43 43 43 43 43 43 43 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2014 Nicira, Inc. */ #include "flow.h" #include "datapath.h" #include "flow_netlink.h" #include <linux/uaccess.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <net/llc_pdu.h> #include <linux/kernel.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/llc.h> #include <linux/module.h> #include <linux/in.h> #include <linux/rcupdate.h> #include <linux/cpumask.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/sctp.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/rculist.h> #include <linux/sort.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #define TBL_MIN_BUCKETS 1024 #define MASK_ARRAY_SIZE_MIN 16 #define REHASH_INTERVAL (10 * 60 * HZ) #define MC_DEFAULT_HASH_ENTRIES 256 #define MC_HASH_SHIFT 8 #define MC_HASH_SEGS ((sizeof(uint32_t) * 8) / MC_HASH_SHIFT) static struct kmem_cache *flow_cache; struct kmem_cache *flow_stats_cache __read_mostly; static u16 range_n_bytes(const struct sw_flow_key_range *range) { return range->end - range->start; } void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, bool full, const struct sw_flow_mask *mask) { int start = full ? 0 : mask->range.start; int len = full ? sizeof *dst : range_n_bytes(&mask->range); const long *m = (const long *)((const u8 *)&mask->key + start); const long *s = (const long *)((const u8 *)src + start); long *d = (long *)((u8 *)dst + start); int i; /* If 'full' is true then all of 'dst' is fully initialized. Otherwise, * if 'full' is false the memory outside of the 'mask->range' is left * uninitialized. This can be used as an optimization when further * operations on 'dst' only use contents within 'mask->range'. */ for (i = 0; i < len; i += sizeof(long)) *d++ = *s++ & *m++; } struct sw_flow *ovs_flow_alloc(void) { struct sw_flow *flow; struct sw_flow_stats *stats; flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL); if (!flow) return ERR_PTR(-ENOMEM); flow->stats_last_writer = -1; flow->cpu_used_mask = (struct cpumask *)&flow->stats[nr_cpu_ids]; /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, GFP_KERNEL | __GFP_ZERO, node_online(0) ? 0 : NUMA_NO_NODE); if (!stats) goto err; spin_lock_init(&stats->lock); RCU_INIT_POINTER(flow->stats[0], stats); cpumask_set_cpu(0, flow->cpu_used_mask); return flow; err: kmem_cache_free(flow_cache, flow); return ERR_PTR(-ENOMEM); } int ovs_flow_tbl_count(const struct flow_table *table) { return table->count; } static void flow_free(struct sw_flow *flow) { int cpu; if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); if (flow->sf_acts) ovs_nla_free_flow_actions((struct sw_flow_actions __force *) flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); } kmem_cache_free(flow_cache, flow); } static void rcu_free_flow_callback(struct rcu_head *rcu) { struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu); flow_free(flow); } void ovs_flow_free(struct sw_flow *flow, bool deferred) { if (!flow) return; if (deferred) call_rcu(&flow->rcu, rcu_free_flow_callback); else flow_free(flow); } static void __table_instance_destroy(struct table_instance *ti) { kvfree(ti->buckets); kfree(ti); } static struct table_instance *table_instance_alloc(int new_size) { struct table_instance *ti = kmalloc(sizeof(*ti), GFP_KERNEL); int i; if (!ti) return NULL; ti->buckets = kvmalloc_array(new_size, sizeof(struct hlist_head), GFP_KERNEL); if (!ti->buckets) { kfree(ti); return NULL; } for (i = 0; i < new_size; i++) INIT_HLIST_HEAD(&ti->buckets[i]); ti->n_buckets = new_size; ti->node_ver = 0; get_random_bytes(&ti->hash_seed, sizeof(u32)); return ti; } static void __mask_array_destroy(struct mask_array *ma) { free_percpu(ma->masks_usage_stats); kfree(ma); } static void mask_array_rcu_cb(struct rcu_head *rcu) { struct mask_array *ma = container_of(rcu, struct mask_array, rcu); __mask_array_destroy(ma); } static void tbl_mask_array_reset_counters(struct mask_array *ma) { int i, cpu; /* As the per CPU counters are not atomic we can not go ahead and * reset them from another CPU. To be able to still have an approximate * zero based counter we store the value at reset, and subtract it * later when processing. */ for (i = 0; i < ma->max; i++) { ma->masks_usage_zero_cntr[i] = 0; for_each_possible_cpu(cpu) { struct mask_array_stats *stats; unsigned int start; u64 counter; stats = per_cpu_ptr(ma->masks_usage_stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); counter = stats->usage_cntrs[i]; } while (u64_stats_fetch_retry(&stats->syncp, start)); ma->masks_usage_zero_cntr[i] += counter; } } } static struct mask_array *tbl_mask_array_alloc(int size) { struct mask_array *new; size = max(MASK_ARRAY_SIZE_MIN, size); new = kzalloc(struct_size(new, masks, size) + sizeof(u64) * size, GFP_KERNEL); if (!new) return NULL; new->masks_usage_zero_cntr = (u64 *)((u8 *)new + struct_size(new, masks, size)); new->masks_usage_stats = __alloc_percpu(sizeof(struct mask_array_stats) + sizeof(u64) * size, __alignof__(u64)); if (!new->masks_usage_stats) { kfree(new); return NULL; } new->count = 0; new->max = size; return new; } static int tbl_mask_array_realloc(struct flow_table *tbl, int size) { struct mask_array *old; struct mask_array *new; new = tbl_mask_array_alloc(size); if (!new) return -ENOMEM; old = ovsl_dereference(tbl->mask_array); if (old) { int i; for (i = 0; i < old->max; i++) { if (ovsl_dereference(old->masks[i])) new->masks[new->count++] = old->masks[i]; } call_rcu(&old->rcu, mask_array_rcu_cb); } rcu_assign_pointer(tbl->mask_array, new); return 0; } static int tbl_mask_array_add_mask(struct flow_table *tbl, struct sw_flow_mask *new) { struct mask_array *ma = ovsl_dereference(tbl->mask_array); int err, ma_count = READ_ONCE(ma->count); if (ma_count >= ma->max) { err = tbl_mask_array_realloc(tbl, ma->max + MASK_ARRAY_SIZE_MIN); if (err) return err; ma = ovsl_dereference(tbl->mask_array); } else { /* On every add or delete we need to reset the counters so * every new mask gets a fair chance of being prioritized. */ tbl_mask_array_reset_counters(ma); } BUG_ON(ovsl_dereference(ma->masks[ma_count])); rcu_assign_pointer(ma->masks[ma_count], new); WRITE_ONCE(ma->count, ma_count + 1); return 0; } static void tbl_mask_array_del_mask(struct flow_table *tbl, struct sw_flow_mask *mask) { struct mask_array *ma = ovsl_dereference(tbl->mask_array); int i, ma_count = READ_ONCE(ma->count); /* Remove the deleted mask pointers from the array */ for (i = 0; i < ma_count; i++) { if (mask == ovsl_dereference(ma->masks[i])) goto found; } BUG(); return; found: WRITE_ONCE(ma->count, ma_count - 1); rcu_assign_pointer(ma->masks[i], ma->masks[ma_count - 1]); RCU_INIT_POINTER(ma->masks[ma_count - 1], NULL); kfree_rcu(mask, rcu); /* Shrink the mask array if necessary. */ if (ma->max >= (MASK_ARRAY_SIZE_MIN * 2) && ma_count <= (ma->max / 3)) tbl_mask_array_realloc(tbl, ma->max / 2); else tbl_mask_array_reset_counters(ma); } /* Remove 'mask' from the mask list, if it is not needed any more. */ static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask) { if (mask) { /* ovs-lock is required to protect mask-refcount and * mask list. */ ASSERT_OVSL(); BUG_ON(!mask->ref_count); mask->ref_count--; if (!mask->ref_count) tbl_mask_array_del_mask(tbl, mask); } } static void __mask_cache_destroy(struct mask_cache *mc) { free_percpu(mc->mask_cache); kfree(mc); } static void mask_cache_rcu_cb(struct rcu_head *rcu) { struct mask_cache *mc = container_of(rcu, struct mask_cache, rcu); __mask_cache_destroy(mc); } static struct mask_cache *tbl_mask_cache_alloc(u32 size) { struct mask_cache_entry __percpu *cache = NULL; struct mask_cache *new; /* Only allow size to be 0, or a power of 2, and does not exceed * percpu allocation size. */ if ((!is_power_of_2(size) && size != 0) || (size * sizeof(struct mask_cache_entry)) > PCPU_MIN_UNIT_SIZE) return NULL; new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; new->cache_size = size; if (new->cache_size > 0) { cache = __alloc_percpu(array_size(sizeof(struct mask_cache_entry), new->cache_size), __alignof__(struct mask_cache_entry)); if (!cache) { kfree(new); return NULL; } } new->mask_cache = cache; return new; } int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size) { struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache); struct mask_cache *new; if (size == mc->cache_size) return 0; if ((!is_power_of_2(size) && size != 0) || (size * sizeof(struct mask_cache_entry)) > PCPU_MIN_UNIT_SIZE) return -EINVAL; new = tbl_mask_cache_alloc(size); if (!new) return -ENOMEM; rcu_assign_pointer(table->mask_cache, new); call_rcu(&mc->rcu, mask_cache_rcu_cb); return 0; } int ovs_flow_tbl_init(struct flow_table *table) { struct table_instance *ti, *ufid_ti; struct mask_cache *mc; struct mask_array *ma; mc = tbl_mask_cache_alloc(MC_DEFAULT_HASH_ENTRIES); if (!mc) return -ENOMEM; ma = tbl_mask_array_alloc(MASK_ARRAY_SIZE_MIN); if (!ma) goto free_mask_cache; ti = table_instance_alloc(TBL_MIN_BUCKETS); if (!ti) goto free_mask_array; ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS); if (!ufid_ti) goto free_ti; rcu_assign_pointer(table->ti, ti); rcu_assign_pointer(table->ufid_ti, ufid_ti); rcu_assign_pointer(table->mask_array, ma); rcu_assign_pointer(table->mask_cache, mc); table->last_rehash = jiffies; table->count = 0; table->ufid_count = 0; return 0; free_ti: __table_instance_destroy(ti); free_mask_array: __mask_array_destroy(ma); free_mask_cache: __mask_cache_destroy(mc); return -ENOMEM; } static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) { struct table_instance *ti; ti = container_of(rcu, struct table_instance, rcu); __table_instance_destroy(ti); } static void table_instance_flow_free(struct flow_table *table, struct table_instance *ti, struct table_instance *ufid_ti, struct sw_flow *flow) { hlist_del_rcu(&flow->flow_table.node[ti->node_ver]); table->count--; if (ovs_identifier_is_ufid(&flow->id)) { hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]); table->ufid_count--; } flow_mask_remove(table, flow->mask); } /* Must be called with OVS mutex held. */ void table_instance_flow_flush(struct flow_table *table, struct table_instance *ti, struct table_instance *ufid_ti) { int i; for (i = 0; i < ti->n_buckets; i++) { struct hlist_head *head = &ti->buckets[i]; struct hlist_node *n; struct sw_flow *flow; hlist_for_each_entry_safe(flow, n, head, flow_table.node[ti->node_ver]) { table_instance_flow_free(table, ti, ufid_ti, flow); ovs_flow_free(flow, true); } } if (WARN_ON(table->count != 0 || table->ufid_count != 0)) { table->count = 0; table->ufid_count = 0; } } static void table_instance_destroy(struct table_instance *ti, struct table_instance *ufid_ti) { call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb); } /* No need for locking this function is called from RCU callback or * error path. */ void ovs_flow_tbl_destroy(struct flow_table *table) { struct table_instance *ti = rcu_dereference_raw(table->ti); struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti); struct mask_cache *mc = rcu_dereference_raw(table->mask_cache); struct mask_array *ma = rcu_dereference_raw(table->mask_array); call_rcu(&mc->rcu, mask_cache_rcu_cb); call_rcu(&ma->rcu, mask_array_rcu_cb); table_instance_destroy(ti, ufid_ti); } struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti, u32 *bucket, u32 *last) { struct sw_flow *flow; struct hlist_head *head; int ver; int i; ver = ti->node_ver; while (*bucket < ti->n_buckets) { i = 0; head = &ti->buckets[*bucket]; hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) { if (i < *last) { i++; continue; } *last = i + 1; return flow; } (*bucket)++; *last = 0; } return NULL; } static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash) { hash = jhash_1word(hash, ti->hash_seed); return &ti->buckets[hash & (ti->n_buckets - 1)]; } static void table_instance_insert(struct table_instance *ti, struct sw_flow *flow) { struct hlist_head *head; head = find_bucket(ti, flow->flow_table.hash); hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head); } static void ufid_table_instance_insert(struct table_instance *ti, struct sw_flow *flow) { struct hlist_head *head; head = find_bucket(ti, flow->ufid_table.hash); hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head); } static void flow_table_copy_flows(struct table_instance *old, struct table_instance *new, bool ufid) { int old_ver; int i; old_ver = old->node_ver; new->node_ver = !old_ver; /* Insert in new table. */ for (i = 0; i < old->n_buckets; i++) { struct sw_flow *flow; struct hlist_head *head = &old->buckets[i]; if (ufid) hlist_for_each_entry_rcu(flow, head, ufid_table.node[old_ver], lockdep_ovsl_is_held()) ufid_table_instance_insert(new, flow); else hlist_for_each_entry_rcu(flow, head, flow_table.node[old_ver], lockdep_ovsl_is_held()) table_instance_insert(new, flow); } } static struct table_instance *table_instance_rehash(struct table_instance *ti, int n_buckets, bool ufid) { struct table_instance *new_ti; new_ti = table_instance_alloc(n_buckets); if (!new_ti) return NULL; flow_table_copy_flows(ti, new_ti, ufid); return new_ti; } int ovs_flow_tbl_flush(struct flow_table *flow_table) { struct table_instance *old_ti, *new_ti; struct table_instance *old_ufid_ti, *new_ufid_ti; new_ti = table_instance_alloc(TBL_MIN_BUCKETS); if (!new_ti) return -ENOMEM; new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS); if (!new_ufid_ti) goto err_free_ti; old_ti = ovsl_dereference(flow_table->ti); old_ufid_ti = ovsl_dereference(flow_table->ufid_ti); rcu_assign_pointer(flow_table->ti, new_ti); rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti); flow_table->last_rehash = jiffies; table_instance_flow_flush(flow_table, old_ti, old_ufid_ti); table_instance_destroy(old_ti, old_ufid_ti); return 0; err_free_ti: __table_instance_destroy(new_ti); return -ENOMEM; } static u32 flow_hash(const struct sw_flow_key *key, const struct sw_flow_key_range *range) { const u32 *hash_key = (const u32 *)((const u8 *)key + range->start); /* Make sure number of hash bytes are multiple of u32. */ int hash_u32s = range_n_bytes(range) >> 2; return jhash2(hash_key, hash_u32s, 0); } static int flow_key_start(const struct sw_flow_key *key) { if (key->tun_proto) return 0; else return rounddown(offsetof(struct sw_flow_key, phy), sizeof(long)); } static bool cmp_key(const struct sw_flow_key *key1, const struct sw_flow_key *key2, int key_start, int key_end) { const long *cp1 = (const long *)((const u8 *)key1 + key_start); const long *cp2 = (const long *)((const u8 *)key2 + key_start); int i; for (i = key_start; i < key_end; i += sizeof(long)) if (*cp1++ ^ *cp2++) return false; return true; } static bool flow_cmp_masked_key(const struct sw_flow *flow, const struct sw_flow_key *key, const struct sw_flow_key_range *range) { return cmp_key(&flow->key, key, range->start, range->end); } static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow, const struct sw_flow_match *match) { struct sw_flow_key *key = match->key; int key_start = flow_key_start(key); int key_end = match->range.end; BUG_ON(ovs_identifier_is_ufid(&flow->id)); return cmp_key(flow->id.unmasked_key, key, key_start, key_end); } static struct sw_flow *masked_flow_lookup(struct table_instance *ti, const struct sw_flow_key *unmasked, const struct sw_flow_mask *mask, u32 *n_mask_hit) { struct sw_flow *flow; struct hlist_head *head; u32 hash; struct sw_flow_key masked_key; ovs_flow_mask_key(&masked_key, unmasked, false, mask); hash = flow_hash(&masked_key, &mask->range); head = find_bucket(ti, hash); (*n_mask_hit)++; hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; } return NULL; } /* Flow lookup does full lookup on flow table. It starts with * mask from index passed in *index. * This function MUST be called with BH disabled due to the use * of CPU specific variables. */ static struct sw_flow *flow_lookup(struct flow_table *tbl, struct table_instance *ti, struct mask_array *ma, const struct sw_flow_key *key, u32 *n_mask_hit, u32 *n_cache_hit, u32 *index) { struct mask_array_stats *stats = this_cpu_ptr(ma->masks_usage_stats); struct sw_flow *flow; struct sw_flow_mask *mask; int i; if (likely(*index < ma->max)) { mask = rcu_dereference_ovsl(ma->masks[*index]); if (mask) { flow = masked_flow_lookup(ti, key, mask, n_mask_hit); if (flow) { u64_stats_update_begin(&stats->syncp); stats->usage_cntrs[*index]++; u64_stats_update_end(&stats->syncp); (*n_cache_hit)++; return flow; } } } for (i = 0; i < ma->max; i++) { if (i == *index) continue; mask = rcu_dereference_ovsl(ma->masks[i]); if (unlikely(!mask)) break; flow = masked_flow_lookup(ti, key, mask, n_mask_hit); if (flow) { /* Found */ *index = i; u64_stats_update_begin(&stats->syncp); stats->usage_cntrs[*index]++; u64_stats_update_end(&stats->syncp); return flow; } } return NULL; } /* * mask_cache maps flow to probable mask. This cache is not tightly * coupled cache, It means updates to mask list can result in inconsistent * cache entry in mask cache. * This is per cpu cache and is divided in MC_HASH_SEGS segments. * In case of a hash collision the entry is hashed in next segment. * */ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl, const struct sw_flow_key *key, u32 skb_hash, u32 *n_mask_hit, u32 *n_cache_hit) { struct mask_cache *mc = rcu_dereference(tbl->mask_cache); struct mask_array *ma = rcu_dereference(tbl->mask_array); struct table_instance *ti = rcu_dereference(tbl->ti); struct mask_cache_entry *entries, *ce; struct sw_flow *flow; u32 hash; int seg; *n_mask_hit = 0; *n_cache_hit = 0; if (unlikely(!skb_hash || mc->cache_size == 0)) { u32 mask_index = 0; u32 cache = 0; return flow_lookup(tbl, ti, ma, key, n_mask_hit, &cache, &mask_index); } /* Pre and post recirulation flows usually have the same skb_hash * value. To avoid hash collisions, rehash the 'skb_hash' with * 'recirc_id'. */ if (key->recirc_id) skb_hash = jhash_1word(skb_hash, key->recirc_id); ce = NULL; hash = skb_hash; entries = this_cpu_ptr(mc->mask_cache); /* Find the cache entry 'ce' to operate on. */ for (seg = 0; seg < MC_HASH_SEGS; seg++) { int index = hash & (mc->cache_size - 1); struct mask_cache_entry *e; e = &entries[index]; if (e->skb_hash == skb_hash) { flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, n_cache_hit, &e->mask_index); if (!flow) e->skb_hash = 0; return flow; } if (!ce || e->skb_hash < ce->skb_hash) ce = e; /* A better replacement cache candidate. */ hash >>= MC_HASH_SHIFT; } /* Cache miss, do full lookup. */ flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, n_cache_hit, &ce->mask_index); if (flow) ce->skb_hash = skb_hash; *n_cache_hit = 0; return flow; } struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl, const struct sw_flow_key *key) { struct table_instance *ti = rcu_dereference_ovsl(tbl->ti); struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array); u32 __always_unused n_mask_hit; u32 __always_unused n_cache_hit; struct sw_flow *flow; u32 index = 0; /* This function gets called trough the netlink interface and therefore * is preemptible. However, flow_lookup() function needs to be called * with BH disabled due to CPU specific variables. */ local_bh_disable(); flow = flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index); local_bh_enable(); return flow; } struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl, const struct sw_flow_match *match) { struct mask_array *ma = ovsl_dereference(tbl->mask_array); int i; /* Always called under ovs-mutex. */ for (i = 0; i < ma->max; i++) { struct table_instance *ti = rcu_dereference_ovsl(tbl->ti); u32 __always_unused n_mask_hit; struct sw_flow_mask *mask; struct sw_flow *flow; mask = ovsl_dereference(ma->masks[i]); if (!mask) continue; flow = masked_flow_lookup(ti, match->key, mask, &n_mask_hit); if (flow && ovs_identifier_is_key(&flow->id) && ovs_flow_cmp_unmasked_key(flow, match)) { return flow; } } return NULL; } static u32 ufid_hash(const struct sw_flow_id *sfid) { return jhash(sfid->ufid, sfid->ufid_len, 0); } static bool ovs_flow_cmp_ufid(const struct sw_flow *flow, const struct sw_flow_id *sfid) { if (flow->id.ufid_len != sfid->ufid_len) return false; return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len); } bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match) { if (ovs_identifier_is_ufid(&flow->id)) return flow_cmp_masked_key(flow, match->key, &match->range); return ovs_flow_cmp_unmasked_key(flow, match); } struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, const struct sw_flow_id *ufid) { struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti); struct sw_flow *flow; struct hlist_head *head; u32 hash; hash = ufid_hash(ufid); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; } return NULL; } int ovs_flow_tbl_num_masks(const struct flow_table *table) { struct mask_array *ma = rcu_dereference_ovsl(table->mask_array); return READ_ONCE(ma->count); } u32 ovs_flow_tbl_masks_cache_size(const struct flow_table *table) { struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache); return READ_ONCE(mc->cache_size); } static struct table_instance *table_instance_expand(struct table_instance *ti, bool ufid) { return table_instance_rehash(ti, ti->n_buckets * 2, ufid); } /* Must be called with OVS mutex held. */ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { struct table_instance *ti = ovsl_dereference(table->ti); struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti); BUG_ON(table->count == 0); table_instance_flow_free(table, ti, ufid_ti, flow); } static struct sw_flow_mask *mask_alloc(void) { struct sw_flow_mask *mask; mask = kmalloc(sizeof(*mask), GFP_KERNEL); if (mask) mask->ref_count = 1; return mask; } static bool mask_equal(const struct sw_flow_mask *a, const struct sw_flow_mask *b) { const u8 *a_ = (const u8 *)&a->key + a->range.start; const u8 *b_ = (const u8 *)&b->key + b->range.start; return (a->range.end == b->range.end) && (a->range.start == b->range.start) && (memcmp(a_, b_, range_n_bytes(&a->range)) == 0); } static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl, const struct sw_flow_mask *mask) { struct mask_array *ma; int i; ma = ovsl_dereference(tbl->mask_array); for (i = 0; i < ma->max; i++) { struct sw_flow_mask *t; t = ovsl_dereference(ma->masks[i]); if (t && mask_equal(mask, t)) return t; } return NULL; } /* Add 'mask' into the mask list, if it is not already there. */ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow, const struct sw_flow_mask *new) { struct sw_flow_mask *mask; mask = flow_mask_find(tbl, new); if (!mask) { /* Allocate a new mask if none exists. */ mask = mask_alloc(); if (!mask) return -ENOMEM; mask->key = new->key; mask->range = new->range; /* Add mask to mask-list. */ if (tbl_mask_array_add_mask(tbl, mask)) { kfree(mask); return -ENOMEM; } } else { BUG_ON(!mask->ref_count); mask->ref_count++; } flow->mask = mask; return 0; } /* Must be called with OVS mutex held. */ static void flow_key_insert(struct flow_table *table, struct sw_flow *flow) { struct table_instance *new_ti = NULL; struct table_instance *ti; flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range); ti = ovsl_dereference(table->ti); table_instance_insert(ti, flow); table->count++; /* Expand table, if necessary, to make room. */ if (table->count > ti->n_buckets) new_ti = table_instance_expand(ti, false); else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL)) new_ti = table_instance_rehash(ti, ti->n_buckets, false); if (new_ti) { rcu_assign_pointer(table->ti, new_ti); call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); table->last_rehash = jiffies; } } /* Must be called with OVS mutex held. */ static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow) { struct table_instance *ti; flow->ufid_table.hash = ufid_hash(&flow->id); ti = ovsl_dereference(table->ufid_ti); ufid_table_instance_insert(ti, flow); table->ufid_count++; /* Expand table, if necessary, to make room. */ if (table->ufid_count > ti->n_buckets) { struct table_instance *new_ti; new_ti = table_instance_expand(ti, true); if (new_ti) { rcu_assign_pointer(table->ufid_ti, new_ti); call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); } } } /* Must be called with OVS mutex held. */ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, const struct sw_flow_mask *mask) { int err; err = flow_mask_insert(table, flow, mask); if (err) return err; flow_key_insert(table, flow); if (ovs_identifier_is_ufid(&flow->id)) flow_ufid_insert(table, flow); return 0; } static int compare_mask_and_count(const void *a, const void *b) { const struct mask_count *mc_a = a; const struct mask_count *mc_b = b; return (s64)mc_b->counter - (s64)mc_a->counter; } /* Must be called with OVS mutex held. */ void ovs_flow_masks_rebalance(struct flow_table *table) { struct mask_array *ma = rcu_dereference_ovsl(table->mask_array); struct mask_count *masks_and_count; struct mask_array *new; int masks_entries = 0; int i; /* Build array of all current entries with use counters. */ masks_and_count = kmalloc_array(ma->max, sizeof(*masks_and_count), GFP_KERNEL); if (!masks_and_count) return; for (i = 0; i < ma->max; i++) { struct sw_flow_mask *mask; int cpu; mask = rcu_dereference_ovsl(ma->masks[i]); if (unlikely(!mask)) break; masks_and_count[i].index = i; masks_and_count[i].counter = 0; for_each_possible_cpu(cpu) { struct mask_array_stats *stats; unsigned int start; u64 counter; stats = per_cpu_ptr(ma->masks_usage_stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); counter = stats->usage_cntrs[i]; } while (u64_stats_fetch_retry(&stats->syncp, start)); masks_and_count[i].counter += counter; } /* Subtract the zero count value. */ masks_and_count[i].counter -= ma->masks_usage_zero_cntr[i]; /* Rather than calling tbl_mask_array_reset_counters() * below when no change is needed, do it inline here. */ ma->masks_usage_zero_cntr[i] += masks_and_count[i].counter; } if (i == 0) goto free_mask_entries; /* Sort the entries */ masks_entries = i; sort(masks_and_count, masks_entries, sizeof(*masks_and_count), compare_mask_and_count, NULL); /* If the order is the same, nothing to do... */ for (i = 0; i < masks_entries; i++) { if (i != masks_and_count[i].index) break; } if (i == masks_entries) goto free_mask_entries; /* Rebuilt the new list in order of usage. */ new = tbl_mask_array_alloc(ma->max); if (!new) goto free_mask_entries; for (i = 0; i < masks_entries; i++) { int index = masks_and_count[i].index; if (ovsl_dereference(ma->masks[index])) new->masks[new->count++] = ma->masks[index]; } rcu_assign_pointer(table->mask_array, new); call_rcu(&ma->rcu, mask_array_rcu_cb); free_mask_entries: kfree(masks_and_count); } /* Initializes the flow module. * Returns zero if successful or a negative error code. */ int ovs_flow_init(void) { BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long)); BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long)); flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids * sizeof(struct sw_flow_stats *)) + cpumask_size(), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; flow_stats_cache = kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats), 0, SLAB_HWCACHE_ALIGN, NULL); if (flow_stats_cache == NULL) { kmem_cache_destroy(flow_cache); flow_cache = NULL; return -ENOMEM; } return 0; } /* Uninitializes the flow module. */ void ovs_flow_exit(void) { kmem_cache_destroy(flow_stats_cache); kmem_cache_destroy(flow_cache); } |
| 390 390 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem. * * Changes: * YOSHIFUJI Hideaki @USAGI: added icmp sysctl table. */ #include <linux/mm.h> #include <linux/sysctl.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ndisc.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> #include <net/netevent.h> #include <net/ip_fib.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif #include <linux/ioam6.h> static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static u32 rt6_multipath_hash_fields_all_mask = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static u32 ioam6_id_max = IOAM6_DEFAULT_ID; static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; static int proc_rt6_multipath_hash_policy(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_policy); ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static int proc_rt6_multipath_hash_fields(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_fields); ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "anycast_src_echo_reply", .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_consistency", .data = &init_net.ipv6.sysctl.flowlabel_consistency, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "auto_flowlabels", .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "idgen_retries", .data = &init_net.ipv6.sysctl.idgen_retries, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "idgen_delay", .data = &init_net.ipv6.sysctl.idgen_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "flowlabel_state_ranges", .data = &init_net.ipv6.sysctl.flowlabel_state_ranges, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_reflect", .data = &init_net.ipv6.sysctl.flowlabel_reflect, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &flowlabel_reflect_max, }, { .procname = "max_dst_opts_number", .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_opts_number", .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_dst_opts_length", .data = &init_net.ipv6.sysctl.max_dst_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_length", .data = &init_net.ipv6.sysctl.max_hbh_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv6.sysctl.multipath_hash_policy, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "fib_multipath_hash_fields", .data = &init_net.ipv6.sysctl.multipath_hash_fields, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_fields, .extra1 = SYSCTL_ONE, .extra2 = &rt6_multipath_hash_fields_all_mask, }, { .procname = "seg6_flowlabel", .data = &init_net.ipv6.sysctl.seg6_flowlabel, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_notify_on_flag_change", .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "ioam6_id", .data = &init_net.ipv6.sysctl.ioam6_id, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra2 = &ioam6_id_max, }, { .procname = "ioam6_id_wide", .data = &init_net.ipv6.sysctl.ioam6_id_wide, .maxlen = sizeof(u64), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra2 = &ioam6_id_wide_max, }, }; static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "mld_qrv", .data = &sysctl_mld_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #ifdef CONFIG_NETLABEL { .procname = "calipso_cache_enable", .data = &calipso_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "calipso_cache_bucket_size", .data = &calipso_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ }; static int __net_init ipv6_sysctl_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(ipv6_table_template); struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; int err, i; err = -ENOMEM; ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), GFP_KERNEL); if (!ipv6_table) goto out; /* Update the variables to point into the current struct net */ for (i = 0; i < table_size; i++) ipv6_table[i].data += (void *)net - (void *)&init_net; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) goto out_ipv6_table; ipv6_icmp_table = ipv6_icmp_sysctl_init(net); if (!ipv6_icmp_table) goto out_ipv6_route_table; net->ipv6.sysctl.hdr = register_net_sysctl_sz(net, "net/ipv6", ipv6_table, table_size); if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; net->ipv6.sysctl.route_hdr = register_net_sysctl_sz(net, "net/ipv6/route", ipv6_route_table, ipv6_route_sysctl_table_size(net)); if (!net->ipv6.sysctl.route_hdr) goto out_unregister_ipv6_table; net->ipv6.sysctl.icmp_hdr = register_net_sysctl_sz(net, "net/ipv6/icmp", ipv6_icmp_table, ipv6_icmp_sysctl_table_size()); if (!net->ipv6.sysctl.icmp_hdr) goto out_unregister_route_table; err = 0; out: return err; out_unregister_route_table: unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); out_unregister_ipv6_table: unregister_net_sysctl_table(net->ipv6.sysctl.hdr); out_ipv6_icmp_table: kfree(ipv6_icmp_table); out_ipv6_route_table: kfree(ipv6_route_table); out_ipv6_table: kfree(ipv6_table); goto out; } static void __net_exit ipv6_sysctl_net_exit(struct net *net) { const struct ctl_table *ipv6_table; const struct ctl_table *ipv6_route_table; const struct ctl_table *ipv6_icmp_table; ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.hdr); kfree(ipv6_table); kfree(ipv6_route_table); kfree(ipv6_icmp_table); } static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, }; static struct ctl_table_header *ip6_header; int ipv6_sysctl_register(void) { int err = -ENOMEM; ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); if (!ip6_header) goto out; err = register_pernet_subsys(&ipv6_sysctl_net_ops); if (err) goto err_pernet; out: return err; err_pernet: unregister_net_sysctl_table(ip6_header); goto out; } void ipv6_sysctl_unregister(void) { unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); } |
| 1301 2163 1301 2157 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 packet mangling table, a port of the IPv4 mangle table to IPv6 * * Copyright (C) 2000-2001 by Harald Welte <laforge@gnumonks.org> * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/slab.h> #include <net/ipv6.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("ip6tables mangle table"); #define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ (1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_MANGLE, }; static unsigned int ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct in6_addr saddr, daddr; unsigned int ret, verdict; u32 flowlabel, mark; u8 hop_limit; int err; /* save source/dest address, mark, hoplimit, flowlabel, priority, */ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); mark = skb->mark; hop_limit = ipv6_hdr(skb)->hop_limit; /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); ret = ip6t_do_table(priv, skb, state); verdict = ret & NF_VERDICT_MASK; if (verdict != NF_DROP && verdict != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } return ret; } /* The work comes in here from netfilter.c. */ static unsigned int ip6table_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) return ip6t_mangle_out(priv, skb, state); return ip6t_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; static int ip6table_mangle_table_init(struct net *net) { struct ip6t_replace *repl; int ret; repl = ip6t_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops); kfree(repl); return ret; } static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) { ip6t_unregister_table_pre_exit(net, "mangle"); } static void __net_exit ip6table_mangle_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "mangle"); } static struct pernet_operations ip6table_mangle_net_ops = { .pre_exit = ip6table_mangle_net_pre_exit, .exit = ip6table_mangle_net_exit, }; static int __init ip6table_mangle_init(void) { int ret = xt_register_template(&packet_mangler, ip6table_mangle_table_init); if (ret < 0) return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); if (IS_ERR(mangle_ops)) { xt_unregister_template(&packet_mangler); return PTR_ERR(mangle_ops); } ret = register_pernet_subsys(&ip6table_mangle_net_ops); if (ret < 0) { xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } return ret; } static void __exit ip6table_mangle_fini(void) { unregister_pernet_subsys(&ip6table_mangle_net_ops); xt_unregister_template(&packet_mangler); kfree(mangle_ops); } module_init(ip6table_mangle_init); module_exit(ip6table_mangle_fini); |
| 5 5 1 6 6 1 1 2 3 3 3 3 17 10 6 1 1 13 2 2 2 2 5 5 3 2 42 1 40 1 13 13 1 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 2005-2006 Ian Kent <raven@themaw.net> */ #include <linux/seq_file.h> #include <linux/pagemap.h> #include "autofs_i.h" struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi) { struct autofs_info *ino; ino = kzalloc(sizeof(*ino), GFP_KERNEL); if (ino) { INIT_LIST_HEAD(&ino->active); INIT_LIST_HEAD(&ino->expiring); ino->last_used = jiffies; ino->sbi = sbi; ino->exp_timeout = -1; ino->count = 1; } return ino; } void autofs_clean_ino(struct autofs_info *ino) { ino->uid = GLOBAL_ROOT_UID; ino->gid = GLOBAL_ROOT_GID; ino->exp_timeout = -1; ino->last_used = jiffies; } void autofs_free_ino(struct autofs_info *ino) { kfree_rcu(ino, rcu); } void autofs_kill_sb(struct super_block *sb) { struct autofs_sb_info *sbi = autofs_sbi(sb); /* * In the event of a failure in get_sb_nodev the superblock * info is not present so nothing else has been setup, so * just call kill_anon_super when we are called from * deactivate_super. */ if (sbi) { /* Free wait queues, close pipe */ autofs_catatonic_mode(sbi); put_pid(sbi->oz_pgrp); } pr_debug("shutting down\n"); kill_litter_super(sb); if (sbi) kfree_rcu(sbi, rcu); } static int autofs_show_options(struct seq_file *m, struct dentry *root) { struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct inode *root_inode = d_inode(root->d_sb->s_root); if (!sbi) return 0; seq_printf(m, ",fd=%d", sbi->pipefd); if (!uid_eq(root_inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, root_inode->i_uid)); if (!gid_eq(root_inode->i_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, root_inode->i_gid)); seq_printf(m, ",pgrp=%d", pid_vnr(sbi->oz_pgrp)); seq_printf(m, ",timeout=%lu", sbi->exp_timeout/HZ); seq_printf(m, ",minproto=%d", sbi->min_proto); seq_printf(m, ",maxproto=%d", sbi->max_proto); if (autofs_type_offset(sbi->type)) seq_puts(m, ",offset"); else if (autofs_type_direct(sbi->type)) seq_puts(m, ",direct"); else seq_puts(m, ",indirect"); if (sbi->flags & AUTOFS_SBI_STRICTEXPIRE) seq_puts(m, ",strictexpire"); if (sbi->flags & AUTOFS_SBI_IGNORE) seq_puts(m, ",ignore"); #ifdef CONFIG_CHECKPOINT_RESTORE if (sbi->pipe) seq_printf(m, ",pipe_ino=%ld", file_inode(sbi->pipe)->i_ino); else seq_puts(m, ",pipe_ino=-1"); #endif return 0; } static void autofs_evict_inode(struct inode *inode) { clear_inode(inode); kfree(inode->i_private); } static const struct super_operations autofs_sops = { .statfs = simple_statfs, .show_options = autofs_show_options, .evict_inode = autofs_evict_inode, }; enum { Opt_direct, Opt_fd, Opt_gid, Opt_ignore, Opt_indirect, Opt_maxproto, Opt_minproto, Opt_offset, Opt_pgrp, Opt_strictexpire, Opt_uid, }; const struct fs_parameter_spec autofs_param_specs[] = { fsparam_flag ("direct", Opt_direct), fsparam_fd ("fd", Opt_fd), fsparam_gid ("gid", Opt_gid), fsparam_flag ("ignore", Opt_ignore), fsparam_flag ("indirect", Opt_indirect), fsparam_u32 ("maxproto", Opt_maxproto), fsparam_u32 ("minproto", Opt_minproto), fsparam_flag ("offset", Opt_offset), fsparam_u32 ("pgrp", Opt_pgrp), fsparam_flag ("strictexpire", Opt_strictexpire), fsparam_uid ("uid", Opt_uid), {} }; struct autofs_fs_context { kuid_t uid; kgid_t gid; int pgrp; bool pgrp_set; }; /* * Open the fd. We do it here rather than in get_tree so that it's done in the * context of the system call that passed the data and not the one that * triggered the superblock creation, lest the fd gets reassigned. */ static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi, struct fs_parameter *param, struct fs_parse_result *result) { struct file *pipe; int ret; if (param->type == fs_value_is_file) { /* came through the new api */ pipe = param->file; param->file = NULL; } else { pipe = fget(result->uint_32); } if (!pipe) { errorf(fc, "could not open pipe file descriptor"); return -EBADF; } ret = autofs_check_pipe(pipe); if (ret < 0) { errorf(fc, "Invalid/unusable pipe"); fput(pipe); return -EBADF; } autofs_set_packet_pipe_flags(pipe); if (sbi->pipe) fput(sbi->pipe); sbi->pipefd = result->uint_32; sbi->pipe = pipe; return 0; } static int autofs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct autofs_fs_context *ctx = fc->fs_private; struct autofs_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, autofs_param_specs, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_fd: return autofs_parse_fd(fc, sbi, param, &result); case Opt_uid: ctx->uid = result.uid; break; case Opt_gid: ctx->gid = result.gid; break; case Opt_pgrp: ctx->pgrp = result.uint_32; ctx->pgrp_set = true; break; case Opt_minproto: sbi->min_proto = result.uint_32; break; case Opt_maxproto: sbi->max_proto = result.uint_32; break; case Opt_indirect: set_autofs_type_indirect(&sbi->type); break; case Opt_direct: set_autofs_type_direct(&sbi->type); break; case Opt_offset: set_autofs_type_offset(&sbi->type); break; case Opt_strictexpire: sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; break; case Opt_ignore: sbi->flags |= AUTOFS_SBI_IGNORE; } return 0; } static struct autofs_sb_info *autofs_alloc_sbi(void) { struct autofs_sb_info *sbi; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return NULL; sbi->magic = AUTOFS_SBI_MAGIC; sbi->flags = AUTOFS_SBI_CATATONIC; sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; sbi->pipefd = -1; set_autofs_type_indirect(&sbi->type); mutex_init(&sbi->wq_mutex); mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); spin_lock_init(&sbi->lookup_lock); INIT_LIST_HEAD(&sbi->active_list); INIT_LIST_HEAD(&sbi->expiring_list); return sbi; } static int autofs_validate_protocol(struct fs_context *fc) { struct autofs_sb_info *sbi = fc->s_fs_info; /* Test versions first */ if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) { errorf(fc, "kernel does not match daemon version " "daemon (%d, %d) kernel (%d, %d)\n", sbi->min_proto, sbi->max_proto, AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION); return -EINVAL; } /* Establish highest kernel protocol version */ if (sbi->max_proto > AUTOFS_MAX_PROTO_VERSION) sbi->version = AUTOFS_MAX_PROTO_VERSION; else sbi->version = sbi->max_proto; switch (sbi->version) { case 4: sbi->sub_version = 7; break; case 5: sbi->sub_version = AUTOFS_PROTO_SUBVERSION; break; default: sbi->sub_version = 0; } return 0; } static int autofs_fill_super(struct super_block *s, struct fs_context *fc) { struct autofs_fs_context *ctx = fc->fs_private; struct autofs_sb_info *sbi = s->s_fs_info; struct inode *root_inode; struct autofs_info *ino; pr_debug("starting up, sbi = %p\n", sbi); sbi->sb = s; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = AUTOFS_SUPER_MAGIC; s->s_op = &autofs_sops; s->s_d_op = &autofs_dentry_operations; s->s_time_gran = 1; /* * Get the root inode and dentry, but defer checking for errors. */ ino = autofs_new_ino(sbi); if (!ino) return -ENOMEM; root_inode = autofs_get_inode(s, S_IFDIR | 0755); if (!root_inode) return -ENOMEM; root_inode->i_uid = ctx->uid; root_inode->i_gid = ctx->gid; root_inode->i_fop = &autofs_root_operations; root_inode->i_op = &autofs_dir_inode_operations; s->s_root = d_make_root(root_inode); if (unlikely(!s->s_root)) { autofs_free_ino(ino); return -ENOMEM; } s->s_root->d_fsdata = ino; if (ctx->pgrp_set) { sbi->oz_pgrp = find_get_pid(ctx->pgrp); if (!sbi->oz_pgrp) return invalf(fc, "Could not find process group %d", ctx->pgrp); } else sbi->oz_pgrp = get_task_pid(current, PIDTYPE_PGID); if (autofs_type_trigger(sbi->type)) /* s->s_root won't be contended so there's little to * be gained by not taking the d_lock when setting * d_flags, even when a lot mounts are being done. */ managed_dentry_set_managed(s->s_root); pr_debug("pipe fd = %d, pgrp = %u\n", sbi->pipefd, pid_nr(sbi->oz_pgrp)); sbi->flags &= ~AUTOFS_SBI_CATATONIC; return 0; } /* * Validate the parameters and then request a superblock. */ static int autofs_get_tree(struct fs_context *fc) { struct autofs_sb_info *sbi = fc->s_fs_info; int ret; ret = autofs_validate_protocol(fc); if (ret) return ret; if (sbi->pipefd < 0) return invalf(fc, "No control pipe specified"); return get_tree_nodev(fc, autofs_fill_super); } static void autofs_free_fc(struct fs_context *fc) { struct autofs_fs_context *ctx = fc->fs_private; struct autofs_sb_info *sbi = fc->s_fs_info; if (sbi) { if (sbi->pipe) fput(sbi->pipe); kfree(sbi); } kfree(ctx); } static const struct fs_context_operations autofs_context_ops = { .free = autofs_free_fc, .parse_param = autofs_parse_param, .get_tree = autofs_get_tree, }; /* * Set up the filesystem mount context. */ int autofs_init_fs_context(struct fs_context *fc) { struct autofs_fs_context *ctx; struct autofs_sb_info *sbi; ctx = kzalloc(sizeof(struct autofs_fs_context), GFP_KERNEL); if (!ctx) goto nomem; ctx->uid = current_uid(); ctx->gid = current_gid(); sbi = autofs_alloc_sbi(); if (!sbi) goto nomem_ctx; fc->fs_private = ctx; fc->s_fs_info = sbi; fc->ops = &autofs_context_ops; return 0; nomem_ctx: kfree(ctx); nomem: return -ENOMEM; } struct inode *autofs_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (inode == NULL) return NULL; inode->i_mode = mode; if (sb->s_root) { inode->i_uid = d_inode(sb->s_root)->i_uid; inode->i_gid = d_inode(sb->s_root)->i_gid; } simple_inode_init_ts(inode); inode->i_ino = get_next_ino(); if (S_ISDIR(mode)) { set_nlink(inode, 2); inode->i_op = &autofs_dir_inode_operations; inode->i_fop = &autofs_dir_operations; } else if (S_ISLNK(mode)) { inode->i_op = &autofs_symlink_inode_operations; } else WARN_ON(1); return inode; } |
| 22 79 78 79 79 79 17 9 8 78 79 8 8 1 8 5 3 4 7 8 105 105 105 95 95 93 91 25 15 12 8 4 7 8 7 2 57 54 8 54 54 23 23 1 23 15 8 13 57 55 1 14 2 14 1 2 16 14 13 13 7 7 8 8 8 8 8 8 8 65 64 65 30 30 30 2 69 68 68 67 8 68 9 9 9 9 8 8 3 3 3 35 28 7 35 35 8 36 36 24 35 13 13 5 13 13 2 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #include <linux/skmsg.h> #include <linux/skbuff.h> #include <linux/scatterlist.h> #include <net/sock.h> #include <net/tcp.h> #include <net/tls.h> #include <trace/events/sock.h> static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce) { if (msg->sg.end > msg->sg.start && elem_first_coalesce < msg->sg.end) return true; if (msg->sg.end < msg->sg.start && (elem_first_coalesce > msg->sg.start || elem_first_coalesce < msg->sg.end)) return true; return false; } int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce) { struct page_frag *pfrag = sk_page_frag(sk); u32 osize = msg->sg.size; int ret = 0; len -= msg->sg.size; while (len > 0) { struct scatterlist *sge; u32 orig_offset; int use, i; if (!sk_page_frag_refill(sk, pfrag)) { ret = -ENOMEM; goto msg_trim; } orig_offset = pfrag->offset; use = min_t(int, len, pfrag->size - orig_offset); if (!sk_wmem_schedule(sk, use)) { ret = -ENOMEM; goto msg_trim; } i = msg->sg.end; sk_msg_iter_var_prev(i); sge = &msg->sg.data[i]; if (sk_msg_try_coalesce_ok(msg, elem_first_coalesce) && sg_page(sge) == pfrag->page && sge->offset + sge->length == orig_offset) { sge->length += use; } else { if (sk_msg_full(msg)) { ret = -ENOSPC; break; } sge = &msg->sg.data[msg->sg.end]; sg_unmark_end(sge); sg_set_page(sge, pfrag->page, use, orig_offset); get_page(pfrag->page); sk_msg_iter_next(msg, end); } sk_mem_charge(sk, use); msg->sg.size += use; pfrag->offset += use; len -= use; } return ret; msg_trim: sk_msg_trim(sk, msg, osize); return ret; } EXPORT_SYMBOL_GPL(sk_msg_alloc); int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, u32 off, u32 len) { int i = src->sg.start; struct scatterlist *sge = sk_msg_elem(src, i); struct scatterlist *sgd = NULL; u32 sge_len, sge_off; while (off) { if (sge->length > off) break; off -= sge->length; sk_msg_iter_var_next(i); if (i == src->sg.end && off) return -ENOSPC; sge = sk_msg_elem(src, i); } while (len) { sge_len = sge->length - off; if (sge_len > len) sge_len = len; if (dst->sg.end) sgd = sk_msg_elem(dst, dst->sg.end - 1); if (sgd && (sg_page(sge) == sg_page(sgd)) && (sg_virt(sge) + off == sg_virt(sgd) + sgd->length)) { sgd->length += sge_len; dst->sg.size += sge_len; } else if (!sk_msg_full(dst)) { sge_off = sge->offset + off; sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off); } else { return -ENOSPC; } off = 0; len -= sge_len; sk_mem_charge(sk, sge_len); sk_msg_iter_var_next(i); if (i == src->sg.end && len) return -ENOSPC; sge = sk_msg_elem(src, i); } return 0; } EXPORT_SYMBOL_GPL(sk_msg_clone); void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes) { int i = msg->sg.start; do { struct scatterlist *sge = sk_msg_elem(msg, i); if (bytes < sge->length) { sge->length -= bytes; sge->offset += bytes; sk_mem_uncharge(sk, bytes); break; } sk_mem_uncharge(sk, sge->length); bytes -= sge->length; sge->length = 0; sge->offset = 0; sk_msg_iter_var_next(i); } while (bytes && i != msg->sg.end); msg->sg.start = i; } EXPORT_SYMBOL_GPL(sk_msg_return_zero); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes) { int i = msg->sg.start; do { struct scatterlist *sge = &msg->sg.data[i]; int uncharge = (bytes < sge->length) ? bytes : sge->length; sk_mem_uncharge(sk, uncharge); bytes -= uncharge; sk_msg_iter_var_next(i); } while (i != msg->sg.end); } EXPORT_SYMBOL_GPL(sk_msg_return); static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, bool charge) { struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length; /* When the skb owns the memory we free it from consume_skb path. */ if (!msg->skb) { if (charge) sk_mem_uncharge(sk, len); put_page(sg_page(sge)); } memset(sge, 0, sizeof(*sge)); return len; } static int __sk_msg_free(struct sock *sk, struct sk_msg *msg, u32 i, bool charge) { struct scatterlist *sge = sk_msg_elem(msg, i); int freed = 0; while (msg->sg.size) { msg->sg.size -= sge->length; freed += sk_msg_free_elem(sk, msg, i, charge); sk_msg_iter_var_next(i); sk_msg_check_to_free(msg, i, msg->sg.size); sge = sk_msg_elem(msg, i); } consume_skb(msg->skb); sk_msg_init(msg); return freed; } int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg) { return __sk_msg_free(sk, msg, msg->sg.start, false); } EXPORT_SYMBOL_GPL(sk_msg_free_nocharge); int sk_msg_free(struct sock *sk, struct sk_msg *msg) { return __sk_msg_free(sk, msg, msg->sg.start, true); } EXPORT_SYMBOL_GPL(sk_msg_free); static void __sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes, bool charge) { struct scatterlist *sge; u32 i = msg->sg.start; while (bytes) { sge = sk_msg_elem(msg, i); if (!sge->length) break; if (bytes < sge->length) { if (charge) sk_mem_uncharge(sk, bytes); sge->length -= bytes; sge->offset += bytes; msg->sg.size -= bytes; break; } msg->sg.size -= sge->length; bytes -= sge->length; sk_msg_free_elem(sk, msg, i, charge); sk_msg_iter_var_next(i); sk_msg_check_to_free(msg, i, bytes); } msg->sg.start = i; } void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes) { __sk_msg_free_partial(sk, msg, bytes, true); } EXPORT_SYMBOL_GPL(sk_msg_free_partial); void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes) { __sk_msg_free_partial(sk, msg, bytes, false); } void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len) { int trim = msg->sg.size - len; u32 i = msg->sg.end; if (trim <= 0) { WARN_ON(trim < 0); return; } sk_msg_iter_var_prev(i); msg->sg.size = len; while (msg->sg.data[i].length && trim >= msg->sg.data[i].length) { trim -= msg->sg.data[i].length; sk_msg_free_elem(sk, msg, i, true); sk_msg_iter_var_prev(i); if (!trim) goto out; } msg->sg.data[i].length -= trim; sk_mem_uncharge(sk, trim); /* Adjust copybreak if it falls into the trimmed part of last buf */ if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length) msg->sg.copybreak = msg->sg.data[i].length; out: sk_msg_iter_var_next(i); msg->sg.end = i; /* If we trim data a full sg elem before curr pointer update * copybreak and current so that any future copy operations * start at new copy location. * However trimmed data that has not yet been used in a copy op * does not require an update. */ if (!msg->sg.size) { msg->sg.curr = msg->sg.start; msg->sg.copybreak = 0; } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >= sk_msg_iter_dist(msg->sg.start, msg->sg.end)) { sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } } EXPORT_SYMBOL_GPL(sk_msg_trim); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes) { int i, maxpages, ret = 0, num_elems = sk_msg_elem_used(msg); const int to_max_pages = MAX_MSG_FRAGS; struct page *pages[MAX_MSG_FRAGS]; ssize_t orig, copied, use, offset; orig = msg->sg.size; while (bytes > 0) { i = 0; maxpages = to_max_pages - num_elems; if (maxpages == 0) { ret = -EFAULT; goto out; } copied = iov_iter_get_pages2(from, pages, bytes, maxpages, &offset); if (copied <= 0) { ret = -EFAULT; goto out; } bytes -= copied; msg->sg.size += copied; while (copied) { use = min_t(int, copied, PAGE_SIZE - offset); sg_set_page(&msg->sg.data[msg->sg.end], pages[i], use, offset); sg_unmark_end(&msg->sg.data[msg->sg.end]); sk_mem_charge(sk, use); offset = 0; copied -= use; sk_msg_iter_next(msg, end); num_elems++; i++; } /* When zerocopy is mixed with sk_msg_*copy* operations we * may have a copybreak set in this case clear and prefer * zerocopy remainder when possible. */ msg->sg.copybreak = 0; msg->sg.curr = msg->sg.end; } out: /* Revert iov_iter updates, msg will need to use 'trim' later if it * also needs to be cleared. */ if (ret) iov_iter_revert(from, msg->sg.size - orig); return ret; } EXPORT_SYMBOL_GPL(sk_msg_zerocopy_from_iter); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes) { int ret = -ENOSPC, i = msg->sg.curr; u32 copy, buf_size, copied = 0; struct scatterlist *sge; void *to; do { sge = sk_msg_elem(msg, i); /* This is possible if a trim operation shrunk the buffer */ if (msg->sg.copybreak >= sge->length) { msg->sg.copybreak = 0; sk_msg_iter_var_next(i); if (i == msg->sg.end) break; sge = sk_msg_elem(msg, i); } buf_size = sge->length - msg->sg.copybreak; copy = (buf_size > bytes) ? bytes : buf_size; to = sg_virt(sge) + msg->sg.copybreak; msg->sg.copybreak += copy; if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) ret = copy_from_iter_nocache(to, copy, from); else ret = copy_from_iter(to, copy, from); if (ret != copy) { ret = -EFAULT; goto out; } bytes -= copy; copied += copy; if (!bytes) break; msg->sg.copybreak = 0; sk_msg_iter_var_next(i); } while (i != msg->sg.end); out: msg->sg.curr = i; return (ret < 0) ? ret : copied; } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); /* Receive sk_msg from psock->ingress_msg to @msg. */ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags) { struct iov_iter *iter = &msg->msg_iter; int peek = flags & MSG_PEEK; struct sk_msg *msg_rx; int i, copied = 0; msg_rx = sk_psock_peek_msg(psock); while (copied != len) { struct scatterlist *sge; if (unlikely(!msg_rx)) break; i = msg_rx->sg.start; do { struct page *page; int copy; sge = sk_msg_elem(msg_rx, i); copy = sge->length; page = sg_page(sge); if (copied + copy > len) copy = len - copied; if (copy) copy = copy_page_to_iter(page, sge->offset, copy, iter); if (!copy) { copied = copied ? copied : -EFAULT; goto out; } copied += copy; if (likely(!peek)) { sge->offset += copy; sge->length -= copy; if (!msg_rx->skb) { sk_mem_uncharge(sk, copy); atomic_sub(copy, &sk->sk_rmem_alloc); } msg_rx->sg.size -= copy; if (!sge->length) { sk_msg_iter_var_next(i); if (!msg_rx->skb) put_page(page); } } else { /* Lets not optimize peek case if copy_page_to_iter * didn't copy the entire length lets just break. */ if (copy != sge->length) goto out; sk_msg_iter_var_next(i); } if (copied == len) break; } while ((i != msg_rx->sg.end) && !sg_is_last(sge)); if (unlikely(peek)) { msg_rx = sk_psock_next_msg(psock, msg_rx); if (!msg_rx) break; continue; } msg_rx->sg.start = i; if (!sge->length && (i == msg_rx->sg.end || sg_is_last(sge))) { msg_rx = sk_psock_dequeue_msg(psock); kfree_sk_msg(msg_rx); } msg_rx = sk_psock_peek_msg(psock); } out: return copied; } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); bool sk_msg_is_readable(struct sock *sk) { struct sk_psock *psock; bool empty = true; rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) empty = list_empty(&psock->ingress_msg); rcu_read_unlock(); return !empty; } EXPORT_SYMBOL_GPL(sk_msg_is_readable); static struct sk_msg *alloc_sk_msg(gfp_t gfp) { struct sk_msg *msg; msg = kzalloc(sizeof(*msg), gfp | __GFP_NOWARN); if (unlikely(!msg)) return NULL; sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); return msg; } static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) return NULL; if (!sk_rmem_schedule(sk, skb, skb->truesize)) return NULL; return alloc_sk_msg(GFP_KERNEL); } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, u32 off, u32 len, struct sk_psock *psock, struct sock *sk, struct sk_msg *msg) { int num_sge, copied; num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (num_sge < 0) { /* skb linearize may fail with ENOMEM, but lets simply try again * later if this happens. Under memory pressure we don't want to * drop the skb. We need to linearize the skb so that the mapping * in skb_to_sgvec can not error. */ if (skb_linearize(skb)) return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (unlikely(num_sge < 0)) return num_sge; } #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) psock->ingress_bytes += len; #endif copied = len; msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; msg->skb = skb; sk_psock_queue_msg(psock, msg); sk_psock_data_ready(sk, psock); return copied; } static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len); static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) { struct sock *sk = psock->sk; struct sk_msg *msg; int err; /* If we are receiving on the same sock skb->sk is already assigned, * skip memory accounting and owner transition seeing it already set * correctly. */ if (unlikely(skb->sk == sk)) return sk_psock_skb_ingress_self(psock, skb, off, len); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; /* This will transition ownership of the data from the socket where * the BPF program was run initiating the redirect to the socket * we will eventually receive this data on. The data will be released * from skb_consume found in __tcp_bpf_recvmsg() after its been copied * into user buffers. */ skb_set_owner_r(skb, sk); err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; } /* Puts an skb on the ingress queue of the socket already assigned to the * skb. In this case we do not need to check memory limits or skb_set_owner_r * because the skb is already accounted for here. */ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) { struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; int err; if (unlikely(!msg)) return -EAGAIN; skb_set_owner_r(skb, sk); err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; } static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { int err = 0; if (!ingress) { if (!sock_writeable(psock->sk)) return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } skb_get(skb); err = sk_psock_skb_ingress(psock, skb, off, len); if (err < 0) kfree_skb(skb); return err; } static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, int len, int off) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { state->len = len; state->off = off; } spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; u32 len = 0, off = 0; bool ingress; int ret; mutex_lock(&psock->work_mutex); if (unlikely(state->len)) { len = state->len; off = state->off; } while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { struct strp_msg *stm = strp_msg(skb); off = stm->offset; len = stm->full_len; } ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { ret = -EIO; if (!sock_flag(psock->sk, SOCK_DEAD)) ret = sk_psock_handle_skb(psock, skb, off, len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { sk_psock_skb_state(psock, state, len, off); /* Delay slightly to prioritize any * other work that might be here. */ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) schedule_delayed_work(&psock->work, 1); goto end; } /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); goto end; } off += ret; len -= ret; } while (len); skb = skb_dequeue(&psock->ingress_skb); kfree_skb(skb); } end: mutex_unlock(&psock->work_mutex); } struct sk_psock *sk_psock_init(struct sock *sk, int node) { struct sk_psock *psock; struct proto *prot; write_lock_bh(&sk->sk_callback_lock); if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) { psock = ERR_PTR(-EINVAL); goto out; } if (sk->sk_user_data) { psock = ERR_PTR(-EBUSY); goto out; } psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node); if (!psock) { psock = ERR_PTR(-ENOMEM); goto out; } prot = READ_ONCE(sk->sk_prot); psock->sk = sk; psock->eval = __SK_NONE; psock->sk_proto = prot; psock->saved_unhash = prot->unhash; psock->saved_destroy = prot->destroy; psock->saved_close = prot->close; psock->saved_write_space = sk->sk_write_space; INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); INIT_DELAYED_WORK(&psock->work, sk_psock_backlog); mutex_init(&psock->work_mutex); INIT_LIST_HEAD(&psock->ingress_msg); spin_lock_init(&psock->ingress_lock); skb_queue_head_init(&psock->ingress_skb); sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED); refcount_set(&psock->refcnt, 1); __rcu_assign_sk_user_data_with_flags(sk, psock, SK_USER_DATA_NOCOPY | SK_USER_DATA_PSOCK); sock_hold(sk); out: write_unlock_bh(&sk->sk_callback_lock); return psock; } EXPORT_SYMBOL_GPL(sk_psock_init); struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock) { struct sk_psock_link *link; spin_lock_bh(&psock->link_lock); link = list_first_entry_or_null(&psock->link, struct sk_psock_link, list); if (link) list_del(&link->list); spin_unlock_bh(&psock->link_lock); return link; } static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) { struct sk_msg *msg, *tmp; list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { list_del(&msg->list); if (!msg->skb) atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); sk_msg_free(psock->sk, msg); kfree(msg); } } static void __sk_psock_zap_ingress(struct sk_psock *psock) { struct sk_buff *skb; while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) { skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } __sk_psock_purge_ingress_msg(psock); } static void sk_psock_link_destroy(struct sk_psock *psock) { struct sk_psock_link *link, *tmp; list_for_each_entry_safe(link, tmp, &psock->link, list) { list_del(&link->list); sk_psock_free_link(link); } } void sk_psock_stop(struct sk_psock *psock) { spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_done_strp(struct sk_psock *psock); static void sk_psock_destroy(struct work_struct *work) { struct sk_psock *psock = container_of(to_rcu_work(work), struct sk_psock, rwork); /* No sk_callback_lock since already detached. */ sk_psock_done_strp(psock); cancel_delayed_work_sync(&psock->work); __sk_psock_zap_ingress(psock); mutex_destroy(&psock->work_mutex); psock_progs_drop(&psock->progs); sk_psock_link_destroy(psock); sk_psock_cork_free(psock); if (psock->sk_redir) sock_put(psock->sk_redir); if (psock->sk_pair) sock_put(psock->sk_pair); sock_put(psock->sk); kfree(psock); } void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); if (psock->progs.stream_parser) sk_psock_stop_strp(sk, psock); else if (psock->progs.stream_verdict || psock->progs.skb_verdict) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); sk_psock_stop(psock); INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); } EXPORT_SYMBOL_GPL(sk_psock_drop); static int sk_psock_map_verd(int verdict, bool redir) { switch (verdict) { case SK_PASS: return redir ? __SK_REDIRECT : __SK_PASS; case SK_DROP: default: break; } return __SK_DROP; } int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg) { struct bpf_prog *prog; int ret; rcu_read_lock(); prog = READ_ONCE(psock->progs.msg_parser); if (unlikely(!prog)) { ret = __SK_PASS; goto out; } sk_msg_compute_data_pointers(msg); msg->sk = sk; ret = bpf_prog_run_pin_on_cpu(prog, msg); ret = sk_psock_map_verd(ret, msg->sk_redir); psock->apply_bytes = msg->apply_bytes; if (ret == __SK_REDIRECT) { if (psock->sk_redir) { sock_put(psock->sk_redir); psock->sk_redir = NULL; } if (!msg->sk_redir) { ret = __SK_DROP; goto out; } psock->redir_ingress = sk_msg_to_ingress(msg); psock->sk_redir = msg->sk_redir; sock_hold(psock->sk_redir); } out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; sk_other = skb_bpf_redirect_fetch(skb); /* This error is a buggy BPF program, it returned a redirect * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } psock_other = sk_psock(sk_other); /* This error indicates the socket is being torn down or had another * error that caused the pipe to break. We can't send a packet on * a socket that is in this state so we drop the skb. */ if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) { skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } spin_lock_bh(&psock_other->ingress_lock); if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { spin_unlock_bh(&psock_other->ingress_lock); skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } skb_queue_tail(&psock_other->ingress_skb, skb); schedule_delayed_work(&psock_other->work, 0); spin_unlock_bh(&psock_other->ingress_lock); return 0; } static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sk_psock *from, int verdict) { switch (verdict) { case __SK_REDIRECT: sk_psock_skb_redirect(from, skb); break; case __SK_PASS: case __SK_DROP: default: break; } } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog; int ret = __SK_PASS; rcu_read_lock(); prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { skb->sk = psock->sk; skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } sk_psock_tls_verdict_apply(skb, psock, ret); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, int verdict) { struct sock *sk_other; int err = 0; u32 len, off; switch (verdict) { case __SK_PASS: err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) goto out_free; skb_bpf_set_ingress(skb); /* If the queue is empty then we can submit directly * into the msg queue. If its not empty we have to * queue work otherwise we may get OOO data. Otherwise, * if sk_psock_skb_ingress errors will be handled by * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { struct strp_msg *stm = strp_msg(skb); off = stm->offset; len = stm->full_len; } err = sk_psock_skb_ingress_self(psock, skb, off, len); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); schedule_delayed_work(&psock->work, 0); err = 0; } spin_unlock_bh(&psock->ingress_lock); if (err < 0) goto out_free; } break; case __SK_REDIRECT: tcp_eat_skb(psock->sk, skb); err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: skb_bpf_redirect_clear(skb); tcp_eat_skb(psock->sk, skb); sock_drop(psock->sk, skb); } return err; } static void sk_psock_write_space(struct sock *sk) { struct sk_psock *psock; void (*write_space)(struct sock *sk) = NULL; rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) { if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) schedule_delayed_work(&psock->work, 0); write_space = psock->saved_write_space; } rcu_read_unlock(); if (write_space) write_space(sk); } #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; struct sock *sk; rcu_read_lock(); sk = strp->sk; psock = sk_psock(sk); if (unlikely(!psock)) { sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { skb->sk = sk; skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } sk_psock_verdict_apply(psock, skb, ret); out: rcu_read_unlock(); } static int sk_psock_strp_read_done(struct strparser *strp, int err) { return err; } static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) { struct sk_psock *psock = container_of(strp, struct sk_psock, strp); struct bpf_prog *prog; int ret = skb->len; rcu_read_lock(); prog = READ_ONCE(psock->progs.stream_parser); if (likely(prog)) { skb->sk = psock->sk; ret = bpf_prog_run_pin_on_cpu(prog, skb); skb->sk = NULL; } rcu_read_unlock(); return ret; } /* Called with socket lock held. */ static void sk_psock_strp_data_ready(struct sock *sk) { struct sk_psock *psock; trace_sk_data_ready(sk); rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) { if (tls_sw_has_ctx_rx(sk)) { psock->saved_data_ready(sk); } else { read_lock_bh(&sk->sk_callback_lock); strp_data_ready(&psock->strp); read_unlock_bh(&sk->sk_callback_lock); } } rcu_read_unlock(); } int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { int ret; static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; ret = strp_init(&psock->strp, sk, &cb); if (!ret) sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); if (sk_is_tcp(sk)) { psock->strp.cb.read_sock = tcp_bpf_strp_read_sock; psock->copied_seq = tcp_sk(sk)->copied_seq; } return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { if (psock->saved_data_ready) return; psock->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = sk_psock_strp_data_ready; sk->sk_write_space = sk_psock_write_space; } void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { psock_set_prog(&psock->progs.stream_parser, NULL); if (!psock->saved_data_ready) return; sk->sk_data_ready = psock->saved_data_ready; psock->saved_data_ready = NULL; strp_stop(&psock->strp); } static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else static void sk_psock_done_strp(struct sk_psock *psock) { } #endif /* CONFIG_BPF_STREAM_PARSER */ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) { struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; int len = skb->len; rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; tcp_eat_skb(sk, skb); sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); if (!prog) prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } ret = sk_psock_verdict_apply(psock, skb, ret); if (ret < 0) len = ret; out: rcu_read_unlock(); return len; } static void sk_psock_verdict_data_ready(struct sock *sk) { struct socket *sock = sk->sk_socket; const struct proto_ops *ops; int copied; trace_sk_data_ready(sk); if (unlikely(!sock)) return; ops = READ_ONCE(sock->ops); if (!ops || !ops->read_skb) return; copied = ops->read_skb(sk, sk_psock_verdict_recv); if (copied >= 0) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (psock) sk_psock_data_ready(sk, psock); rcu_read_unlock(); } } void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) { if (psock->saved_data_ready) return; psock->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = sk_psock_verdict_data_ready; sk->sk_write_space = sk_psock_write_space; } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { psock_set_prog(&psock->progs.stream_verdict, NULL); psock_set_prog(&psock->progs.skb_verdict, NULL); if (!psock->saved_data_ready) return; sk->sk_data_ready = psock->saved_data_ready; psock->saved_data_ready = NULL; } |
| 5 5 2205 3 315 2203 2203 2205 10 2205 2205 2203 2201 2205 2208 2205 421 421 391 350 61 400 402 390 4 5 391 136 299 330 371 330 2 9 161 331 212 206 2 1 1 4 5 9 475 470 474 440 474 4 412 202 202 172 124 179 504 1 495 484 2 474 474 6 17 43 422 225 401 333 332 1 5 4 4 1 5 1 1 1 1 1 93 3 18 72 3 504 1 1 1 402 93 1 1 1 1 1 514 2 509 4 20 1 8 6 5 2 1 5 5 2 3 3 390 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (C) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cache.h> #include <linux/capability.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <net/ip.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv4 packet filter"); void *ipt_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ipt, IPT); } EXPORT_SYMBOL_GPL(ipt_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip_packet_match(const struct iphdr *ip, const char *indev, const char *outdev, const struct ipt_ip *ipinfo, int isfrag) { unsigned long ret; if (NF_INVF(ipinfo, IPT_INV_SRCIP, (ip->saddr & ipinfo->smsk.s_addr) != ipinfo->src.s_addr) || NF_INVF(ipinfo, IPT_INV_DSTIP, (ip->daddr & ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr)) return false; ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask); if (NF_INVF(ipinfo, IPT_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask); if (NF_INVF(ipinfo, IPT_INV_VIA_OUT, ret != 0)) return false; /* Check specific protocol */ if (ipinfo->proto && NF_INVF(ipinfo, IPT_INV_PROTO, ip->protocol != ipinfo->proto)) return false; /* If we have a fragment rule but the packet is not a fragment * then we return zero */ if (NF_INVF(ipinfo, IPT_INV_FRAG, (ipinfo->flags & IPT_F_FRAG) && !isfrag)) return false; return true; } static bool ip_checkentry(const struct ipt_ip *ip) { if (ip->flags & ~IPT_F_MASK) return false; if (ip->invflags & ~IPT_INV_MASK) return false; return true; } static unsigned int ipt_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } /* Performance critical */ static inline struct ipt_entry * get_entry(const void *base, unsigned int offset) { return (struct ipt_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; return e->target_offset == sizeof(struct ipt_entry) && memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; } /* for const-correctness */ static inline const struct xt_entry_target * ipt_get_target_c(const struct ipt_entry *e) { return ipt_get_target((struct ipt_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP_TRACE_COMMENT_RULE, NF_IP_TRACE_COMMENT_RETURN, NF_IP_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP_TRACE_COMMENT_RULE] = "rule", [NF_IP_TRACE_COMMENT_RETURN] = "return", [NF_IP_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = 4, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ipt_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] : comments[NF_IP_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ipt_entry *e) { const struct ipt_entry *root; const char *hookname, *chainname, *comment; const struct ipt_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ipt_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; ip = ip_hdr(skb); indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; acpar.thoff = ip_hdrlen(skb); acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); if (!ip_packet_match(ip, indev, outdev, &e->ip, acpar.fragoff)) { no_match: e = ipt_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ipt_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); } else { e = jumpstack[--stackidx]; e = ipt_next_entry(e); } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) { /* Target might have changed stuff. */ ip = ip_hdr(skb); e = ipt_next_entry(e); } else { /* Verdict */ break; } } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ipt_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ipt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV4; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ip->proto, ip->invflags & IPT_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ipt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ipt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV4, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ip.proto, e->ip.invflags & IPT_INV_PROTO); } static int find_check_entry(struct ipt_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ip; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV4; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ipt_get_target(e); target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ipt_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ipt_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || (unsigned char *)e + sizeof(struct ipt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ipt_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip_checkentry(&e->ip)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ipt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ipt_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV4; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ipt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ipt_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ipt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ipt_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; /* macro does multi eval of i */ cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ipt_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; /* macro does multi eval of i */ } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ipt_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ipt_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ipt_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ipt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ipt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ipt_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ipt_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ipt_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ipt_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET); #endif t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strscpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET); #endif return ret; } static int get_entries(struct net *net, struct ipt_get_entries __user *uptr, const int *len) { int ret; struct ipt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ipt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ipt_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ipt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ipt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ipt_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ipt_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ipt_entry entries[]; }; static int compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ipt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ipt_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ipt_entry); *size -= sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ipt_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ipt_ip *ip, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ipt_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ipt_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ipt_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip_checkentry(&e->ip)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ip, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ipt_get_target(e); target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ipt_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ipt_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ipt_entry); *size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ipt_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ipt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ipt_entry *iter0; struct ipt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET); ret = xt_compat_init_offsets(AF_INET, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. * entry1/newinfo contains a 64bit ruleset that looks exactly as * generated by 64bit userspace. * * Call standard translate_table() to validate all hook_entrys, * underflows, check for loops, etc. */ xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ipt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ipt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ipt_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ipt_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ipt_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, int *len) { int ret; struct compat_ipt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ipt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET); return ret; } #endif static int do_ipt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IPT_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IPT_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IPT_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IPT_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IPT_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET, rev.name, rev.revision, target, &ret), "ipt_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ipt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ipt_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ipt_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } /* No template? No need to do anything. This is used by 'nat' table, it registers * with the nat core instead of the netfilter core. */ if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ipt_unregister_table(net, new_table); return ret; } void ipt_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ipt_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); if (table) __ipt_unregister_table(net, table); } static struct xt_target ipt_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV4, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ipt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV4, }, }; static struct nf_sockopt_ops ipt_sockopts = { .pf = PF_INET, .set_optmin = IPT_BASE_CTL, .set_optmax = IPT_SO_SET_MAX+1, .set = do_ipt_set_ctl, .get_optmin = IPT_BASE_CTL, .get_optmax = IPT_SO_GET_MAX+1, .get = do_ipt_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV4); } static void __net_exit ip_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV4); } static struct pernet_operations ip_tables_net_ops = { .init = ip_tables_net_init, .exit = ip_tables_net_exit, }; static int __init ip_tables_init(void) { int ret; ret = register_pernet_subsys(&ip_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ipt_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); err2: unregister_pernet_subsys(&ip_tables_net_ops); err1: return ret; } static void __exit ip_tables_fini(void) { nf_unregister_sockopt(&ipt_sockopts); xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); unregister_pernet_subsys(&ip_tables_net_ops); } EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table_pre_exit); EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); module_exit(ip_tables_fini); |
| 379 376 2 2 2 2 1 1 49 62 2 1 10 49 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * scsi_error.c Copyright (C) 1997 Eric Youngdale * * SCSI error/timeout handling * Initial versions: Eric Youngdale. Based upon conversations with * Leonard Zubkoff and David Miller at Linux Expo, * ideas originating from all over the place. * * Restructured scsi_unjam_host and associated functions. * September 04, 2002 Mike Anderson (andmike@us.ibm.com) * * Forward port of Russell King's (rmk@arm.linux.org.uk) changes and * minor cleanups. * September 30, 2002 Mike Anderson (andmike@us.ibm.com) */ #include <linux/module.h> #include <linux/sched.h> #include <linux/gfp.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/interrupt.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/jiffies.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_common.h> #include <scsi/scsi_transport.h> #include <scsi/scsi_host.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsi_dh.h> #include <scsi/scsi_devinfo.h> #include <scsi/sg.h> #include "scsi_priv.h" #include "scsi_logging.h" #include "scsi_transport_api.h" #include <trace/events/scsi.h> #include <linux/unaligned.h> /* * These should *probably* be handled by the host itself. * Since it is allowed to sleep, it probably should. */ #define BUS_RESET_SETTLE_TIME (10) #define HOST_RESET_SETTLE_TIME (10) static int scsi_eh_try_stu(struct scsi_cmnd *scmd); static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *, struct scsi_cmnd *); void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) { lockdep_assert_held(shost->host_lock); if (busy == shost->host_failed) { trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, "Waking error handler thread\n")); } } /** * scsi_schedule_eh - schedule EH for SCSI host * @shost: SCSI host to invoke error handling on. * * Schedule SCSI EH without scmd. */ void scsi_schedule_eh(struct Scsi_Host *shost) { unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { shost->host_eh_scheduled++; scsi_eh_wakeup(shost, scsi_host_busy(shost)); } spin_unlock_irqrestore(shost->host_lock, flags); } EXPORT_SYMBOL_GPL(scsi_schedule_eh); static int scsi_host_eh_past_deadline(struct Scsi_Host *shost) { if (!shost->last_reset || shost->eh_deadline == -1) return 0; /* * 32bit accesses are guaranteed to be atomic * (on all supported architectures), so instead * of using a spinlock we can as well double check * if eh_deadline has been set to 'off' during the * time_before call. */ if (time_before(jiffies, shost->last_reset + shost->eh_deadline) && shost->eh_deadline > -1) return 0; return 1; } static bool scsi_cmd_retry_allowed(struct scsi_cmnd *cmd) { if (cmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT) return true; return ++cmd->retries <= cmd->allowed; } static bool scsi_eh_should_retry_cmd(struct scsi_cmnd *cmd) { struct scsi_device *sdev = cmd->device; struct Scsi_Host *host = sdev->host; if (host->hostt->eh_should_retry_cmd) return host->hostt->eh_should_retry_cmd(cmd); return true; } /** * scmd_eh_abort_handler - Handle command aborts * @work: command to be aborted. * * Note: this function must be called only for a command that has timed out. * Because the block layer marks a request as complete before it calls * scsi_timeout(), a .scsi_done() call from the LLD for a command that has * timed out do not have any effect. Hence it is safe to call * scsi_finish_command() from this function. */ void scmd_eh_abort_handler(struct work_struct *work) { struct scsi_cmnd *scmd = container_of(work, struct scsi_cmnd, abort_work.work); struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; enum scsi_disposition rtn; unsigned long flags; if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "eh timeout, not aborting\n")); goto out; } SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "aborting command\n")); rtn = scsi_try_to_abort_cmd(shost->hostt, scmd); if (rtn != SUCCESS) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "cmd abort %s\n", (rtn == FAST_IO_FAIL) ? "not send" : "failed")); goto out; } set_host_byte(scmd, DID_TIME_OUT); if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "eh timeout, not retrying " "aborted command\n")); goto out; } spin_lock_irqsave(shost->host_lock, flags); list_del_init(&scmd->eh_entry); /* * If the abort succeeds, and there is no further * EH action, clear the ->last_reset time. */ if (list_empty(&shost->eh_abort_list) && list_empty(&shost->eh_cmd_q)) if (shost->eh_deadline != -1) shost->last_reset = 0; spin_unlock_irqrestore(shost->host_lock, flags); if (!scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) && scsi_eh_should_retry_cmd(scmd)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "retry aborted command\n")); scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY); } else { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "finish aborted command\n")); scsi_finish_command(scmd); } return; out: spin_lock_irqsave(shost->host_lock, flags); list_del_init(&scmd->eh_entry); spin_unlock_irqrestore(shost->host_lock, flags); scsi_eh_scmd_add(scmd); } /** * scsi_abort_command - schedule a command abort * @scmd: scmd to abort. * * We only need to abort commands after a command timeout */ static int scsi_abort_command(struct scsi_cmnd *scmd) { struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; unsigned long flags; if (!shost->hostt->eh_abort_handler) { /* No abort handler, fail command directly */ return FAILED; } if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { /* * Retry after abort failed, escalate to next level. */ SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "previous abort failed\n")); BUG_ON(delayed_work_pending(&scmd->abort_work)); return FAILED; } spin_lock_irqsave(shost->host_lock, flags); if (shost->eh_deadline != -1 && !shost->last_reset) shost->last_reset = jiffies; BUG_ON(!list_empty(&scmd->eh_entry)); list_add_tail(&scmd->eh_entry, &shost->eh_abort_list); spin_unlock_irqrestore(shost->host_lock, flags); scmd->eh_eflags |= SCSI_EH_ABORT_SCHEDULED; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "abort scheduled\n")); queue_delayed_work(shost->tmf_work_q, &scmd->abort_work, HZ / 100); return SUCCESS; } /** * scsi_eh_reset - call into ->eh_action to reset internal counters * @scmd: scmd to run eh on. * * The scsi driver might be carrying internal state about the * devices, so we need to call into the driver to reset the * internal state once the error handler is started. */ static void scsi_eh_reset(struct scsi_cmnd *scmd) { if (!blk_rq_is_passthrough(scsi_cmd_to_rq(scmd))) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); if (sdrv->eh_reset) sdrv->eh_reset(scmd); } } static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; unsigned int busy = scsi_host_busy(shost); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } /** * scsi_eh_scmd_add - add scsi cmd to error handling. * @scmd: scmd to run eh on. */ void scsi_eh_scmd_add(struct scsi_cmnd *scmd) { struct Scsi_Host *shost = scmd->device->host; unsigned long flags; int ret; WARN_ON_ONCE(!shost->ehandler); WARN_ON_ONCE(!test_bit(SCMD_STATE_INFLIGHT, &scmd->state)); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RECOVERY)) { ret = scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY); WARN_ON_ONCE(ret); } if (shost->eh_deadline != -1 && !shost->last_reset) shost->last_reset = jiffies; scsi_eh_reset(scmd); list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q); spin_unlock_irqrestore(shost->host_lock, flags); /* * Ensure that all tasks observe the host state change before the * host_failed change. */ call_rcu_hurry(&scmd->rcu, scsi_eh_inc_host_failed); } /** * scsi_timeout - Timeout function for normal scsi commands. * @req: request that is timing out. * * Notes: * We do not need to lock this. There is the potential for a race * only in that the normal completion handling might run, but if the * normal completion function determines that the timer has already * fired, then it mustn't do anything. */ enum blk_eh_timer_return scsi_timeout(struct request *req) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); struct Scsi_Host *host = scmd->device->host; trace_scsi_dispatch_cmd_timeout(scmd); scsi_log_completion(scmd, TIMEOUT_ERROR); atomic_inc(&scmd->device->iotmo_cnt); if (host->eh_deadline != -1 && !host->last_reset) host->last_reset = jiffies; if (host->hostt->eh_timed_out) { switch (host->hostt->eh_timed_out(scmd)) { case SCSI_EH_DONE: return BLK_EH_DONE; case SCSI_EH_RESET_TIMER: return BLK_EH_RESET_TIMER; case SCSI_EH_NOT_HANDLED: break; } } /* * If scsi_done() has already set SCMD_STATE_COMPLETE, do not modify * *scmd. */ if (test_and_set_bit(SCMD_STATE_COMPLETE, &scmd->state)) return BLK_EH_DONE; atomic_inc(&scmd->device->iodone_cnt); if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); } return BLK_EH_DONE; } /** * scsi_block_when_processing_errors - Prevent cmds from being queued. * @sdev: Device on which we are performing recovery. * * Description: * We block until the host is out of error recovery, and then check to * see whether the host or the device is offline. * * Return value: * 0 when dev was taken offline by error recovery. 1 OK to proceed. */ int scsi_block_when_processing_errors(struct scsi_device *sdev) { int online; wait_event(sdev->host->host_wait, !scsi_host_in_recovery(sdev->host)); online = scsi_device_online(sdev); return online; } EXPORT_SYMBOL(scsi_block_when_processing_errors); #ifdef CONFIG_SCSI_LOGGING /** * scsi_eh_prt_fail_stats - Log info on failures. * @shost: scsi host being recovered. * @work_q: Queue of scsi cmds to process. */ static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost, struct list_head *work_q) { struct scsi_cmnd *scmd; struct scsi_device *sdev; int total_failures = 0; int cmd_failed = 0; int cmd_cancel = 0; int devices_failed = 0; shost_for_each_device(sdev, shost) { list_for_each_entry(scmd, work_q, eh_entry) { if (scmd->device == sdev) { ++total_failures; if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) ++cmd_cancel; else ++cmd_failed; } } if (cmd_cancel || cmd_failed) { SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: cmds failed: %d, cancel: %d\n", __func__, cmd_failed, cmd_cancel)); cmd_cancel = 0; cmd_failed = 0; ++devices_failed; } } SCSI_LOG_ERROR_RECOVERY(2, shost_printk(KERN_INFO, shost, "Total of %d commands on %d" " devices require eh work\n", total_failures, devices_failed)); } #endif /** * scsi_report_lun_change - Set flag on all *other* devices on the same target * to indicate that a UNIT ATTENTION is expected. * @sdev: Device reporting the UNIT ATTENTION */ static void scsi_report_lun_change(struct scsi_device *sdev) { sdev->sdev_target->expecting_lun_change = 1; } /** * scsi_report_sense - Examine scsi sense information and log messages for * certain conditions, also issue uevents for some of them. * @sdev: Device reporting the sense code * @sshdr: sshdr to be examined */ static void scsi_report_sense(struct scsi_device *sdev, struct scsi_sense_hdr *sshdr) { enum scsi_device_event evt_type = SDEV_EVT_MAXBITS; /* i.e. none */ if (sshdr->sense_key == UNIT_ATTENTION) { if (sshdr->asc == 0x3f && sshdr->ascq == 0x03) { evt_type = SDEV_EVT_INQUIRY_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Inquiry data has changed"); } else if (sshdr->asc == 0x3f && sshdr->ascq == 0x0e) { evt_type = SDEV_EVT_LUN_CHANGE_REPORTED; scsi_report_lun_change(sdev); sdev_printk(KERN_WARNING, sdev, "LUN assignments on this target have " "changed. The Linux SCSI layer does not " "automatically remap LUN assignments.\n"); } else if (sshdr->asc == 0x3f) sdev_printk(KERN_WARNING, sdev, "Operating parameters on this target have " "changed. The Linux SCSI layer does not " "automatically adjust these parameters.\n"); if (sshdr->asc == 0x38 && sshdr->ascq == 0x07) { evt_type = SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED; sdev_printk(KERN_WARNING, sdev, "Warning! Received an indication that the " "LUN reached a thin provisioning soft " "threshold.\n"); } if (sshdr->asc == 0x29) { evt_type = SDEV_EVT_POWER_ON_RESET_OCCURRED; /* * Do not print message if it is an expected side-effect * of runtime PM. */ if (!sdev->silence_suspend) sdev_printk(KERN_WARNING, sdev, "Power-on or device reset occurred\n"); } if (sshdr->asc == 0x2a && sshdr->ascq == 0x01) { evt_type = SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Mode parameters changed"); } else if (sshdr->asc == 0x2a && sshdr->ascq == 0x06) { evt_type = SDEV_EVT_ALUA_STATE_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Asymmetric access state changed"); } else if (sshdr->asc == 0x2a && sshdr->ascq == 0x09) { evt_type = SDEV_EVT_CAPACITY_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Capacity data has changed"); } else if (sshdr->asc == 0x2a) sdev_printk(KERN_WARNING, sdev, "Parameters changed"); } if (evt_type != SDEV_EVT_MAXBITS) { set_bit(evt_type, sdev->pending_events); schedule_work(&sdev->event_work); } } static inline void set_scsi_ml_byte(struct scsi_cmnd *cmd, u8 status) { cmd->result = (cmd->result & 0xffff00ff) | (status << 8); } /** * scsi_check_sense - Examine scsi cmd sense * @scmd: Cmd to have sense checked. * * Return value: * SUCCESS or FAILED or NEEDS_RETRY or ADD_TO_MLQUEUE * * Notes: * When a deferred error is detected the current command has * not been executed and needs retrying. */ enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd) { struct request *req = scsi_cmd_to_rq(scmd); struct scsi_device *sdev = scmd->device; struct scsi_sense_hdr sshdr; if (! scsi_command_normalize_sense(scmd, &sshdr)) return FAILED; /* no valid sense data */ scsi_report_sense(sdev, &sshdr); if (sshdr.sense_key == UNIT_ATTENTION) { /* * Increment the counters for Power on/Reset or New Media so * that all ULDs interested in these can see that those have * happened, even if someone else gets the sense data. */ if (sshdr.asc == 0x28) scmd->device->ua_new_media_ctr++; else if (sshdr.asc == 0x29) scmd->device->ua_por_ctr++; } if (scsi_sense_is_deferred(&sshdr)) return NEEDS_RETRY; if (sdev->handler && sdev->handler->check_sense) { enum scsi_disposition rc; rc = sdev->handler->check_sense(sdev, &sshdr); if (rc != SCSI_RETURN_NOT_HANDLED) return rc; /* handler does not care. Drop down to default handling */ } if (scmd->cmnd[0] == TEST_UNIT_READY && scmd->submitter != SUBMITTED_BY_SCSI_ERROR_HANDLER) /* * nasty: for mid-layer issued TURs, we need to return the * actual sense data without any recovery attempt. For eh * issued ones, we need to try to recover and interpret */ return SUCCESS; /* * Previous logic looked for FILEMARK, EOM or ILI which are * mainly associated with tapes and returned SUCCESS. */ if (sshdr.response_code == 0x70) { /* fixed format */ if (scmd->sense_buffer[2] & 0xe0) return SUCCESS; } else { /* * descriptor format: look for "stream commands sense data * descriptor" (see SSC-3). Assume single sense data * descriptor. Ignore ILI from SBC-2 READ LONG and WRITE LONG. */ if ((sshdr.additional_length > 3) && (scmd->sense_buffer[8] == 0x4) && (scmd->sense_buffer[11] & 0xe0)) return SUCCESS; } switch (sshdr.sense_key) { case NO_SENSE: return SUCCESS; case RECOVERED_ERROR: return /* soft_error */ SUCCESS; case ABORTED_COMMAND: if (sshdr.asc == 0x10) /* DIF */ return SUCCESS; /* * Check aborts due to command duration limit policy: * ABORTED COMMAND additional sense code with the * COMMAND TIMEOUT BEFORE PROCESSING or * COMMAND TIMEOUT DURING PROCESSING or * COMMAND TIMEOUT DURING PROCESSING DUE TO ERROR RECOVERY * additional sense code qualifiers. */ if (sshdr.asc == 0x2e && sshdr.ascq >= 0x01 && sshdr.ascq <= 0x03) { set_scsi_ml_byte(scmd, SCSIML_STAT_DL_TIMEOUT); req->cmd_flags |= REQ_FAILFAST_DEV; req->rq_flags |= RQF_QUIET; return SUCCESS; } if (sshdr.asc == 0x44 && sdev->sdev_bflags & BLIST_RETRY_ITF) return ADD_TO_MLQUEUE; if (sshdr.asc == 0xc1 && sshdr.ascq == 0x01 && sdev->sdev_bflags & BLIST_RETRY_ASC_C1) return ADD_TO_MLQUEUE; return NEEDS_RETRY; case NOT_READY: case UNIT_ATTENTION: /* * if we are expecting a cc/ua because of a bus reset that we * performed, treat this just as a retry. otherwise this is * information that we should pass up to the upper-level driver * so that we can deal with it there. */ if (scmd->device->expecting_cc_ua) { /* * Because some device does not queue unit * attentions correctly, we carefully check * additional sense code and qualifier so as * not to squash media change unit attention. */ if (sshdr.asc != 0x28 || sshdr.ascq != 0x00) { scmd->device->expecting_cc_ua = 0; return NEEDS_RETRY; } } /* * we might also expect a cc/ua if another LUN on the target * reported a UA with an ASC/ASCQ of 3F 0E - * REPORTED LUNS DATA HAS CHANGED. */ if (scmd->device->sdev_target->expecting_lun_change && sshdr.asc == 0x3f && sshdr.ascq == 0x0e) return NEEDS_RETRY; /* * if the device is in the process of becoming ready, we * should retry. */ if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01)) return NEEDS_RETRY; /* * if the device is not started, we need to wake * the error handler to start the motor */ if (scmd->device->allow_restart && (sshdr.asc == 0x04) && (sshdr.ascq == 0x02)) return FAILED; /* * Pass the UA upwards for a determination in the completion * functions. */ return SUCCESS; /* these are not supported */ case DATA_PROTECT: if (sshdr.asc == 0x27 && sshdr.ascq == 0x07) { /* Thin provisioning hard threshold reached */ set_scsi_ml_byte(scmd, SCSIML_STAT_NOSPC); return SUCCESS; } fallthrough; case COPY_ABORTED: case VOLUME_OVERFLOW: case MISCOMPARE: case BLANK_CHECK: set_scsi_ml_byte(scmd, SCSIML_STAT_TGT_FAILURE); return SUCCESS; case MEDIUM_ERROR: if (sshdr.asc == 0x11 || /* UNRECOVERED READ ERR */ sshdr.asc == 0x13 || /* AMNF DATA FIELD */ sshdr.asc == 0x14) { /* RECORD NOT FOUND */ set_scsi_ml_byte(scmd, SCSIML_STAT_MED_ERROR); return SUCCESS; } return NEEDS_RETRY; case HARDWARE_ERROR: if (scmd->device->retry_hwerror) return ADD_TO_MLQUEUE; else set_scsi_ml_byte(scmd, SCSIML_STAT_TGT_FAILURE); fallthrough; case ILLEGAL_REQUEST: if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x22 || /* Invalid function */ sshdr.asc == 0x24 || /* Invalid field in cdb */ sshdr.asc == 0x26 || /* Parameter value invalid */ sshdr.asc == 0x27) { /* Write protected */ set_scsi_ml_byte(scmd, SCSIML_STAT_TGT_FAILURE); } return SUCCESS; case COMPLETED: /* * A command using command duration limits (CDL) with a * descriptor set with policy 0xD may be completed with success * and the sense data DATA CURRENTLY UNAVAILABLE, indicating * that the command was in fact aborted because it exceeded its * duration limit. Never retry these commands. */ if (sshdr.asc == 0x55 && sshdr.ascq == 0x0a) { set_scsi_ml_byte(scmd, SCSIML_STAT_DL_TIMEOUT); req->cmd_flags |= REQ_FAILFAST_DEV; req->rq_flags |= RQF_QUIET; } return SUCCESS; default: return SUCCESS; } } EXPORT_SYMBOL_GPL(scsi_check_sense); static void scsi_handle_queue_ramp_up(struct scsi_device *sdev) { const struct scsi_host_template *sht = sdev->host->hostt; struct scsi_device *tmp_sdev; if (!sht->track_queue_depth || sdev->queue_depth >= sdev->max_queue_depth) return; if (time_before(jiffies, sdev->last_queue_ramp_up + sdev->queue_ramp_up_period)) return; if (time_before(jiffies, sdev->last_queue_full_time + sdev->queue_ramp_up_period)) return; /* * Walk all devices of a target and do * ramp up on them. */ shost_for_each_device(tmp_sdev, sdev->host) { if (tmp_sdev->channel != sdev->channel || tmp_sdev->id != sdev->id || tmp_sdev->queue_depth == sdev->max_queue_depth) continue; scsi_change_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1); sdev->last_queue_ramp_up = jiffies; } } static void scsi_handle_queue_full(struct scsi_device *sdev) { const struct scsi_host_template *sht = sdev->host->hostt; struct scsi_device *tmp_sdev; if (!sht->track_queue_depth) return; shost_for_each_device(tmp_sdev, sdev->host) { if (tmp_sdev->channel != sdev->channel || tmp_sdev->id != sdev->id) continue; /* * We do not know the number of commands that were at * the device when we got the queue full so we start * from the highest possible value and work our way down. */ scsi_track_queue_full(tmp_sdev, tmp_sdev->queue_depth - 1); } } /** * scsi_eh_completed_normally - Disposition a eh cmd on return from LLD. * @scmd: SCSI cmd to examine. * * Notes: * This is *only* called when we are examining the status of commands * queued during error recovery. the main difference here is that we * don't allow for the possibility of retries here, and we are a lot * more restrictive about what we consider acceptable. */ static enum scsi_disposition scsi_eh_completed_normally(struct scsi_cmnd *scmd) { /* * first check the host byte, to see if there is anything in there * that would indicate what we need to do. */ if (host_byte(scmd->result) == DID_RESET) { /* * rats. we are already in the error handler, so we now * get to try and figure out what to do next. if the sense * is valid, we have a pretty good idea of what to do. * if not, we mark it as FAILED. */ return scsi_check_sense(scmd); } if (host_byte(scmd->result) != DID_OK) return FAILED; /* * now, check the status byte to see if this indicates * anything special. */ switch (get_status_byte(scmd)) { case SAM_STAT_GOOD: scsi_handle_queue_ramp_up(scmd->device); if (scmd->sense_buffer && SCSI_SENSE_VALID(scmd)) /* * If we have sense data, call scsi_check_sense() in * order to set the correct SCSI ML byte (if any). * No point in checking the return value, since the * command has already completed successfully. */ scsi_check_sense(scmd); fallthrough; case SAM_STAT_COMMAND_TERMINATED: return SUCCESS; case SAM_STAT_CHECK_CONDITION: return scsi_check_sense(scmd); case SAM_STAT_CONDITION_MET: case SAM_STAT_INTERMEDIATE: case SAM_STAT_INTERMEDIATE_CONDITION_MET: /* * who knows? FIXME(eric) */ return SUCCESS; case SAM_STAT_RESERVATION_CONFLICT: if (scmd->cmnd[0] == TEST_UNIT_READY) /* it is a success, we probed the device and * found it */ return SUCCESS; /* otherwise, we failed to send the command */ return FAILED; case SAM_STAT_TASK_SET_FULL: scsi_handle_queue_full(scmd->device); fallthrough; case SAM_STAT_BUSY: return NEEDS_RETRY; default: return FAILED; } return FAILED; } /** * scsi_eh_done - Completion function for error handling. * @scmd: Cmd that is done. */ void scsi_eh_done(struct scsi_cmnd *scmd) { struct completion *eh_action; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s result: %x\n", __func__, scmd->result)); eh_action = scmd->device->host->eh_action; if (eh_action) complete(eh_action); } /** * scsi_try_host_reset - ask host adapter to reset itself * @scmd: SCSI cmd to send host reset. */ static enum scsi_disposition scsi_try_host_reset(struct scsi_cmnd *scmd) { unsigned long flags; enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; const struct scsi_host_template *hostt = host->hostt; SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, host, "Snd Host RST\n")); if (!hostt->eh_host_reset_handler) return FAILED; rtn = hostt->eh_host_reset_handler(scmd); if (rtn == SUCCESS) { if (!hostt->skip_settle_delay) ssleep(HOST_RESET_SETTLE_TIME); spin_lock_irqsave(host->host_lock, flags); scsi_report_bus_reset(host, scmd_channel(scmd)); spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } /** * scsi_try_bus_reset - ask host to perform a bus reset * @scmd: SCSI cmd to send bus reset. */ static enum scsi_disposition scsi_try_bus_reset(struct scsi_cmnd *scmd) { unsigned long flags; enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; const struct scsi_host_template *hostt = host->hostt; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: Snd Bus RST\n", __func__)); if (!hostt->eh_bus_reset_handler) return FAILED; rtn = hostt->eh_bus_reset_handler(scmd); if (rtn == SUCCESS) { if (!hostt->skip_settle_delay) ssleep(BUS_RESET_SETTLE_TIME); spin_lock_irqsave(host->host_lock, flags); scsi_report_bus_reset(host, scmd_channel(scmd)); spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } static void __scsi_report_device_reset(struct scsi_device *sdev, void *data) { sdev->was_reset = 1; sdev->expecting_cc_ua = 1; } /** * scsi_try_target_reset - Ask host to perform a target reset * @scmd: SCSI cmd used to send a target reset * * Notes: * There is no timeout for this operation. if this operation is * unreliable for a given host, then the host itself needs to put a * timer on it, and set the host back to a consistent state prior to * returning. */ static enum scsi_disposition scsi_try_target_reset(struct scsi_cmnd *scmd) { unsigned long flags; enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; const struct scsi_host_template *hostt = host->hostt; if (!hostt->eh_target_reset_handler) return FAILED; rtn = hostt->eh_target_reset_handler(scmd); if (rtn == SUCCESS) { spin_lock_irqsave(host->host_lock, flags); __starget_for_each_device(scsi_target(scmd->device), NULL, __scsi_report_device_reset); spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } /** * scsi_try_bus_device_reset - Ask host to perform a BDR on a dev * @scmd: SCSI cmd used to send BDR * * Notes: * There is no timeout for this operation. if this operation is * unreliable for a given host, then the host itself needs to put a * timer on it, and set the host back to a consistent state prior to * returning. */ static enum scsi_disposition scsi_try_bus_device_reset(struct scsi_cmnd *scmd) { enum scsi_disposition rtn; const struct scsi_host_template *hostt = scmd->device->host->hostt; if (!hostt->eh_device_reset_handler) return FAILED; rtn = hostt->eh_device_reset_handler(scmd); if (rtn == SUCCESS) __scsi_report_device_reset(scmd->device, NULL); return rtn; } /** * scsi_try_to_abort_cmd - Ask host to abort a SCSI command * @hostt: SCSI driver host template * @scmd: SCSI cmd used to send a target reset * * Return value: * SUCCESS, FAILED, or FAST_IO_FAIL * * Notes: * SUCCESS does not necessarily indicate that the command * has been aborted; it only indicates that the LLDDs * has cleared all references to that command. * LLDDs should return FAILED only if an abort was required * but could not be executed. LLDDs should return FAST_IO_FAIL * if the device is temporarily unavailable (eg due to a * link down on FibreChannel) */ static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *hostt, struct scsi_cmnd *scmd) { if (!hostt->eh_abort_handler) return FAILED; return hostt->eh_abort_handler(scmd); } static void scsi_abort_eh_cmnd(struct scsi_cmnd *scmd) { if (scsi_try_to_abort_cmd(scmd->device->host->hostt, scmd) != SUCCESS) if (scsi_try_bus_device_reset(scmd) != SUCCESS) if (scsi_try_target_reset(scmd) != SUCCESS) if (scsi_try_bus_reset(scmd) != SUCCESS) scsi_try_host_reset(scmd); } /** * scsi_eh_prep_cmnd - Save a scsi command info as part of error recovery * @scmd: SCSI command structure to hijack * @ses: structure to save restore information * @cmnd: CDB to send. Can be NULL if no new cmnd is needed * @cmnd_size: size in bytes of @cmnd (must be <= MAX_COMMAND_SIZE) * @sense_bytes: size of sense data to copy. or 0 (if != 0 @cmnd is ignored) * * This function is used to save a scsi command information before re-execution * as part of the error recovery process. If @sense_bytes is 0 the command * sent must be one that does not transfer any data. If @sense_bytes != 0 * @cmnd is ignored and this functions sets up a REQUEST_SENSE command * and cmnd buffers to read @sense_bytes into @scmd->sense_buffer. */ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, unsigned char *cmnd, int cmnd_size, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; /* * We need saved copies of a number of fields - this is because * error handling may need to overwrite these with different values * to run different commands, and once error handling is complete, * we will need to restore these values prior to running the actual * command. */ ses->cmd_len = scmd->cmd_len; ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; ses->result = scmd->result; ses->resid_len = scmd->resid_len; ses->underflow = scmd->underflow; ses->prot_op = scmd->prot_op; ses->eh_eflags = scmd->eh_eflags; scmd->prot_op = SCSI_PROT_NORMAL; scmd->eh_eflags = 0; memcpy(ses->cmnd, scmd->cmnd, sizeof(ses->cmnd)); memset(scmd->cmnd, 0, sizeof(scmd->cmnd)); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->result = 0; scmd->resid_len = 0; if (sense_bytes) { scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, sense_bytes); sg_init_one(&ses->sense_sgl, scmd->sense_buffer, scmd->sdb.length); scmd->sdb.table.sgl = &ses->sense_sgl; scmd->sc_data_direction = DMA_FROM_DEVICE; scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1; scmd->cmnd[0] = REQUEST_SENSE; scmd->cmnd[4] = scmd->sdb.length; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } else { scmd->sc_data_direction = DMA_NONE; if (cmnd) { BUG_ON(cmnd_size > sizeof(scmd->cmnd)); memcpy(scmd->cmnd, cmnd, cmnd_size); scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } } scmd->underflow = 0; if (sdev->scsi_level <= SCSI_2 && sdev->scsi_level != SCSI_UNKNOWN) scmd->cmnd[1] = (scmd->cmnd[1] & 0x1f) | (sdev->lun << 5 & 0xe0); /* * Zero the sense buffer. The scsi spec mandates that any * untransferred sense data should be interpreted as being zero. */ memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); } EXPORT_SYMBOL(scsi_eh_prep_cmnd); /** * scsi_eh_restore_cmnd - Restore a scsi command info as part of error recovery * @scmd: SCSI command structure to restore * @ses: saved information from a coresponding call to scsi_eh_prep_cmnd * * Undo any damage done by above scsi_eh_prep_cmnd(). */ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) { /* * Restore original data */ scmd->cmd_len = ses->cmd_len; memcpy(scmd->cmnd, ses->cmnd, sizeof(ses->cmnd)); scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; scmd->result = ses->result; scmd->resid_len = ses->resid_len; scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; } EXPORT_SYMBOL(scsi_eh_restore_cmnd); /** * scsi_send_eh_cmnd - submit a scsi command as part of error recovery * @scmd: SCSI command structure to hijack * @cmnd: CDB to send * @cmnd_size: size in bytes of @cmnd * @timeout: timeout for this request * @sense_bytes: size of sense data to copy or 0 * * This function is used to send a scsi command down to a target device * as part of the error recovery process. See also scsi_eh_prep_cmnd() above. * * Return value: * SUCCESS or FAILED or NEEDS_RETRY */ static enum scsi_disposition scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd, int cmnd_size, int timeout, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; DECLARE_COMPLETION_ONSTACK(done); unsigned long timeleft = timeout, delay; struct scsi_eh_save ses; const unsigned long stall_for = msecs_to_jiffies(100); int rtn; retry: scsi_eh_prep_cmnd(scmd, &ses, cmnd, cmnd_size, sense_bytes); shost->eh_action = &done; scsi_log_send(scmd); scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER; scmd->flags |= SCMD_LAST; /* * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can * change the SCSI device state after we have examined it and before * .queuecommand() is called. */ mutex_lock(&sdev->state_mutex); while (sdev->sdev_state == SDEV_BLOCK && timeleft > 0) { mutex_unlock(&sdev->state_mutex); SCSI_LOG_ERROR_RECOVERY(5, sdev_printk(KERN_DEBUG, sdev, "%s: state %d <> %d\n", __func__, sdev->sdev_state, SDEV_BLOCK)); delay = min(timeleft, stall_for); timeleft -= delay; msleep(jiffies_to_msecs(delay)); mutex_lock(&sdev->state_mutex); } if (sdev->sdev_state != SDEV_BLOCK) rtn = shost->hostt->queuecommand(shost, scmd); else rtn = FAILED; mutex_unlock(&sdev->state_mutex); if (rtn) { if (timeleft > stall_for) { scsi_eh_restore_cmnd(scmd, &ses); timeleft -= stall_for; msleep(jiffies_to_msecs(stall_for)); goto retry; } /* signal not to enter either branch of the if () below */ timeleft = 0; rtn = FAILED; } else { timeleft = wait_for_completion_timeout(&done, timeout); rtn = SUCCESS; } shost->eh_action = NULL; scsi_log_completion(scmd, rtn); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s timeleft: %ld\n", __func__, timeleft)); /* * If there is time left scsi_eh_done got called, and we will examine * the actual status codes to see whether the command actually did * complete normally, else if we have a zero return and no time left, * the command must still be pending, so abort it and return FAILED. * If we never actually managed to issue the command, because * ->queuecommand() kept returning non zero, use the rtn = FAILED * value above (so don't execute either branch of the if) */ if (timeleft) { rtn = scsi_eh_completed_normally(scmd); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: scsi_eh_completed_normally %x\n", __func__, rtn)); switch (rtn) { case SUCCESS: case NEEDS_RETRY: case FAILED: break; case ADD_TO_MLQUEUE: rtn = NEEDS_RETRY; break; default: rtn = FAILED; break; } } else if (rtn != FAILED) { scsi_abort_eh_cmnd(scmd); rtn = FAILED; } scsi_eh_restore_cmnd(scmd, &ses); return rtn; } /** * scsi_request_sense - Request sense data from a particular target. * @scmd: SCSI cmd for request sense. * * Notes: * Some hosts automatically obtain this information, others require * that we obtain it on our own. This function will *not* return until * the command either times out, or it completes. */ static enum scsi_disposition scsi_request_sense(struct scsi_cmnd *scmd) { return scsi_send_eh_cmnd(scmd, NULL, 0, scmd->device->eh_timeout, ~0); } static enum scsi_disposition scsi_eh_action(struct scsi_cmnd *scmd, enum scsi_disposition rtn) { if (!blk_rq_is_passthrough(scsi_cmd_to_rq(scmd))) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); if (sdrv->eh_action) rtn = sdrv->eh_action(scmd, rtn); } return rtn; } /** * scsi_eh_finish_cmd - Handle a cmd that eh is finished with. * @scmd: Original SCSI cmd that eh has finished. * @done_q: Queue for processed commands. * * Notes: * We don't want to use the normal command completion while we are are * still handling errors - it may cause other commands to be queued, * and that would disturb what we are doing. Thus we really want to * keep a list of pending commands for final completion, and once we * are ready to leave error handling we handle completion for real. */ void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q) { list_move_tail(&scmd->eh_entry, done_q); } EXPORT_SYMBOL(scsi_eh_finish_cmd); /** * scsi_eh_get_sense - Get device sense data. * @work_q: Queue of commands to process. * @done_q: Queue of processed commands. * * Description: * See if we need to request sense information. if so, then get it * now, so we have a better idea of what to do. * * Notes: * This has the unfortunate side effect that if a shost adapter does * not automatically request sense information, we end up shutting * it down before we request it. * * All drivers should request sense information internally these days, * so for now all I have to say is tough noogies if you end up in here. * * XXX: Long term this code should go away, but that needs an audit of * all LLDDs first. */ int scsi_eh_get_sense(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; struct Scsi_Host *shost; enum scsi_disposition rtn; /* * If SCSI_EH_ABORT_SCHEDULED has been set, it is timeout IO, * should not get sense. */ list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if ((scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) || SCSI_SENSE_VALID(scmd)) continue; shost = scmd->device->host; if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: skip request sense, past eh deadline\n", current->comm)); break; } if (!scsi_status_is_check_condition(scmd->result)) /* * don't request sense if there's no check condition * status because the error we're processing isn't one * that has a sense code (and some devices get * confused by sense requests out of the blue) */ continue; SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd, "%s: requesting sense\n", current->comm)); rtn = scsi_request_sense(scmd); if (rtn != SUCCESS) continue; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "sense requested, result %x\n", scmd->result)); SCSI_LOG_ERROR_RECOVERY(3, scsi_print_sense(scmd)); rtn = scsi_decide_disposition(scmd); /* * if the result was normal, then just pass it along to the * upper level. */ if (rtn == SUCCESS) /* * We don't want this command reissued, just finished * with the sense data, so set retries to the max * allowed to ensure it won't get reissued. If the user * has requested infinite retries, we also want to * finish this command, so force completion by setting * retries and allowed to the same value. */ if (scmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT) scmd->retries = scmd->allowed = 1; else scmd->retries = scmd->allowed; else if (rtn != NEEDS_RETRY) continue; scsi_eh_finish_cmd(scmd, done_q); } return list_empty(work_q); } EXPORT_SYMBOL_GPL(scsi_eh_get_sense); /** * scsi_eh_tur - Send TUR to device. * @scmd: &scsi_cmnd to send TUR * * Return value: * 0 - Device is ready. 1 - Device NOT ready. */ static int scsi_eh_tur(struct scsi_cmnd *scmd) { static unsigned char tur_command[6] = {TEST_UNIT_READY, 0, 0, 0, 0, 0}; int retry_cnt = 1; enum scsi_disposition rtn; retry_tur: rtn = scsi_send_eh_cmnd(scmd, tur_command, 6, scmd->device->eh_timeout, 0); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s return: %x\n", __func__, rtn)); switch (rtn) { case NEEDS_RETRY: if (retry_cnt--) goto retry_tur; fallthrough; case SUCCESS: return 0; default: return 1; } } /** * scsi_eh_test_devices - check if devices are responding from error recovery. * @cmd_list: scsi commands in error recovery. * @work_q: queue for commands which still need more error recovery * @done_q: queue for commands which are finished * @try_stu: boolean on if a STU command should be tried in addition to TUR. * * Decription: * Tests if devices are in a working state. Commands to devices now in * a working state are sent to the done_q while commands to devices which * are still failing to respond are returned to the work_q for more * processing. **/ static int scsi_eh_test_devices(struct list_head *cmd_list, struct list_head *work_q, struct list_head *done_q, int try_stu) { struct scsi_cmnd *scmd, *next; struct scsi_device *sdev; int finish_cmds; while (!list_empty(cmd_list)) { scmd = list_entry(cmd_list->next, struct scsi_cmnd, eh_entry); sdev = scmd->device; if (!try_stu) { if (scsi_host_eh_past_deadline(sdev->host)) { /* Push items back onto work_q */ list_splice_init(cmd_list, work_q); SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: skip test device, past eh deadline", current->comm)); break; } } finish_cmds = !scsi_device_online(scmd->device) || (try_stu && !scsi_eh_try_stu(scmd) && !scsi_eh_tur(scmd)) || !scsi_eh_tur(scmd); list_for_each_entry_safe(scmd, next, cmd_list, eh_entry) if (scmd->device == sdev) { if (finish_cmds && (try_stu || scsi_eh_action(scmd, SUCCESS) == SUCCESS)) scsi_eh_finish_cmd(scmd, done_q); else list_move_tail(&scmd->eh_entry, work_q); } } return list_empty(work_q); } /** * scsi_eh_try_stu - Send START_UNIT to device. * @scmd: &scsi_cmnd to send START_UNIT * * Return value: * 0 - Device is ready. 1 - Device NOT ready. */ static int scsi_eh_try_stu(struct scsi_cmnd *scmd) { static unsigned char stu_command[6] = {START_STOP, 0, 0, 0, 1, 0}; if (scmd->device->allow_restart) { int i; enum scsi_disposition rtn = NEEDS_RETRY; for (i = 0; rtn == NEEDS_RETRY && i < 2; i++) rtn = scsi_send_eh_cmnd(scmd, stu_command, 6, scmd->device->eh_timeout, 0); if (rtn == SUCCESS) return 0; } return 1; } /** * scsi_eh_stu - send START_UNIT if needed * @shost: &scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. * * Notes: * If commands are failing due to not ready, initializing command required, * try revalidating the device, which will end up sending a start unit. */ static int scsi_eh_stu(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *stu_scmd, *next; struct scsi_device *sdev; shost_for_each_device(sdev, shost) { if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: skip START_UNIT, past eh deadline\n", current->comm)); scsi_device_put(sdev); break; } stu_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) if (scmd->device == sdev && SCSI_SENSE_VALID(scmd) && scsi_check_sense(scmd) == FAILED ) { stu_scmd = scmd; break; } if (!stu_scmd) continue; SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: Sending START_UNIT\n", current->comm)); if (!scsi_eh_try_stu(stu_scmd)) { if (!scsi_device_online(sdev) || !scsi_eh_tur(stu_scmd)) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (scmd->device == sdev && scsi_eh_action(scmd, SUCCESS) == SUCCESS) scsi_eh_finish_cmd(scmd, done_q); } } } else { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: START_UNIT failed\n", current->comm)); } } return list_empty(work_q); } /** * scsi_eh_bus_device_reset - send bdr if needed * @shost: scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. * * Notes: * Try a bus device reset. Still, look to see whether we have multiple * devices that are jammed or not - if we have multiple devices, it * makes no sense to try bus_device_reset - we really would need to try * a bus_reset instead. */ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *bdr_scmd, *next; struct scsi_device *sdev; enum scsi_disposition rtn; shost_for_each_device(sdev, shost) { if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: skip BDR, past eh deadline\n", current->comm)); scsi_device_put(sdev); break; } bdr_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) if (scmd->device == sdev) { bdr_scmd = scmd; break; } if (!bdr_scmd) continue; SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: Sending BDR\n", current->comm)); rtn = scsi_try_bus_device_reset(bdr_scmd); if (rtn == SUCCESS || rtn == FAST_IO_FAIL) { if (!scsi_device_online(sdev) || rtn == FAST_IO_FAIL || !scsi_eh_tur(bdr_scmd)) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (scmd->device == sdev && scsi_eh_action(scmd, rtn) != FAILED) scsi_eh_finish_cmd(scmd, done_q); } } } else { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: BDR failed\n", current->comm)); } } return list_empty(work_q); } /** * scsi_eh_target_reset - send target reset if needed * @shost: scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. * * Notes: * Try a target reset. */ static int scsi_eh_target_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { LIST_HEAD(tmp_list); LIST_HEAD(check_list); list_splice_init(work_q, &tmp_list); while (!list_empty(&tmp_list)) { struct scsi_cmnd *next, *scmd; enum scsi_disposition rtn; unsigned int id; if (scsi_host_eh_past_deadline(shost)) { /* push back on work queue for further processing */ list_splice_init(&check_list, work_q); list_splice_init(&tmp_list, work_q); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Skip target reset, past eh deadline\n", current->comm)); return list_empty(work_q); } scmd = list_entry(tmp_list.next, struct scsi_cmnd, eh_entry); id = scmd_id(scmd); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Sending target reset to target %d\n", current->comm, id)); rtn = scsi_try_target_reset(scmd); if (rtn != SUCCESS && rtn != FAST_IO_FAIL) SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Target reset failed" " target: %d\n", current->comm, id)); list_for_each_entry_safe(scmd, next, &tmp_list, eh_entry) { if (scmd_id(scmd) != id) continue; if (rtn == SUCCESS) list_move_tail(&scmd->eh_entry, &check_list); else if (rtn == FAST_IO_FAIL) scsi_eh_finish_cmd(scmd, done_q); else /* push back on work queue for further processing */ list_move(&scmd->eh_entry, work_q); } } return scsi_eh_test_devices(&check_list, work_q, done_q, 0); } /** * scsi_eh_bus_reset - send a bus reset * @shost: &scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ static int scsi_eh_bus_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *chan_scmd, *next; LIST_HEAD(check_list); unsigned int channel; enum scsi_disposition rtn; /* * we really want to loop over the various channels, and do this on * a channel by channel basis. we should also check to see if any * of the failed commands are on soft_reset devices, and if so, skip * the reset. */ for (channel = 0; channel <= shost->max_channel; channel++) { if (scsi_host_eh_past_deadline(shost)) { list_splice_init(&check_list, work_q); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: skip BRST, past eh deadline\n", current->comm)); return list_empty(work_q); } chan_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) { if (channel == scmd_channel(scmd)) { chan_scmd = scmd; break; /* * FIXME add back in some support for * soft_reset devices. */ } } if (!chan_scmd) continue; SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Sending BRST chan: %d\n", current->comm, channel)); rtn = scsi_try_bus_reset(chan_scmd); if (rtn == SUCCESS || rtn == FAST_IO_FAIL) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (channel == scmd_channel(scmd)) { if (rtn == FAST_IO_FAIL) scsi_eh_finish_cmd(scmd, done_q); else list_move_tail(&scmd->eh_entry, &check_list); } } } else { SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: BRST failed chan: %d\n", current->comm, channel)); } } return scsi_eh_test_devices(&check_list, work_q, done_q, 0); } /** * scsi_eh_host_reset - send a host reset * @shost: host to be reset. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ static int scsi_eh_host_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; LIST_HEAD(check_list); enum scsi_disposition rtn; if (!list_empty(work_q)) { scmd = list_entry(work_q->next, struct scsi_cmnd, eh_entry); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Sending HRST\n", current->comm)); rtn = scsi_try_host_reset(scmd); if (rtn == SUCCESS) { list_splice_init(work_q, &check_list); } else if (rtn == FAST_IO_FAIL) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { scsi_eh_finish_cmd(scmd, done_q); } } else { SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: HRST failed\n", current->comm)); } } return scsi_eh_test_devices(&check_list, work_q, done_q, 1); } /** * scsi_eh_offline_sdevs - offline scsi devices that fail to recover * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ static void scsi_eh_offline_sdevs(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; struct scsi_device *sdev; list_for_each_entry_safe(scmd, next, work_q, eh_entry) { sdev_printk(KERN_INFO, scmd->device, "Device offlined - " "not ready after error recovery\n"); sdev = scmd->device; mutex_lock(&sdev->state_mutex); scsi_device_set_state(sdev, SDEV_OFFLINE); mutex_unlock(&sdev->state_mutex); scsi_eh_finish_cmd(scmd, done_q); } return; } /** * scsi_noretry_cmd - determine if command should be failed fast * @scmd: SCSI cmd to examine. */ bool scsi_noretry_cmd(struct scsi_cmnd *scmd) { struct request *req = scsi_cmd_to_rq(scmd); switch (host_byte(scmd->result)) { case DID_OK: break; case DID_TIME_OUT: goto check_type; case DID_BUS_BUSY: return !!(req->cmd_flags & REQ_FAILFAST_TRANSPORT); case DID_PARITY: return !!(req->cmd_flags & REQ_FAILFAST_DEV); case DID_ERROR: if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT) return false; fallthrough; case DID_SOFT_ERROR: return !!(req->cmd_flags & REQ_FAILFAST_DRIVER); } /* Never retry commands aborted due to a duration limit timeout */ if (scsi_ml_byte(scmd->result) == SCSIML_STAT_DL_TIMEOUT) return true; if (!scsi_status_is_check_condition(scmd->result)) return false; check_type: /* * assume caller has checked sense and determined * the check condition was retryable. */ if (req->cmd_flags & REQ_FAILFAST_DEV || blk_rq_is_passthrough(req)) return true; return false; } /** * scsi_decide_disposition - Disposition a cmd on return from LLD. * @scmd: SCSI cmd to examine. * * Notes: * This is *only* called when we are examining the status after sending * out the actual data command. any commands that are queued for error * recovery (e.g. test_unit_ready) do *not* come through here. * * When this routine returns failed, it means the error handler thread * is woken. In cases where the error code indicates an error that * doesn't require the error handler read (i.e. we don't need to * abort/reset), this function should return SUCCESS. */ enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *scmd) { enum scsi_disposition rtn; /* * if the device is offline, then we clearly just pass the result back * up to the top level. */ if (!scsi_device_online(scmd->device)) { SCSI_LOG_ERROR_RECOVERY(5, scmd_printk(KERN_INFO, scmd, "%s: device offline - report as SUCCESS\n", __func__)); return SUCCESS; } /* * first check the host byte, to see if there is anything in there * that would indicate what we need to do. */ switch (host_byte(scmd->result)) { case DID_PASSTHROUGH: /* * no matter what, pass this through to the upper layer. * nuke this special code so that it looks like we are saying * did_ok. */ scmd->result &= 0xff00ffff; return SUCCESS; case DID_OK: /* * looks good. drop through, and check the next byte. */ break; case DID_ABORT: if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { set_host_byte(scmd, DID_TIME_OUT); return SUCCESS; } fallthrough; case DID_NO_CONNECT: case DID_BAD_TARGET: /* * note - this means that we just report the status back * to the top level driver, not that we actually think * that it indicates SUCCESS. */ return SUCCESS; case DID_SOFT_ERROR: /* * when the low level driver returns did_soft_error, * it is responsible for keeping an internal retry counter * in order to avoid endless loops (db) */ goto maybe_retry; case DID_IMM_RETRY: return NEEDS_RETRY; case DID_REQUEUE: return ADD_TO_MLQUEUE; case DID_TRANSPORT_DISRUPTED: /* * LLD/transport was disrupted during processing of the IO. * The transport class is now blocked/blocking, * and the transport will decide what to do with the IO * based on its timers and recovery capablilities if * there are enough retries. */ goto maybe_retry; case DID_TRANSPORT_FAILFAST: /* * The transport decided to failfast the IO (most likely * the fast io fail tmo fired), so send IO directly upwards. */ return SUCCESS; case DID_TRANSPORT_MARGINAL: /* * caller has decided not to do retries on * abort success, so send IO directly upwards */ return SUCCESS; case DID_ERROR: if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT) /* * execute reservation conflict processing code * lower down */ break; fallthrough; case DID_BUS_BUSY: case DID_PARITY: goto maybe_retry; case DID_TIME_OUT: /* * when we scan the bus, we get timeout messages for * these commands if there is no device available. * other hosts report did_no_connect for the same thing. */ if ((scmd->cmnd[0] == TEST_UNIT_READY || scmd->cmnd[0] == INQUIRY)) { return SUCCESS; } else { return FAILED; } case DID_RESET: return SUCCESS; default: return FAILED; } /* * check the status byte to see if this indicates anything special. */ switch (get_status_byte(scmd)) { case SAM_STAT_TASK_SET_FULL: scsi_handle_queue_full(scmd->device); /* * the case of trying to send too many commands to a * tagged queueing device. */ fallthrough; case SAM_STAT_BUSY: /* * device can't talk to us at the moment. Should only * occur (SAM-3) when the task queue is empty, so will cause * the empty queue handling to trigger a stall in the * device. */ return ADD_TO_MLQUEUE; case SAM_STAT_GOOD: if (scmd->cmnd[0] == REPORT_LUNS) scmd->device->sdev_target->expecting_lun_change = 0; scsi_handle_queue_ramp_up(scmd->device); if (scmd->sense_buffer && SCSI_SENSE_VALID(scmd)) /* * If we have sense data, call scsi_check_sense() in * order to set the correct SCSI ML byte (if any). * No point in checking the return value, since the * command has already completed successfully. */ scsi_check_sense(scmd); fallthrough; case SAM_STAT_COMMAND_TERMINATED: return SUCCESS; case SAM_STAT_TASK_ABORTED: goto maybe_retry; case SAM_STAT_CHECK_CONDITION: rtn = scsi_check_sense(scmd); if (rtn == NEEDS_RETRY) goto maybe_retry; /* if rtn == FAILED, we have no sense information; * returning FAILED will wake the error handler thread * to collect the sense and redo the decide * disposition */ return rtn; case SAM_STAT_CONDITION_MET: case SAM_STAT_INTERMEDIATE: case SAM_STAT_INTERMEDIATE_CONDITION_MET: case SAM_STAT_ACA_ACTIVE: /* * who knows? FIXME(eric) */ return SUCCESS; case SAM_STAT_RESERVATION_CONFLICT: sdev_printk(KERN_INFO, scmd->device, "reservation conflict\n"); set_scsi_ml_byte(scmd, SCSIML_STAT_RESV_CONFLICT); return SUCCESS; /* causes immediate i/o error */ } return FAILED; maybe_retry: /* we requeue for retry because the error was retryable, and * the request was not marked fast fail. Note that above, * even if the request is marked fast fail, we still requeue * for queue congestion conditions (QUEUE_FULL or BUSY) */ if (scsi_cmd_retry_allowed(scmd) && !scsi_noretry_cmd(scmd)) { return NEEDS_RETRY; } else { /* * no more retries - report this one back to upper level. */ return SUCCESS; } } static enum rq_end_io_ret eh_lock_door_done(struct request *req, blk_status_t status) { blk_mq_free_request(req); return RQ_END_IO_NONE; } /** * scsi_eh_lock_door - Prevent medium removal for the specified device * @sdev: SCSI device to prevent medium removal * * Locking: * We must be called from process context. * * Notes: * We queue up an asynchronous "ALLOW MEDIUM REMOVAL" request on the * head of the devices request queue, and continue. */ static void scsi_eh_lock_door(struct scsi_device *sdev) { struct scsi_cmnd *scmd; struct request *req; req = scsi_alloc_request(sdev->request_queue, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) return; scmd = blk_mq_rq_to_pdu(req); scmd->cmnd[0] = ALLOW_MEDIUM_REMOVAL; scmd->cmnd[1] = 0; scmd->cmnd[2] = 0; scmd->cmnd[3] = 0; scmd->cmnd[4] = SCSI_REMOVAL_PREVENT; scmd->cmnd[5] = 0; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); scmd->allowed = 5; req->rq_flags |= RQF_QUIET; req->timeout = 10 * HZ; req->end_io = eh_lock_door_done; blk_execute_rq_nowait(req, true); } /** * scsi_restart_operations - restart io operations to the specified host. * @shost: Host we are restarting. * * Notes: * When we entered the error handler, we blocked all further i/o to * this device. we need to 'reverse' this process. */ static void scsi_restart_operations(struct Scsi_Host *shost) { struct scsi_device *sdev; unsigned long flags; /* * If the door was locked, we need to insert a door lock request * onto the head of the SCSI request queue for the device. There * is no point trying to lock the door of an off-line device. */ shost_for_each_device(sdev, shost) { if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) { scsi_eh_lock_door(sdev); sdev->was_reset = 0; } } /* * next free up anything directly waiting upon the host. this * will be requests for character device operations, and also for * ioctls to queued block devices. */ SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "waking up host to restart\n")); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RUNNING)) if (scsi_host_set_state(shost, SHOST_CANCEL)) BUG_ON(scsi_host_set_state(shost, SHOST_DEL)); spin_unlock_irqrestore(shost->host_lock, flags); wake_up(&shost->host_wait); /* * finally we need to re-initiate requests that may be pending. we will * have had everything blocked while error handling is taking place, and * now that error recovery is done, we will need to ensure that these * requests are started. */ scsi_run_host_queues(shost); /* * if eh is active and host_eh_scheduled is pending we need to re-run * recovery. we do this check after scsi_run_host_queues() to allow * everything pent up since the last eh run a chance to make forward * progress before we sync again. Either we'll immediately re-run * recovery or scsi_device_unbusy() will wake us again when these * pending commands complete. */ spin_lock_irqsave(shost->host_lock, flags); if (shost->host_eh_scheduled) if (scsi_host_set_state(shost, SHOST_RECOVERY)) WARN_ON(scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)); spin_unlock_irqrestore(shost->host_lock, flags); } /** * scsi_eh_ready_devs - check device ready state and recover if not. * @shost: host to be recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ void scsi_eh_ready_devs(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { if (!scsi_eh_stu(shost, work_q, done_q)) if (!scsi_eh_bus_device_reset(shost, work_q, done_q)) if (!scsi_eh_target_reset(shost, work_q, done_q)) if (!scsi_eh_bus_reset(shost, work_q, done_q)) if (!scsi_eh_host_reset(shost, work_q, done_q)) scsi_eh_offline_sdevs(work_q, done_q); } EXPORT_SYMBOL_GPL(scsi_eh_ready_devs); /** * scsi_eh_flush_done_q - finish processed commands or retry them. * @done_q: list_head of processed commands. */ void scsi_eh_flush_done_q(struct list_head *done_q) { struct scsi_cmnd *scmd, *next; list_for_each_entry_safe(scmd, next, done_q, eh_entry) { struct scsi_device *sdev = scmd->device; list_del_init(&scmd->eh_entry); if (scsi_device_online(sdev) && !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) && scsi_eh_should_retry_cmd(scmd)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: flush retry cmd\n", current->comm)); scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY); blk_mq_kick_requeue_list(sdev->request_queue); } else { /* * If just we got sense for the device (called * scsi_eh_get_sense), scmd->result is already * set, do not set DID_TIME_OUT. */ if (!scmd->result && !(scmd->flags & SCMD_FORCE_EH_SUCCESS)) scmd->result |= (DID_TIME_OUT << 16); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: flush finish cmd\n", current->comm)); scsi_finish_command(scmd); } } } EXPORT_SYMBOL(scsi_eh_flush_done_q); /** * scsi_unjam_host - Attempt to fix a host which has a cmd that failed. * @shost: Host to unjam. * * Notes: * When we come in here, we *know* that all commands on the bus have * either completed, failed or timed out. we also know that no further * commands are being sent to the host, so things are relatively quiet * and we have freedom to fiddle with things as we wish. * * This is only the *default* implementation. it is possible for * individual drivers to supply their own version of this function, and * if the maintainer wishes to do this, it is strongly suggested that * this function be taken as a template and modified. this function * was designed to correctly handle problems for about 95% of the * different cases out there, and it should always provide at least a * reasonable amount of error recovery. * * Any command marked 'failed' or 'timeout' must eventually have * scsi_finish_cmd() called for it. we do all of the retry stuff * here, so when we restart the host after we return it should have an * empty queue. */ static void scsi_unjam_host(struct Scsi_Host *shost) { unsigned long flags; LIST_HEAD(eh_work_q); LIST_HEAD(eh_done_q); spin_lock_irqsave(shost->host_lock, flags); list_splice_init(&shost->eh_cmd_q, &eh_work_q); spin_unlock_irqrestore(shost->host_lock, flags); SCSI_LOG_ERROR_RECOVERY(1, scsi_eh_prt_fail_stats(shost, &eh_work_q)); if (!scsi_eh_get_sense(&eh_work_q, &eh_done_q)) scsi_eh_ready_devs(shost, &eh_work_q, &eh_done_q); spin_lock_irqsave(shost->host_lock, flags); if (shost->eh_deadline != -1) shost->last_reset = 0; spin_unlock_irqrestore(shost->host_lock, flags); scsi_eh_flush_done_q(&eh_done_q); } /** * scsi_error_handler - SCSI error handler thread * @data: Host for which we are running. * * Notes: * This is the main error handling loop. This is run as a kernel thread * for every SCSI host and handles all error handling activity. */ int scsi_error_handler(void *data) { struct Scsi_Host *shost = data; /* * We use TASK_INTERRUPTIBLE so that the thread is not * counted against the load average as a running process. * We never actually get interrupted because kthread_run * disables signal delivery for the created thread. */ while (true) { /* * The sequence in kthread_stop() sets the stop flag first * then wakes the process. To avoid missed wakeups, the task * should always be in a non running state before the stop * flag is checked */ set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) break; if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) || shost->host_failed != scsi_host_busy(shost)) { SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "scsi_eh_%d: sleeping\n", shost->host_no)); schedule(); continue; } __set_current_state(TASK_RUNNING); SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "scsi_eh_%d: waking up %d/%d/%d\n", shost->host_no, shost->host_eh_scheduled, shost->host_failed, scsi_host_busy(shost))); /* * We have a host that is failing for some reason. Figure out * what we need to do to get it up and online again (if we can). * If we fail, we end up taking the thing offline. */ if (!shost->eh_noresume && scsi_autopm_get_host(shost) != 0) { SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_ERR, shost, "scsi_eh_%d: unable to autoresume\n", shost->host_no)); continue; } if (shost->transportt->eh_strategy_handler) shost->transportt->eh_strategy_handler(shost); else scsi_unjam_host(shost); /* All scmds have been handled */ shost->host_failed = 0; /* * Note - if the above fails completely, the action is to take * individual devices offline and flush the queue of any * outstanding requests that may have been pending. When we * restart, we restart any I/O to any other devices on the bus * which are still online. */ scsi_restart_operations(shost); if (!shost->eh_noresume) scsi_autopm_put_host(shost); } __set_current_state(TASK_RUNNING); SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "Error handler scsi_eh_%d exiting\n", shost->host_no)); shost->ehandler = NULL; return 0; } /** * scsi_report_bus_reset() - report bus reset observed * * Utility function used by low-level drivers to report that * they have observed a bus reset on the bus being handled. * * @shost: Host in question * @channel: channel on which reset was observed. * * Returns: Nothing * * Lock status: Host lock must be held. * * Notes: This only needs to be called if the reset is one which * originates from an unknown location. Resets originated * by the mid-level itself don't need to call this, but there * should be no harm. * * The main purpose of this is to make sure that a CHECK_CONDITION * is properly treated. */ void scsi_report_bus_reset(struct Scsi_Host *shost, int channel) { struct scsi_device *sdev; __shost_for_each_device(sdev, shost) { if (channel == sdev_channel(sdev)) __scsi_report_device_reset(sdev, NULL); } } EXPORT_SYMBOL(scsi_report_bus_reset); /** * scsi_report_device_reset() - report device reset observed * * Utility function used by low-level drivers to report that * they have observed a device reset on the device being handled. * * @shost: Host in question * @channel: channel on which reset was observed * @target: target on which reset was observed * * Returns: Nothing * * Lock status: Host lock must be held * * Notes: This only needs to be called if the reset is one which * originates from an unknown location. Resets originated * by the mid-level itself don't need to call this, but there * should be no harm. * * The main purpose of this is to make sure that a CHECK_CONDITION * is properly treated. */ void scsi_report_device_reset(struct Scsi_Host *shost, int channel, int target) { struct scsi_device *sdev; __shost_for_each_device(sdev, shost) { if (channel == sdev_channel(sdev) && target == sdev_id(sdev)) __scsi_report_device_reset(sdev, NULL); } } EXPORT_SYMBOL(scsi_report_device_reset); /** * scsi_ioctl_reset: explicitly reset a host/bus/target/device * @dev: scsi_device to operate on * @arg: reset type (see sg.h) */ int scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) { struct scsi_cmnd *scmd; struct Scsi_Host *shost = dev->host; struct request *rq; unsigned long flags; int error = 0, val; enum scsi_disposition rtn; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; error = get_user(val, arg); if (error) return error; if (scsi_autopm_get_host(shost) < 0) return -EIO; error = -EIO; rq = kzalloc(sizeof(struct request) + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size, GFP_KERNEL); if (!rq) goto out_put_autopm_host; blk_rq_init(NULL, rq); scmd = (struct scsi_cmnd *)(rq + 1); scsi_init_command(dev, scmd); scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL; scmd->flags |= SCMD_LAST; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->cmd_len = 0; scmd->sc_data_direction = DMA_BIDIRECTIONAL; spin_lock_irqsave(shost->host_lock, flags); shost->tmf_in_progress = 1; spin_unlock_irqrestore(shost->host_lock, flags); switch (val & ~SG_SCSI_RESET_NO_ESCALATE) { case SG_SCSI_RESET_NOTHING: rtn = SUCCESS; break; case SG_SCSI_RESET_DEVICE: rtn = scsi_try_bus_device_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; fallthrough; case SG_SCSI_RESET_TARGET: rtn = scsi_try_target_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; fallthrough; case SG_SCSI_RESET_BUS: rtn = scsi_try_bus_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; fallthrough; case SG_SCSI_RESET_HOST: rtn = scsi_try_host_reset(scmd); if (rtn == SUCCESS) break; fallthrough; default: rtn = FAILED; break; } error = (rtn == SUCCESS) ? 0 : -EIO; spin_lock_irqsave(shost->host_lock, flags); shost->tmf_in_progress = 0; spin_unlock_irqrestore(shost->host_lock, flags); /* * be sure to wake up anyone who was sleeping or had their queue * suspended while we performed the TMF. */ SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "waking up host to restart after TMF\n")); wake_up(&shost->host_wait); scsi_run_host_queues(shost); kfree(rq); out_put_autopm_host: scsi_autopm_put_host(shost); return error; } bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd, struct scsi_sense_hdr *sshdr) { return scsi_normalize_sense(cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE, sshdr); } EXPORT_SYMBOL(scsi_command_normalize_sense); /** * scsi_get_sense_info_fld - get information field from sense data (either fixed or descriptor format) * @sense_buffer: byte array of sense data * @sb_len: number of valid bytes in sense_buffer * @info_out: pointer to 64 integer where 8 or 4 byte information * field will be placed if found. * * Return value: * true if information field found, false if not found. */ bool scsi_get_sense_info_fld(const u8 *sense_buffer, int sb_len, u64 *info_out) { const u8 * ucp; if (sb_len < 7) return false; switch (sense_buffer[0] & 0x7f) { case 0x70: case 0x71: if (sense_buffer[0] & 0x80) { *info_out = get_unaligned_be32(&sense_buffer[3]); return true; } return false; case 0x72: case 0x73: ucp = scsi_sense_desc_find(sense_buffer, sb_len, 0 /* info desc */); if (ucp && (0xa == ucp[1])) { *info_out = get_unaligned_be64(&ucp[4]); return true; } return false; default: return false; } } EXPORT_SYMBOL(scsi_get_sense_info_fld); |
| 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Initialization routines * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/device.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/ctype.h> #include <linux/pm.h> #include <linux/debugfs.h> #include <linux/completion.h> #include <linux/interrupt.h> #include <sound/core.h> #include <sound/control.h> #include <sound/info.h> /* monitor files for graceful shutdown (hotplug) */ struct snd_monitor_file { struct file *file; const struct file_operations *disconnected_f_op; struct list_head shutdown_list; /* still need to shutdown */ struct list_head list; /* link of monitor files */ }; static DEFINE_SPINLOCK(shutdown_lock); static LIST_HEAD(shutdown_files); static const struct file_operations snd_shutdown_f_ops; /* locked for registering/using */ static DECLARE_BITMAP(snd_cards_lock, SNDRV_CARDS); static struct snd_card *snd_cards[SNDRV_CARDS]; static DEFINE_MUTEX(snd_card_mutex); static char *slots[SNDRV_CARDS]; module_param_array(slots, charp, NULL, 0444); MODULE_PARM_DESC(slots, "Module names assigned to the slots."); /* return non-zero if the given index is reserved for the given * module via slots option */ static int module_slot_match(struct module *module, int idx) { int match = 1; #ifdef CONFIG_MODULES const char *s1, *s2; if (!module || !*module->name || !slots[idx]) return 0; s1 = module->name; s2 = slots[idx]; if (*s2 == '!') { match = 0; /* negative match */ s2++; } /* compare module name strings * hyphens are handled as equivalent with underscore */ for (;;) { char c1 = *s1++; char c2 = *s2++; if (c1 == '-') c1 = '_'; if (c2 == '-') c2 = '_'; if (c1 != c2) return !match; if (!c1) break; } #endif /* CONFIG_MODULES */ return match; } #if IS_ENABLED(CONFIG_SND_MIXER_OSS) int (*snd_mixer_oss_notify_callback)(struct snd_card *card, int free_flag); EXPORT_SYMBOL(snd_mixer_oss_notify_callback); #endif static int check_empty_slot(struct module *module, int slot) { return !slots[slot] || !*slots[slot]; } /* return an empty slot number (>= 0) found in the given bitmask @mask. * @mask == -1 == 0xffffffff means: take any free slot up to 32 * when no slot is available, return the original @mask as is. */ static int get_slot_from_bitmask(int mask, int (*check)(struct module *, int), struct module *module) { int slot; for (slot = 0; slot < SNDRV_CARDS; slot++) { if (slot < 32 && !(mask & (1U << slot))) continue; if (!test_bit(slot, snd_cards_lock)) { if (check(module, slot)) return slot; /* found */ } } return mask; /* unchanged */ } /* the default release callback set in snd_device_alloc() */ static void default_release_alloc(struct device *dev) { kfree(dev); } /** * snd_device_alloc - Allocate and initialize struct device for sound devices * @dev_p: pointer to store the allocated device * @card: card to assign, optional * * For releasing the allocated device, call put_device(). */ int snd_device_alloc(struct device **dev_p, struct snd_card *card) { struct device *dev; *dev_p = NULL; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; device_initialize(dev); if (card) dev->parent = &card->card_dev; dev->class = &sound_class; dev->release = default_release_alloc; *dev_p = dev; return 0; } EXPORT_SYMBOL_GPL(snd_device_alloc); static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size); static int snd_card_do_free(struct snd_card *card); static const struct attribute_group card_dev_attr_group; static void release_card_device(struct device *dev) { snd_card_do_free(dev_to_snd_card(dev)); } /** * snd_card_new - create and initialize a soundcard structure * @parent: the parent device object * @idx: card index (address) [0 ... (SNDRV_CARDS-1)] * @xid: card identification (ASCII string) * @module: top level module for locking * @extra_size: allocate this extra size after the main soundcard structure * @card_ret: the pointer to store the created card instance * * The function allocates snd_card instance via kzalloc with the given * space for the driver to use freely. The allocated struct is stored * in the given card_ret pointer. * * Return: Zero if successful or a negative error code. */ int snd_card_new(struct device *parent, int idx, const char *xid, struct module *module, int extra_size, struct snd_card **card_ret) { struct snd_card *card; int err; if (snd_BUG_ON(!card_ret)) return -EINVAL; *card_ret = NULL; if (extra_size < 0) extra_size = 0; card = kzalloc(sizeof(*card) + extra_size, GFP_KERNEL); if (!card) return -ENOMEM; err = snd_card_init(card, parent, idx, xid, module, extra_size); if (err < 0) return err; /* card is freed by error handler */ *card_ret = card; return 0; } EXPORT_SYMBOL(snd_card_new); static void __snd_card_release(struct device *dev, void *data) { snd_card_free(data); } /** * snd_devm_card_new - managed snd_card object creation * @parent: the parent device object * @idx: card index (address) [0 ... (SNDRV_CARDS-1)] * @xid: card identification (ASCII string) * @module: top level module for locking * @extra_size: allocate this extra size after the main soundcard structure * @card_ret: the pointer to store the created card instance * * This function works like snd_card_new() but manages the allocated resource * via devres, i.e. you don't need to free explicitly. * * When a snd_card object is created with this function and registered via * snd_card_register(), the very first devres action to call snd_card_free() * is added automatically. In that way, the resource disconnection is assured * at first, then released in the expected order. * * If an error happens at the probe before snd_card_register() is called and * there have been other devres resources, you'd need to free the card manually * via snd_card_free() call in the error; otherwise it may lead to UAF due to * devres call orders. You can use snd_card_free_on_error() helper for * handling it more easily. * * Return: zero if successful, or a negative error code */ int snd_devm_card_new(struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size, struct snd_card **card_ret) { struct snd_card *card; int err; *card_ret = NULL; card = devres_alloc(__snd_card_release, sizeof(*card) + extra_size, GFP_KERNEL); if (!card) return -ENOMEM; card->managed = true; err = snd_card_init(card, parent, idx, xid, module, extra_size); if (err < 0) { devres_free(card); /* in managed mode, we need to free manually */ return err; } devres_add(parent, card); *card_ret = card; return 0; } EXPORT_SYMBOL_GPL(snd_devm_card_new); /** * snd_card_free_on_error - a small helper for handling devm probe errors * @dev: the managed device object * @ret: the return code from the probe callback * * This function handles the explicit snd_card_free() call at the error from * the probe callback. It's just a small helper for simplifying the error * handling with the managed devices. * * Return: zero if successful, or a negative error code */ int snd_card_free_on_error(struct device *dev, int ret) { struct snd_card *card; if (!ret) return 0; card = devres_find(dev, __snd_card_release, NULL, NULL); if (card) snd_card_free(card); return ret; } EXPORT_SYMBOL_GPL(snd_card_free_on_error); static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size) { int err; if (extra_size > 0) card->private_data = (char *)card + sizeof(struct snd_card); if (xid) strscpy(card->id, xid, sizeof(card->id)); err = 0; scoped_guard(mutex, &snd_card_mutex) { if (idx < 0) /* first check the matching module-name slot */ idx = get_slot_from_bitmask(idx, module_slot_match, module); if (idx < 0) /* if not matched, assign an empty slot */ idx = get_slot_from_bitmask(idx, check_empty_slot, module); if (idx < 0) err = -ENODEV; else if (idx < snd_ecards_limit) { if (test_bit(idx, snd_cards_lock)) err = -EBUSY; /* invalid */ } else if (idx >= SNDRV_CARDS) err = -ENODEV; if (!err) { set_bit(idx, snd_cards_lock); /* lock it */ if (idx >= snd_ecards_limit) snd_ecards_limit = idx + 1; /* increase the limit */ } } if (err < 0) { dev_err(parent, "cannot find the slot for index %d (range 0-%i), error: %d\n", idx, snd_ecards_limit - 1, err); if (!card->managed) kfree(card); /* manually free here, as no destructor called */ return err; } card->dev = parent; card->number = idx; WARN_ON(IS_MODULE(CONFIG_SND) && !module); card->module = module; INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->controls_rwlock); INIT_LIST_HEAD(&card->controls); INIT_LIST_HEAD(&card->ctl_files); #ifdef CONFIG_SND_CTL_FAST_LOOKUP xa_init(&card->ctl_numids); xa_init(&card->ctl_hash); #endif spin_lock_init(&card->files_lock); INIT_LIST_HEAD(&card->files_list); mutex_init(&card->memory_mutex); #ifdef CONFIG_PM init_waitqueue_head(&card->power_sleep); init_waitqueue_head(&card->power_ref_sleep); atomic_set(&card->power_ref, 0); #endif init_waitqueue_head(&card->remove_sleep); card->sync_irq = -1; device_initialize(&card->card_dev); card->card_dev.parent = parent; card->card_dev.class = &sound_class; card->card_dev.release = release_card_device; card->card_dev.groups = card->dev_groups; card->dev_groups[0] = &card_dev_attr_group; err = kobject_set_name(&card->card_dev.kobj, "card%d", idx); if (err < 0) goto __error; snprintf(card->irq_descr, sizeof(card->irq_descr), "%s:%s", dev_driver_string(card->dev), dev_name(&card->card_dev)); /* the control interface cannot be accessed from the user space until */ /* snd_cards_bitmask and snd_cards are set with snd_card_register */ err = snd_ctl_create(card); if (err < 0) { dev_err(parent, "unable to register control minors\n"); goto __error; } err = snd_info_card_create(card); if (err < 0) { dev_err(parent, "unable to create card info\n"); goto __error_ctl; } #ifdef CONFIG_SND_DEBUG card->debugfs_root = debugfs_create_dir(dev_name(&card->card_dev), sound_debugfs_root); #endif return 0; __error_ctl: snd_device_free_all(card); __error: put_device(&card->card_dev); return err; } /** * snd_card_ref - Get the card object from the index * @idx: the card index * * Returns a card object corresponding to the given index or NULL if not found. * Release the object via snd_card_unref(). * * Return: a card object or NULL */ struct snd_card *snd_card_ref(int idx) { struct snd_card *card; guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) get_device(&card->card_dev); return card; } EXPORT_SYMBOL_GPL(snd_card_ref); /* return non-zero if a card is already locked */ int snd_card_locked(int card) { guard(mutex)(&snd_card_mutex); return test_bit(card, snd_cards_lock); } static loff_t snd_disconnect_llseek(struct file *file, loff_t offset, int orig) { return -ENODEV; } static ssize_t snd_disconnect_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { return -ENODEV; } static ssize_t snd_disconnect_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { return -ENODEV; } static int snd_disconnect_release(struct inode *inode, struct file *file) { struct snd_monitor_file *df = NULL, *_df; scoped_guard(spinlock, &shutdown_lock) { list_for_each_entry(_df, &shutdown_files, shutdown_list) { if (_df->file == file) { df = _df; list_del_init(&df->shutdown_list); break; } } } if (likely(df)) { if ((file->f_flags & FASYNC) && df->disconnected_f_op->fasync) df->disconnected_f_op->fasync(-1, file, 0); return df->disconnected_f_op->release(inode, file); } panic("%s(%p, %p) failed!", __func__, inode, file); } static __poll_t snd_disconnect_poll(struct file * file, poll_table * wait) { return EPOLLERR | EPOLLNVAL; } static long snd_disconnect_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -ENODEV; } static int snd_disconnect_mmap(struct file *file, struct vm_area_struct *vma) { return -ENODEV; } static int snd_disconnect_fasync(int fd, struct file *file, int on) { return -ENODEV; } static const struct file_operations snd_shutdown_f_ops = { .owner = THIS_MODULE, .llseek = snd_disconnect_llseek, .read = snd_disconnect_read, .write = snd_disconnect_write, .release = snd_disconnect_release, .poll = snd_disconnect_poll, .unlocked_ioctl = snd_disconnect_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = snd_disconnect_ioctl, #endif .mmap = snd_disconnect_mmap, .fasync = snd_disconnect_fasync }; /** * snd_card_disconnect - disconnect all APIs from the file-operations (user space) * @card: soundcard structure * * Disconnects all APIs from the file-operations (user space). * * Return: Zero, otherwise a negative error code. * * Note: The current implementation replaces all active file->f_op with special * dummy file operations (they do nothing except release). */ void snd_card_disconnect(struct snd_card *card) { struct snd_monitor_file *mfile; if (!card) return; scoped_guard(spinlock, &card->files_lock) { if (card->shutdown) return; card->shutdown = 1; /* replace file->f_op with special dummy operations */ list_for_each_entry(mfile, &card->files_list, list) { /* it's critical part, use endless loop */ /* we have no room to fail */ mfile->disconnected_f_op = mfile->file->f_op; scoped_guard(spinlock, &shutdown_lock) list_add(&mfile->shutdown_list, &shutdown_files); mfile->file->f_op = &snd_shutdown_f_ops; fops_get(mfile->file->f_op); } } #ifdef CONFIG_PM /* wake up sleepers here before other callbacks for avoiding potential * deadlocks with other locks (e.g. in kctls); * then this notifies the shutdown and sleepers would abort immediately */ wake_up_all(&card->power_sleep); #endif /* notify all connected devices about disconnection */ /* at this point, they cannot respond to any calls except release() */ #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_DISCONNECT); #endif /* notify all devices that we are disconnected */ snd_device_disconnect_all(card); if (card->sync_irq > 0) synchronize_irq(card->sync_irq); snd_info_card_disconnect(card); #ifdef CONFIG_SND_DEBUG debugfs_remove(card->debugfs_root); card->debugfs_root = NULL; #endif if (card->registered) { device_del(&card->card_dev); card->registered = false; } /* disable fops (user space) operations for ALSA API */ scoped_guard(mutex, &snd_card_mutex) { snd_cards[card->number] = NULL; clear_bit(card->number, snd_cards_lock); } snd_power_sync_ref(card); } EXPORT_SYMBOL(snd_card_disconnect); /** * snd_card_disconnect_sync - disconnect card and wait until files get closed * @card: card object to disconnect * * This calls snd_card_disconnect() for disconnecting all belonging components * and waits until all pending files get closed. * It assures that all accesses from user-space finished so that the driver * can release its resources gracefully. */ void snd_card_disconnect_sync(struct snd_card *card) { snd_card_disconnect(card); guard(spinlock_irq)(&card->files_lock); wait_event_lock_irq(card->remove_sleep, list_empty(&card->files_list), card->files_lock); } EXPORT_SYMBOL_GPL(snd_card_disconnect_sync); static int snd_card_do_free(struct snd_card *card) { card->releasing = true; #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_FREE); #endif snd_device_free_all(card); if (card->private_free) card->private_free(card); if (snd_info_card_free(card) < 0) { dev_warn(card->dev, "unable to free card info\n"); /* Not fatal error */ } if (card->release_completion) complete(card->release_completion); if (!card->managed) kfree(card); return 0; } /** * snd_card_free_when_closed - Disconnect the card, free it later eventually * @card: soundcard structure * * Unlike snd_card_free(), this function doesn't try to release the card * resource immediately, but tries to disconnect at first. When the card * is still in use, the function returns before freeing the resources. * The card resources will be freed when the refcount gets to zero. * * Return: zero if successful, or a negative error code */ void snd_card_free_when_closed(struct snd_card *card) { if (!card) return; snd_card_disconnect(card); put_device(&card->card_dev); return; } EXPORT_SYMBOL(snd_card_free_when_closed); /** * snd_card_free - frees given soundcard structure * @card: soundcard structure * * This function releases the soundcard structure and the all assigned * devices automatically. That is, you don't have to release the devices * by yourself. * * This function waits until the all resources are properly released. * * Return: Zero. Frees all associated devices and frees the control * interface associated to given soundcard. */ void snd_card_free(struct snd_card *card) { DECLARE_COMPLETION_ONSTACK(released); /* The call of snd_card_free() is allowed from various code paths; * a manual call from the driver and the call via devres_free, and * we need to avoid double-free. Moreover, the release via devres * may call snd_card_free() twice due to its nature, we need to have * the check here at the beginning. */ if (card->releasing) return; card->release_completion = &released; snd_card_free_when_closed(card); /* wait, until all devices are ready for the free operation */ wait_for_completion(&released); } EXPORT_SYMBOL(snd_card_free); /* check, if the character is in the valid ASCII range */ static inline bool safe_ascii_char(char c) { return isascii(c) && isalnum(c); } /* retrieve the last word of shortname or longname */ static const char *retrieve_id_from_card_name(const char *name) { const char *spos = name; while (*name) { if (isspace(*name) && safe_ascii_char(name[1])) spos = name + 1; name++; } return spos; } /* return true if the given id string doesn't conflict any other card ids */ static bool card_id_ok(struct snd_card *card, const char *id) { int i; if (!snd_info_check_reserved_words(id)) return false; for (i = 0; i < snd_ecards_limit; i++) { if (snd_cards[i] && snd_cards[i] != card && !strcmp(snd_cards[i]->id, id)) return false; } return true; } /* copy to card->id only with valid letters from nid */ static void copy_valid_id_string(struct snd_card *card, const char *src, const char *nid) { char *id = card->id; while (*nid && !safe_ascii_char(*nid)) nid++; if (isdigit(*nid)) *id++ = isalpha(*src) ? *src : 'D'; while (*nid && (size_t)(id - card->id) < sizeof(card->id) - 1) { if (safe_ascii_char(*nid)) *id++ = *nid; nid++; } *id = 0; } /* Set card->id from the given string * If the string conflicts with other ids, add a suffix to make it unique. */ static void snd_card_set_id_no_lock(struct snd_card *card, const char *src, const char *nid) { int len, loops; bool is_default = false; char *id; copy_valid_id_string(card, src, nid); id = card->id; again: /* use "Default" for obviously invalid strings * ("card" conflicts with proc directories) */ if (!*id || !strncmp(id, "card", 4)) { strcpy(id, "Default"); is_default = true; } len = strlen(id); for (loops = 0; loops < SNDRV_CARDS; loops++) { char *spos; char sfxstr[5]; /* "_012" */ int sfxlen; if (card_id_ok(card, id)) return; /* OK */ /* Add _XYZ suffix */ sprintf(sfxstr, "_%X", loops + 1); sfxlen = strlen(sfxstr); if (len + sfxlen >= sizeof(card->id)) spos = id + sizeof(card->id) - sfxlen - 1; else spos = id + len; strcpy(spos, sfxstr); } /* fallback to the default id */ if (!is_default) { *id = 0; goto again; } /* last resort... */ dev_err(card->dev, "unable to set card id (%s)\n", id); if (card->proc_root->name) strscpy(card->id, card->proc_root->name, sizeof(card->id)); } /** * snd_card_set_id - set card identification name * @card: soundcard structure * @nid: new identification string * * This function sets the card identification and checks for name * collisions. */ void snd_card_set_id(struct snd_card *card, const char *nid) { /* check if user specified own card->id */ if (card->id[0] != '\0') return; guard(mutex)(&snd_card_mutex); snd_card_set_id_no_lock(card, nid, nid); } EXPORT_SYMBOL(snd_card_set_id); static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = container_of(dev, struct snd_card, card_dev); return sysfs_emit(buf, "%s\n", card->id); } static ssize_t id_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct snd_card *card = container_of(dev, struct snd_card, card_dev); char buf1[sizeof(card->id)]; size_t copy = count > sizeof(card->id) - 1 ? sizeof(card->id) - 1 : count; size_t idx; int c; for (idx = 0; idx < copy; idx++) { c = buf[idx]; if (!safe_ascii_char(c) && c != '_' && c != '-') return -EINVAL; } memcpy(buf1, buf, copy); buf1[copy] = '\0'; guard(mutex)(&snd_card_mutex); if (!card_id_ok(NULL, buf1)) return -EEXIST; strcpy(card->id, buf1); snd_info_card_id_change(card); return count; } static DEVICE_ATTR_RW(id); static ssize_t number_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = container_of(dev, struct snd_card, card_dev); return sysfs_emit(buf, "%i\n", card->number); } static DEVICE_ATTR_RO(number); static struct attribute *card_dev_attrs[] = { &dev_attr_id.attr, &dev_attr_number.attr, NULL }; static const struct attribute_group card_dev_attr_group = { .attrs = card_dev_attrs, }; /** * snd_card_add_dev_attr - Append a new sysfs attribute group to card * @card: card instance * @group: attribute group to append * * Return: zero if successful, or a negative error code */ int snd_card_add_dev_attr(struct snd_card *card, const struct attribute_group *group) { int i; /* loop for (arraysize-1) here to keep NULL at the last entry */ for (i = 0; i < ARRAY_SIZE(card->dev_groups) - 1; i++) { if (!card->dev_groups[i]) { card->dev_groups[i] = group; return 0; } } dev_err(card->dev, "Too many groups assigned\n"); return -ENOSPC; } EXPORT_SYMBOL_GPL(snd_card_add_dev_attr); static void trigger_card_free(void *data) { snd_card_free(data); } /** * snd_card_register - register the soundcard * @card: soundcard structure * * This function registers all the devices assigned to the soundcard. * Until calling this, the ALSA control interface is blocked from the * external accesses. Thus, you should call this function at the end * of the initialization of the card. * * Return: Zero otherwise a negative error code if the registration failed. */ int snd_card_register(struct snd_card *card) { int err; if (snd_BUG_ON(!card)) return -EINVAL; if (!card->registered) { err = device_add(&card->card_dev); if (err < 0) return err; card->registered = true; } else { if (card->managed) devm_remove_action(card->dev, trigger_card_free, card); } if (card->managed) { err = devm_add_action(card->dev, trigger_card_free, card); if (err < 0) return err; } err = snd_device_register_all(card); if (err < 0) return err; scoped_guard(mutex, &snd_card_mutex) { if (snd_cards[card->number]) { /* already registered */ return snd_info_card_register(card); /* register pending info */ } if (*card->id) { /* make a unique id name from the given string */ char tmpid[sizeof(card->id)]; memcpy(tmpid, card->id, sizeof(card->id)); snd_card_set_id_no_lock(card, tmpid, tmpid); } else { /* create an id from either shortname or longname */ const char *src; src = *card->shortname ? card->shortname : card->longname; snd_card_set_id_no_lock(card, src, retrieve_id_from_card_name(src)); } snd_cards[card->number] = card; } err = snd_info_card_register(card); if (err < 0) return err; #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_REGISTER); #endif return 0; } EXPORT_SYMBOL(snd_card_register); #ifdef CONFIG_SND_PROC_FS static void snd_card_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int idx, count; struct snd_card *card; for (idx = count = 0; idx < SNDRV_CARDS; idx++) { guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) { count++; snd_iprintf(buffer, "%2i [%-15s]: %s - %s\n", idx, card->id, card->driver, card->shortname); snd_iprintf(buffer, " %s\n", card->longname); } } if (!count) snd_iprintf(buffer, "--- no soundcards ---\n"); } #ifdef CONFIG_SND_OSSEMUL void snd_card_info_read_oss(struct snd_info_buffer *buffer) { int idx, count; struct snd_card *card; for (idx = count = 0; idx < SNDRV_CARDS; idx++) { guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) { count++; snd_iprintf(buffer, "%s\n", card->longname); } } if (!count) { snd_iprintf(buffer, "--- no soundcards ---\n"); } } #endif #ifdef CONFIG_MODULES static void snd_card_module_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int idx; struct snd_card *card; for (idx = 0; idx < SNDRV_CARDS; idx++) { guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) snd_iprintf(buffer, "%2i %s\n", idx, card->module->name); } } #endif int __init snd_card_info_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "cards", NULL); if (! entry) return -ENOMEM; entry->c.text.read = snd_card_info_read; if (snd_info_register(entry) < 0) return -ENOMEM; /* freed in error path */ #ifdef CONFIG_MODULES entry = snd_info_create_module_entry(THIS_MODULE, "modules", NULL); if (!entry) return -ENOMEM; entry->c.text.read = snd_card_module_info_read; if (snd_info_register(entry) < 0) return -ENOMEM; /* freed in error path */ #endif return 0; } #endif /* CONFIG_SND_PROC_FS */ /** * snd_component_add - add a component string * @card: soundcard structure * @component: the component id string * * This function adds the component id string to the supported list. * The component can be referred from the alsa-lib. * * Return: Zero otherwise a negative error code. */ int snd_component_add(struct snd_card *card, const char *component) { char *ptr; int len = strlen(component); ptr = strstr(card->components, component); if (ptr != NULL) { if (ptr[len] == '\0' || ptr[len] == ' ') /* already there */ return 1; } if (strlen(card->components) + 1 + len + 1 > sizeof(card->components)) { snd_BUG(); return -ENOMEM; } if (card->components[0] != '\0') strcat(card->components, " "); strcat(card->components, component); return 0; } EXPORT_SYMBOL(snd_component_add); /** * snd_card_file_add - add the file to the file list of the card * @card: soundcard structure * @file: file pointer * * This function adds the file to the file linked-list of the card. * This linked-list is used to keep tracking the connection state, * and to avoid the release of busy resources by hotplug. * * Return: zero or a negative error code. */ int snd_card_file_add(struct snd_card *card, struct file *file) { struct snd_monitor_file *mfile; mfile = kmalloc(sizeof(*mfile), GFP_KERNEL); if (mfile == NULL) return -ENOMEM; mfile->file = file; mfile->disconnected_f_op = NULL; INIT_LIST_HEAD(&mfile->shutdown_list); guard(spinlock)(&card->files_lock); if (card->shutdown) { kfree(mfile); return -ENODEV; } list_add(&mfile->list, &card->files_list); get_device(&card->card_dev); return 0; } EXPORT_SYMBOL(snd_card_file_add); /** * snd_card_file_remove - remove the file from the file list * @card: soundcard structure * @file: file pointer * * This function removes the file formerly added to the card via * snd_card_file_add() function. * If all files are removed and snd_card_free_when_closed() was * called beforehand, it processes the pending release of * resources. * * Return: Zero or a negative error code. */ int snd_card_file_remove(struct snd_card *card, struct file *file) { struct snd_monitor_file *mfile, *found = NULL; scoped_guard(spinlock, &card->files_lock) { list_for_each_entry(mfile, &card->files_list, list) { if (mfile->file == file) { list_del(&mfile->list); scoped_guard(spinlock, &shutdown_lock) list_del(&mfile->shutdown_list); if (mfile->disconnected_f_op) fops_put(mfile->disconnected_f_op); found = mfile; break; } } if (list_empty(&card->files_list)) wake_up_all(&card->remove_sleep); } if (!found) { dev_err(card->dev, "card file remove problem (%p)\n", file); return -ENOENT; } kfree(found); put_device(&card->card_dev); return 0; } EXPORT_SYMBOL(snd_card_file_remove); #ifdef CONFIG_PM /** * snd_power_ref_and_wait - wait until the card gets powered up * @card: soundcard structure * * Take the power_ref reference count of the given card, and * wait until the card gets powered up to SNDRV_CTL_POWER_D0 state. * The refcount is down again while sleeping until power-up, hence this * function can be used for syncing the floating control ops accesses, * typically around calling control ops. * * The caller needs to pull down the refcount via snd_power_unref() later * no matter whether the error is returned from this function or not. * * Return: Zero if successful, or a negative error code. */ int snd_power_ref_and_wait(struct snd_card *card) { snd_power_ref(card); if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) return 0; wait_event_cmd(card->power_sleep, card->shutdown || snd_power_get_state(card) == SNDRV_CTL_POWER_D0, snd_power_unref(card), snd_power_ref(card)); return card->shutdown ? -ENODEV : 0; } EXPORT_SYMBOL_GPL(snd_power_ref_and_wait); /** * snd_power_wait - wait until the card gets powered up (old form) * @card: soundcard structure * * Wait until the card gets powered up to SNDRV_CTL_POWER_D0 state. * * Return: Zero if successful, or a negative error code. */ int snd_power_wait(struct snd_card *card) { int ret; ret = snd_power_ref_and_wait(card); snd_power_unref(card); return ret; } EXPORT_SYMBOL(snd_power_wait); #endif /* CONFIG_PM */ |
| 561 560 8677 155 612 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sched #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCHED_H #include <linux/kthread.h> #include <linux/sched/numa_balancing.h> #include <linux/tracepoint.h> #include <linux/binfmts.h> /* * Tracepoint for calling kthread_stop, performed to end a kthread: */ TRACE_EVENT(sched_kthread_stop, TP_PROTO(struct task_struct *t), TP_ARGS(t), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) ), TP_fast_assign( memcpy(__entry->comm, t->comm, TASK_COMM_LEN); __entry->pid = t->pid; ), TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid) ); /* * Tracepoint for the return value of the kthread stopping: */ TRACE_EVENT(sched_kthread_stop_ret, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field( int, ret ) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); /** * sched_kthread_work_queue_work - called when a work gets queued * @worker: pointer to the kthread_worker * @work: pointer to struct kthread_work * * This event occurs when a work is queued immediately or once a * delayed work is actually queued (ie: once the delay has been * reached). */ TRACE_EVENT(sched_kthread_work_queue_work, TP_PROTO(struct kthread_worker *worker, struct kthread_work *work), TP_ARGS(worker, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __field( void *, worker) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __entry->worker = worker; ), TP_printk("work struct=%p function=%ps worker=%p", __entry->work, __entry->function, __entry->worker) ); /** * sched_kthread_work_execute_start - called immediately before the work callback * @work: pointer to struct kthread_work * * Allows to track kthread work execution. */ TRACE_EVENT(sched_kthread_work_execute_start, TP_PROTO(struct kthread_work *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * sched_kthread_work_execute_end - called immediately after the work callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(sched_kthread_work_execute_end, TP_PROTO(struct kthread_work *work, kthread_work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /* * Tracepoint for waking up a task: */ DECLARE_EVENT_CLASS(sched_wakeup_template, TP_PROTO(struct task_struct *p), TP_ARGS(__perf_task(p)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, target_cpu ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->target_cpu = task_cpu(p); ), TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d", __entry->comm, __entry->pid, __entry->prio, __entry->target_cpu) ); /* * Tracepoint called when waking a task; this tracepoint is guaranteed to be * called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_waking, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING. * It is not always called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for waking up a new task: */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_PROTO(struct task_struct *p), TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS static inline long __trace_sched_switch_state(bool preempt, unsigned int prev_state, struct task_struct *p) { unsigned int state; BUG_ON(p != current); /* * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ if (preempt) return TASK_REPORT_MAX; /* * task_state_index() uses fls() and returns a value from 0-8 range. * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using * it for left shift operation to get the correct task->state * mapping. */ state = __task_state_index(prev_state, p->exit_state); return state ? (1 << (state - 1)) : state; } #endif /* CREATE_TRACE_POINTS */ /* * Tracepoint for task switches, performed by the scheduler: */ TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, struct task_struct *prev, struct task_struct *next, unsigned int prev_state), TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) __field( pid_t, prev_pid ) __field( int, prev_prio ) __field( long, prev_state ) __array( char, next_comm, TASK_COMM_LEN ) __field( pid_t, next_pid ) __field( int, next_prio ) ), TP_fast_assign( memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev); memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", { TASK_INTERRUPTIBLE, "S" }, { TASK_UNINTERRUPTIBLE, "D" }, { __TASK_STOPPED, "T" }, { __TASK_TRACED, "t" }, { EXIT_DEAD, "X" }, { EXIT_ZOMBIE, "Z" }, { TASK_PARKED, "P" }, { TASK_DEAD, "I" }) : "R", __entry->prev_state & TASK_REPORT_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); /* * Tracepoint for a task being migrated: */ TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu), TP_ARGS(p, dest_cpu), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu) ); DECLARE_EVENT_CLASS(sched_process_template, TP_PROTO(struct task_struct *p), TP_ARGS(p), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); /* * Tracepoint for freeing a task: */ DEFINE_EVENT(sched_process_template, sched_process_free, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a task exiting: */ DEFINE_EVENT(sched_process_template, sched_process_exit, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for waiting on task to unschedule: */ DEFINE_EVENT(sched_process_template, sched_wait_task, TP_PROTO(struct task_struct *p), TP_ARGS(p)); /* * Tracepoint for a waiting task: */ TRACE_EVENT(sched_process_wait, TP_PROTO(struct pid *pid), TP_ARGS(pid), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) ), TP_fast_assign( memcpy(__entry->comm, current->comm, TASK_COMM_LEN); __entry->pid = pid_nr(pid); __entry->prio = current->prio; /* XXX SCHED_DEADLINE */ ), TP_printk("comm=%s pid=%d prio=%d", __entry->comm, __entry->pid, __entry->prio) ); /* * Tracepoint for kernel_clone: */ TRACE_EVENT(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child), TP_ARGS(parent, child), TP_STRUCT__entry( __array( char, parent_comm, TASK_COMM_LEN ) __field( pid_t, parent_pid ) __array( char, child_comm, TASK_COMM_LEN ) __field( pid_t, child_pid ) ), TP_fast_assign( memcpy(__entry->parent_comm, parent->comm, TASK_COMM_LEN); __entry->parent_pid = parent->pid; memcpy(__entry->child_comm, child->comm, TASK_COMM_LEN); __entry->child_pid = child->pid; ), TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d", __entry->parent_comm, __entry->parent_pid, __entry->child_comm, __entry->child_pid) ); /* * Tracepoint for exec: */ TRACE_EVENT(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm), TP_ARGS(p, old_pid, bprm), TP_STRUCT__entry( __string( filename, bprm->filename ) __field( pid_t, pid ) __field( pid_t, old_pid ) ), TP_fast_assign( __assign_str(filename); __entry->pid = p->pid; __entry->old_pid = old_pid; ), TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename), __entry->pid, __entry->old_pid) ); /** * sched_prepare_exec - called before setting up new exec * @task: pointer to the current task * @bprm: pointer to linux_binprm used for new exec * * Called before flushing the old exec, where @task is still unchanged, but at * the point of no return during switching to the new exec. At the point it is * called the exec will either succeed, or on failure terminate the task. Also * see the "sched_process_exec" tracepoint, which is called right after @task * has successfully switched to the new exec. */ TRACE_EVENT(sched_prepare_exec, TP_PROTO(struct task_struct *task, struct linux_binprm *bprm), TP_ARGS(task, bprm), TP_STRUCT__entry( __string( interp, bprm->interp ) __string( filename, bprm->filename ) __field( pid_t, pid ) __string( comm, task->comm ) ), TP_fast_assign( __assign_str(interp); __assign_str(filename); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("interp=%s filename=%s pid=%d comm=%s", __get_str(interp), __get_str(filename), __entry->pid, __get_str(comm)) ); #ifdef CONFIG_SCHEDSTATS #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS #else #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT_NOP #define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS_NOP #endif /* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ DECLARE_EVENT_CLASS_SCHEDSTAT(sched_stat_template, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(__perf_task(tsk), __perf_count(delay)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( u64, delay ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->delay = delay; ), TP_printk("comm=%s pid=%d delay=%Lu [ns]", __entry->comm, __entry->pid, (unsigned long long)__entry->delay) ); /* * Tracepoint for accounting wait time (time the task is runnable * but not actually running due to scheduler contention). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_wait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting sleep time (time the task is not runnable, * including iowait, see below). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_sleep, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting iowait time (time the task is not runnable * due to waiting on IO to complete). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_iowait, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting blocked time (time the task is in uninterruptible). */ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked, TP_PROTO(struct task_struct *tsk, u64 delay), TP_ARGS(tsk, delay)); /* * Tracepoint for accounting runtime (time the task is executing * on a CPU). */ DECLARE_EVENT_CLASS(sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime), TP_ARGS(tsk, __perf_count(runtime)), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( u64, runtime ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->runtime = runtime; ), TP_printk("comm=%s pid=%d runtime=%Lu [ns]", __entry->comm, __entry->pid, (unsigned long long)__entry->runtime) ); DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime, TP_PROTO(struct task_struct *tsk, u64 runtime), TP_ARGS(tsk, runtime)); /* * Tracepoint for showing priority inheritance modifying a tasks * priority. */ TRACE_EVENT(sched_pi_setprio, TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task), TP_ARGS(tsk, pi_task), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, oldprio ) __field( int, newprio ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; __entry->oldprio = tsk->prio; __entry->newprio = pi_task ? min(tsk->normal_prio, pi_task->prio) : tsk->normal_prio; /* XXX SCHED_DEADLINE bits missing */ ), TP_printk("comm=%s pid=%d oldprio=%d newprio=%d", __entry->comm, __entry->pid, __entry->oldprio, __entry->newprio) ); #ifdef CONFIG_DETECT_HUNG_TASK TRACE_EVENT(sched_process_hang, TP_PROTO(struct task_struct *tsk), TP_ARGS(tsk), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) ), TP_fast_assign( memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); __entry->pid = tsk->pid; ), TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid) ); #endif /* CONFIG_DETECT_HUNG_TASK */ /* * Tracks migration of tasks from one runqueue to another. Can be used to * detect if automatic NUMA balancing is bouncing between nodes. */ TRACE_EVENT(sched_move_numa, TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), TP_ARGS(tsk, src_cpu, dst_cpu), TP_STRUCT__entry( __field( pid_t, pid ) __field( pid_t, tgid ) __field( pid_t, ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->pid = task_pid_nr(tsk); __entry->tgid = task_tgid_nr(tsk); __entry->ngid = task_numa_group_id(tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_cpu = dst_cpu; __entry->dst_nid = cpu_to_node(dst_cpu); ), TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d", __entry->pid, __entry->tgid, __entry->ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_cpu, __entry->dst_nid) ); DECLARE_EVENT_CLASS(sched_numa_pair_template, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu), TP_STRUCT__entry( __field( pid_t, src_pid ) __field( pid_t, src_tgid ) __field( pid_t, src_ngid ) __field( int, src_cpu ) __field( int, src_nid ) __field( pid_t, dst_pid ) __field( pid_t, dst_tgid ) __field( pid_t, dst_ngid ) __field( int, dst_cpu ) __field( int, dst_nid ) ), TP_fast_assign( __entry->src_pid = task_pid_nr(src_tsk); __entry->src_tgid = task_tgid_nr(src_tsk); __entry->src_ngid = task_numa_group_id(src_tsk); __entry->src_cpu = src_cpu; __entry->src_nid = cpu_to_node(src_cpu); __entry->dst_pid = dst_tsk ? task_pid_nr(dst_tsk) : 0; __entry->dst_tgid = dst_tsk ? task_tgid_nr(dst_tsk) : 0; __entry->dst_ngid = dst_tsk ? task_numa_group_id(dst_tsk) : 0; __entry->dst_cpu = dst_cpu; __entry->dst_nid = dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1; ), TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d", __entry->src_pid, __entry->src_tgid, __entry->src_ngid, __entry->src_cpu, __entry->src_nid, __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid, __entry->dst_cpu, __entry->dst_nid) ); DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa, TP_PROTO(struct task_struct *src_tsk, int src_cpu, struct task_struct *dst_tsk, int dst_cpu), TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu) ); #ifdef CONFIG_NUMA_BALANCING #define NUMAB_SKIP_REASON \ EM( NUMAB_SKIP_UNSUITABLE, "unsuitable" ) \ EM( NUMAB_SKIP_SHARED_RO, "shared_ro" ) \ EM( NUMAB_SKIP_INACCESSIBLE, "inaccessible" ) \ EM( NUMAB_SKIP_SCAN_DELAY, "scan_delay" ) \ EM( NUMAB_SKIP_PID_INACTIVE, "pid_inactive" ) \ EM( NUMAB_SKIP_IGNORE_PID, "ignore_pid_inactive" ) \ EMe(NUMAB_SKIP_SEQ_COMPLETED, "seq_completed" ) /* Redefine for export. */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); NUMAB_SKIP_REASON /* Redefine for symbolic printing. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } TRACE_EVENT(sched_skip_vma_numa, TP_PROTO(struct mm_struct *mm, struct vm_area_struct *vma, enum numa_vmaskip_reason reason), TP_ARGS(mm, vma, reason), TP_STRUCT__entry( __field(unsigned long, numa_scan_offset) __field(unsigned long, vm_start) __field(unsigned long, vm_end) __field(enum numa_vmaskip_reason, reason) ), TP_fast_assign( __entry->numa_scan_offset = mm->numa_scan_offset; __entry->vm_start = vma->vm_start; __entry->vm_end = vma->vm_end; __entry->reason = reason; ), TP_printk("numa_scan_offset=%lX vm_start=%lX vm_end=%lX reason=%s", __entry->numa_scan_offset, __entry->vm_start, __entry->vm_end, __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) ); #endif /* CONFIG_NUMA_BALANCING */ /* * Tracepoint for waking a polling cpu without an IPI. */ TRACE_EVENT(sched_wake_idle_without_ipi, TP_PROTO(int cpu), TP_ARGS(cpu), TP_STRUCT__entry( __field( int, cpu ) ), TP_fast_assign( __entry->cpu = cpu; ), TP_printk("cpu=%d", __entry->cpu) ); /* * Following tracepoints are not exported in tracefs and provide hooking * mechanisms only for testing and debugging purposes. * * Postfixed with _tp to make them easily identifiable in the code. */ DECLARE_TRACE(pelt_cfs_tp, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(pelt_rt_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_dl_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_hw_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_irq_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(pelt_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_cpu_capacity_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_TRACE(sched_overutilized_tp, TP_PROTO(struct root_domain *rd, bool overutilized), TP_ARGS(rd, overutilized)); DECLARE_TRACE(sched_util_est_cfs_tp, TP_PROTO(struct cfs_rq *cfs_rq), TP_ARGS(cfs_rq)); DECLARE_TRACE(sched_util_est_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); DECLARE_TRACE(sched_update_nr_running_tp, TP_PROTO(struct rq *rq, int change), TP_ARGS(rq, change)); DECLARE_TRACE(sched_compute_energy_tp, TP_PROTO(struct task_struct *p, int dst_cpu, unsigned long energy, unsigned long max_util, unsigned long busy_time), TP_ARGS(p, dst_cpu, energy, max_util, busy_time)); DECLARE_TRACE(sched_entry_tp, TP_PROTO(bool preempt, unsigned long ip), TP_ARGS(preempt, ip)); DECLARE_TRACE(sched_exit_tp, TP_PROTO(bool is_switch, unsigned long ip), TP_ARGS(is_switch, ip)); DECLARE_TRACE_CONDITION(sched_set_state_tp, TP_PROTO(struct task_struct *tsk, int state), TP_ARGS(tsk, state), TP_CONDITION(!!(tsk->__state) != !!state)); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 106 7 2 2 6 102 6 5 2 5 1 99 106 108 99 99 99 97 96 104 95 99 99 85 98 98 99 99 97 97 97 97 97 96 96 10 10 96 132 45 96 96 96 96 9 96 96 94 94 85 75 76 2 97 84 1 97 97 85 1 84 97 14 97 13 85 85 96 97 195 1 194 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kexec.c - kexec system call core code. * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/btf.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/kexec.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/syscalls.h> #include <linux/reboot.h> #include <linux/ioport.h> #include <linux/hardirq.h> #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/utsname.h> #include <linux/numa.h> #include <linux/suspend.h> #include <linux/device.h> #include <linux/freezer.h> #include <linux/panic_notifier.h> #include <linux/pm.h> #include <linux/cpu.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/console.h> #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/syscore_ops.h> #include <linux/compiler.h> #include <linux/hugetlb.h> #include <linux/objtool.h> #include <linux/kmsg_dump.h> #include <asm/page.h> #include <asm/sections.h> #include <crypto/hash.h> #include "kexec_internal.h" atomic_t __kexec_lock = ATOMIC_INIT(0); /* Flag to indicate we are going to kexec a new kernel */ bool kexec_in_progress = false; bool kexec_file_dbg_print; /* * When kexec transitions to the new kernel there is a one-to-one * mapping between physical and virtual addresses. On processors * where you can disable the MMU this is trivial, and easy. For * others it is still a simple predictable page table to setup. * * In that environment kexec copies the new kernel to its final * resting place. This means I can only support memory whose * physical address can fit in an unsigned long. In particular * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled. * If the assembly stub has more restrictive requirements * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be * defined more restrictively in <asm/kexec.h>. * * The code for the transition from the current kernel to the * new kernel is placed in the control_code_buffer, whose size * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single * page of memory is necessary, but some architectures require more. * Because this memory must be identity mapped in the transition from * virtual to physical addresses it must live in the range * 0 - TASK_SIZE, as only the user space mappings are arbitrarily * modifiable. * * The assembly stub in the control code buffer is passed a linked list * of descriptor pages detailing the source pages of the new kernel, * and the destination addresses of those source pages. As this data * structure is not used in the context of the current OS, it must * be self-contained. * * The code has been made to work with highmem pages and will use a * destination page in its final resting place (if it happens * to allocate it). The end product of this is that most of the * physical address space, and most of RAM can be used. * * Future directions include: * - allocating a page table with the control code buffer identity * mapped, to simplify machine_kexec and make kexec_on_panic more * reliable. */ /* * KIMAGE_NO_DEST is an impossible destination address..., for * allocating pages whose destination address we do not care about. */ #define KIMAGE_NO_DEST (-1UL) #define PAGE_COUNT(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT) static struct page *kimage_alloc_page(struct kimage *image, gfp_t gfp_mask, unsigned long dest); int sanity_check_segment_list(struct kimage *image) { int i; unsigned long nr_segments = image->nr_segments; unsigned long total_pages = 0; unsigned long nr_pages = totalram_pages(); /* * Verify we have good destination addresses. The caller is * responsible for making certain we don't attempt to load * the new image into invalid or reserved areas of RAM. This * just verifies it is an address we can use. * * Since the kernel does everything in page size chunks ensure * the destination addresses are page aligned. Too many * special cases crop of when we don't do this. The most * insidious is getting overlapping destination addresses * simply because addresses are changed to page size * granularity. */ for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; if (mstart > mend) return -EADDRNOTAVAIL; if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK)) return -EADDRNOTAVAIL; if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT) return -EADDRNOTAVAIL; } /* Verify our destination addresses do not overlap. * If we alloed overlapping destination addresses * through very weird things can happen with no * easy explanation as one segment stops on another. */ for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; unsigned long j; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; for (j = 0; j < i; j++) { unsigned long pstart, pend; pstart = image->segment[j].mem; pend = pstart + image->segment[j].memsz; /* Do the segments overlap ? */ if ((mend > pstart) && (mstart < pend)) return -EINVAL; } } /* Ensure our buffer sizes are strictly less than * our memory sizes. This should always be the case, * and it is easier to check up front than to be surprised * later on. */ for (i = 0; i < nr_segments; i++) { if (image->segment[i].bufsz > image->segment[i].memsz) return -EINVAL; } /* * Verify that no more than half of memory will be consumed. If the * request from userspace is too large, a large amount of time will be * wasted allocating pages, which can cause a soft lockup. */ for (i = 0; i < nr_segments; i++) { if (PAGE_COUNT(image->segment[i].memsz) > nr_pages / 2) return -EINVAL; total_pages += PAGE_COUNT(image->segment[i].memsz); } if (total_pages > nr_pages / 2) return -EINVAL; #ifdef CONFIG_CRASH_DUMP /* * Verify we have good destination addresses. Normally * the caller is responsible for making certain we don't * attempt to load the new image into invalid or reserved * areas of RAM. But crash kernels are preloaded into a * reserved area of ram. We must ensure the addresses * are in the reserved area otherwise preloading the * kernel could corrupt things. */ if (image->type == KEXEC_TYPE_CRASH) { for (i = 0; i < nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; /* Ensure we are within the crash kernel limits */ if ((mstart < phys_to_boot_phys(crashk_res.start)) || (mend > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } } #endif /* * The destination addresses are searched from system RAM rather than * being allocated from the buddy allocator, so they are not guaranteed * to be accepted by the current kernel. Accept the destination * addresses before kexec swaps their content with the segments' source * pages to avoid accessing memory before it is accepted. */ for (i = 0; i < nr_segments; i++) accept_memory(image->segment[i].mem, image->segment[i].memsz); return 0; } struct kimage *do_kimage_alloc_init(void) { struct kimage *image; /* Allocate a controlling structure */ image = kzalloc(sizeof(*image), GFP_KERNEL); if (!image) return NULL; image->head = 0; image->entry = &image->head; image->last_entry = &image->head; image->control_page = ~0; /* By default this does not apply */ image->type = KEXEC_TYPE_DEFAULT; /* Initialize the list of control pages */ INIT_LIST_HEAD(&image->control_pages); /* Initialize the list of destination pages */ INIT_LIST_HEAD(&image->dest_pages); /* Initialize the list of unusable pages */ INIT_LIST_HEAD(&image->unusable_pages); #ifdef CONFIG_CRASH_HOTPLUG image->hp_action = KEXEC_CRASH_HP_NONE; image->elfcorehdr_index = -1; image->elfcorehdr_updated = false; #endif return image; } int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end) { unsigned long i; for (i = 0; i < image->nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; if ((end >= mstart) && (start <= mend)) return 1; } return 0; } static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) { struct page *pages; if (fatal_signal_pending(current)) return NULL; pages = alloc_pages(gfp_mask & ~__GFP_ZERO, order); if (pages) { unsigned int count, i; pages->mapping = NULL; set_page_private(pages, order); count = 1 << order; for (i = 0; i < count; i++) SetPageReserved(pages + i); arch_kexec_post_alloc_pages(page_address(pages), count, gfp_mask); if (gfp_mask & __GFP_ZERO) for (i = 0; i < count; i++) clear_highpage(pages + i); } return pages; } static void kimage_free_pages(struct page *page) { unsigned int order, count, i; order = page_private(page); count = 1 << order; arch_kexec_pre_free_pages(page_address(page), count); for (i = 0; i < count; i++) ClearPageReserved(page + i); __free_pages(page, order); } void kimage_free_page_list(struct list_head *list) { struct page *page, *next; list_for_each_entry_safe(page, next, list, lru) { list_del(&page->lru); kimage_free_pages(page); } } static struct page *kimage_alloc_normal_control_pages(struct kimage *image, unsigned int order) { /* Control pages are special, they are the intermediaries * that are needed while we copy the rest of the pages * to their final resting place. As such they must * not conflict with either the destination addresses * or memory the kernel is already using. * * The only case where we really need more than one of * these are for architectures where we cannot disable * the MMU and must instead generate an identity mapped * page table for all of the memory. * * At worst this runs in O(N) of the image size. */ struct list_head extra_pages; struct page *pages; unsigned int count; count = 1 << order; INIT_LIST_HEAD(&extra_pages); /* Loop while I can allocate a page and the page allocated * is a destination page. */ do { unsigned long pfn, epfn, addr, eaddr; pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; pfn = page_to_boot_pfn(pages); epfn = pfn + count; addr = pfn << PAGE_SHIFT; eaddr = (epfn << PAGE_SHIFT) - 1; if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) || kimage_is_destination_range(image, addr, eaddr)) { list_add(&pages->lru, &extra_pages); pages = NULL; } } while (!pages); if (pages) { /* Remember the allocated page... */ list_add(&pages->lru, &image->control_pages); /* Because the page is already in it's destination * location we will never allocate another page at * that address. Therefore kimage_alloc_pages * will not return it (again) and we don't need * to give it an entry in image->segment[]. */ } /* Deal with the destination pages I have inadvertently allocated. * * Ideally I would convert multi-page allocations into single * page allocations, and add everything to image->dest_pages. * * For now it is simpler to just free the pages. */ kimage_free_page_list(&extra_pages); return pages; } #ifdef CONFIG_CRASH_DUMP static struct page *kimage_alloc_crash_control_pages(struct kimage *image, unsigned int order) { /* Control pages are special, they are the intermediaries * that are needed while we copy the rest of the pages * to their final resting place. As such they must * not conflict with either the destination addresses * or memory the kernel is already using. * * Control pages are also the only pags we must allocate * when loading a crash kernel. All of the other pages * are specified by the segments and we just memcpy * into them directly. * * The only case where we really need more than one of * these are for architectures where we cannot disable * the MMU and must instead generate an identity mapped * page table for all of the memory. * * Given the low demand this implements a very simple * allocator that finds the first hole of the appropriate * size in the reserved memory region, and allocates all * of the memory up to and including the hole. */ unsigned long hole_start, hole_end, size; struct page *pages; pages = NULL; size = (1 << order) << PAGE_SHIFT; hole_start = ALIGN(image->control_page, size); hole_end = hole_start + size - 1; while (hole_end <= crashk_res.end) { unsigned long i; cond_resched(); if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT) break; /* See if I overlap any of the segments */ for (i = 0; i < image->nr_segments; i++) { unsigned long mstart, mend; mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz - 1; if ((hole_end >= mstart) && (hole_start <= mend)) { /* Advance the hole to the end of the segment */ hole_start = ALIGN(mend, size); hole_end = hole_start + size - 1; break; } } /* If I don't overlap any segments I have found my hole! */ if (i == image->nr_segments) { pages = pfn_to_page(hole_start >> PAGE_SHIFT); image->control_page = hole_end + 1; break; } } /* Ensure that these pages are decrypted if SME is enabled. */ if (pages) arch_kexec_post_alloc_pages(page_address(pages), 1 << order, 0); return pages; } #endif struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order) { struct page *pages = NULL; switch (image->type) { case KEXEC_TYPE_DEFAULT: pages = kimage_alloc_normal_control_pages(image, order); break; #ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: pages = kimage_alloc_crash_control_pages(image, order); break; #endif } return pages; } static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) { if (*image->entry != 0) image->entry++; if (image->entry == image->last_entry) { kimage_entry_t *ind_page; struct page *page; page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST); if (!page) return -ENOMEM; ind_page = page_address(page); *image->entry = virt_to_boot_phys(ind_page) | IND_INDIRECTION; image->entry = ind_page; image->last_entry = ind_page + ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1); } *image->entry = entry; image->entry++; *image->entry = 0; return 0; } static int kimage_set_destination(struct kimage *image, unsigned long destination) { destination &= PAGE_MASK; return kimage_add_entry(image, destination | IND_DESTINATION); } static int kimage_add_page(struct kimage *image, unsigned long page) { page &= PAGE_MASK; return kimage_add_entry(image, page | IND_SOURCE); } static void kimage_free_extra_pages(struct kimage *image) { /* Walk through and free any extra destination pages I may have */ kimage_free_page_list(&image->dest_pages); /* Walk through and free any unusable pages I have cached */ kimage_free_page_list(&image->unusable_pages); } void kimage_terminate(struct kimage *image) { if (*image->entry != 0) image->entry++; *image->entry = IND_DONE; } #define for_each_kimage_entry(image, ptr, entry) \ for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \ ptr = (entry & IND_INDIRECTION) ? \ boot_phys_to_virt((entry & PAGE_MASK)) : ptr + 1) static void kimage_free_entry(kimage_entry_t entry) { struct page *page; page = boot_pfn_to_page(entry >> PAGE_SHIFT); kimage_free_pages(page); } void kimage_free(struct kimage *image) { kimage_entry_t *ptr, entry; kimage_entry_t ind = 0; if (!image) return; #ifdef CONFIG_CRASH_DUMP if (image->vmcoreinfo_data_copy) { crash_update_vmcoreinfo_safecopy(NULL); vunmap(image->vmcoreinfo_data_copy); } #endif kimage_free_extra_pages(image); for_each_kimage_entry(image, ptr, entry) { if (entry & IND_INDIRECTION) { /* Free the previous indirection page */ if (ind & IND_INDIRECTION) kimage_free_entry(ind); /* Save this indirection page until we are * done with it. */ ind = entry; } else if (entry & IND_SOURCE) kimage_free_entry(entry); } /* Free the final indirection page */ if (ind & IND_INDIRECTION) kimage_free_entry(ind); /* Handle any machine specific cleanup */ machine_kexec_cleanup(image); /* Free the kexec control pages... */ kimage_free_page_list(&image->control_pages); /* * Free up any temporary buffers allocated. This might hit if * error occurred much later after buffer allocation. */ if (image->file_mode) kimage_file_post_load_cleanup(image); kfree(image); } static kimage_entry_t *kimage_dst_used(struct kimage *image, unsigned long page) { kimage_entry_t *ptr, entry; unsigned long destination = 0; for_each_kimage_entry(image, ptr, entry) { if (entry & IND_DESTINATION) destination = entry & PAGE_MASK; else if (entry & IND_SOURCE) { if (page == destination) return ptr; destination += PAGE_SIZE; } } return NULL; } static struct page *kimage_alloc_page(struct kimage *image, gfp_t gfp_mask, unsigned long destination) { /* * Here we implement safeguards to ensure that a source page * is not copied to its destination page before the data on * the destination page is no longer useful. * * To do this we maintain the invariant that a source page is * either its own destination page, or it is not a * destination page at all. * * That is slightly stronger than required, but the proof * that no problems will not occur is trivial, and the * implementation is simply to verify. * * When allocating all pages normally this algorithm will run * in O(N) time, but in the worst case it will run in O(N^2) * time. If the runtime is a problem the data structures can * be fixed. */ struct page *page; unsigned long addr; /* * Walk through the list of destination pages, and see if I * have a match. */ list_for_each_entry(page, &image->dest_pages, lru) { addr = page_to_boot_pfn(page) << PAGE_SHIFT; if (addr == destination) { list_del(&page->lru); return page; } } page = NULL; while (1) { kimage_entry_t *old; /* Allocate a page, if we run out of memory give up */ page = kimage_alloc_pages(gfp_mask, 0); if (!page) return NULL; /* If the page cannot be used file it away */ if (page_to_boot_pfn(page) > (KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) { list_add(&page->lru, &image->unusable_pages); continue; } addr = page_to_boot_pfn(page) << PAGE_SHIFT; /* If it is the destination page we want use it */ if (addr == destination) break; /* If the page is not a destination page use it */ if (!kimage_is_destination_range(image, addr, addr + PAGE_SIZE - 1)) break; /* * I know that the page is someones destination page. * See if there is already a source page for this * destination page. And if so swap the source pages. */ old = kimage_dst_used(image, addr); if (old) { /* If so move it */ unsigned long old_addr; struct page *old_page; old_addr = *old & PAGE_MASK; old_page = boot_pfn_to_page(old_addr >> PAGE_SHIFT); copy_highpage(page, old_page); *old = addr | (*old & ~PAGE_MASK); /* The old page I have found cannot be a * destination page, so return it if it's * gfp_flags honor the ones passed in. */ if (!(gfp_mask & __GFP_HIGHMEM) && PageHighMem(old_page)) { kimage_free_pages(old_page); continue; } page = old_page; break; } /* Place the page on the destination list, to be used later */ list_add(&page->lru, &image->dest_pages); } return page; } static int kimage_load_normal_segment(struct kimage *image, struct kexec_segment *segment) { unsigned long maddr; size_t ubytes, mbytes; int result; unsigned char __user *buf = NULL; unsigned char *kbuf = NULL; if (image->file_mode) kbuf = segment->kbuf; else buf = segment->buf; ubytes = segment->bufsz; mbytes = segment->memsz; maddr = segment->mem; result = kimage_set_destination(image, maddr); if (result < 0) goto out; while (mbytes) { struct page *page; char *ptr; size_t uchunk, mchunk; page = kimage_alloc_page(image, GFP_HIGHUSER, maddr); if (!page) { result = -ENOMEM; goto out; } result = kimage_add_page(image, page_to_boot_pfn(page) << PAGE_SHIFT); if (result < 0) goto out; ptr = kmap_local_page(page); /* Start with a clear page */ clear_page(ptr); ptr += maddr & ~PAGE_MASK; mchunk = min_t(size_t, mbytes, PAGE_SIZE - (maddr & ~PAGE_MASK)); uchunk = min(ubytes, mchunk); if (uchunk) { /* For file based kexec, source pages are in kernel memory */ if (image->file_mode) memcpy(ptr, kbuf, uchunk); else result = copy_from_user(ptr, buf, uchunk); ubytes -= uchunk; if (image->file_mode) kbuf += uchunk; else buf += uchunk; } kunmap_local(ptr); if (result) { result = -EFAULT; goto out; } maddr += mchunk; mbytes -= mchunk; cond_resched(); } out: return result; } #ifdef CONFIG_CRASH_DUMP static int kimage_load_crash_segment(struct kimage *image, struct kexec_segment *segment) { /* For crash dumps kernels we simply copy the data from * user space to it's destination. * We do things a page at a time for the sake of kmap. */ unsigned long maddr; size_t ubytes, mbytes; int result; unsigned char __user *buf = NULL; unsigned char *kbuf = NULL; result = 0; if (image->file_mode) kbuf = segment->kbuf; else buf = segment->buf; ubytes = segment->bufsz; mbytes = segment->memsz; maddr = segment->mem; while (mbytes) { struct page *page; char *ptr; size_t uchunk, mchunk; page = boot_pfn_to_page(maddr >> PAGE_SHIFT); if (!page) { result = -ENOMEM; goto out; } arch_kexec_post_alloc_pages(page_address(page), 1, 0); ptr = kmap_local_page(page); ptr += maddr & ~PAGE_MASK; mchunk = min_t(size_t, mbytes, PAGE_SIZE - (maddr & ~PAGE_MASK)); uchunk = min(ubytes, mchunk); if (mchunk > uchunk) { /* Zero the trailing part of the page */ memset(ptr + uchunk, 0, mchunk - uchunk); } if (uchunk) { /* For file based kexec, source pages are in kernel memory */ if (image->file_mode) memcpy(ptr, kbuf, uchunk); else result = copy_from_user(ptr, buf, uchunk); ubytes -= uchunk; if (image->file_mode) kbuf += uchunk; else buf += uchunk; } kexec_flush_icache_page(page); kunmap_local(ptr); arch_kexec_pre_free_pages(page_address(page), 1); if (result) { result = -EFAULT; goto out; } maddr += mchunk; mbytes -= mchunk; cond_resched(); } out: return result; } #endif int kimage_load_segment(struct kimage *image, struct kexec_segment *segment) { int result = -ENOMEM; switch (image->type) { case KEXEC_TYPE_DEFAULT: result = kimage_load_normal_segment(image, segment); break; #ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: result = kimage_load_crash_segment(image, segment); break; #endif } return result; } struct kexec_load_limit { /* Mutex protects the limit count. */ struct mutex mutex; int limit; }; static struct kexec_load_limit load_limit_reboot = { .mutex = __MUTEX_INITIALIZER(load_limit_reboot.mutex), .limit = -1, }; static struct kexec_load_limit load_limit_panic = { .mutex = __MUTEX_INITIALIZER(load_limit_panic.mutex), .limit = -1, }; struct kimage *kexec_image; struct kimage *kexec_crash_image; static int kexec_load_disabled; #ifdef CONFIG_SYSCTL static int kexec_limit_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct kexec_load_limit *limit = table->data; int val; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(val), .mode = table->mode, }; int ret; if (write) { ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (ret) return ret; if (val < 0) return -EINVAL; mutex_lock(&limit->mutex); if (limit->limit != -1 && val >= limit->limit) ret = -EINVAL; else limit->limit = val; mutex_unlock(&limit->mutex); return ret; } mutex_lock(&limit->mutex); val = limit->limit; mutex_unlock(&limit->mutex); return proc_dointvec(&tmp, write, buffer, lenp, ppos); } static const struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", .data = &kexec_load_disabled, .maxlen = sizeof(int), .mode = 0644, /* only handle a transition from default "0" to "1" */ .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_ONE, }, { .procname = "kexec_load_limit_panic", .data = &load_limit_panic, .mode = 0644, .proc_handler = kexec_limit_handler, }, { .procname = "kexec_load_limit_reboot", .data = &load_limit_reboot, .mode = 0644, .proc_handler = kexec_limit_handler, }, }; static int __init kexec_core_sysctl_init(void) { register_sysctl_init("kernel", kexec_core_sysctls); return 0; } late_initcall(kexec_core_sysctl_init); #endif bool kexec_load_permitted(int kexec_image_type) { struct kexec_load_limit *limit; /* * Only the superuser can use the kexec syscall and if it has not * been disabled. */ if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) return false; /* Check limit counter and decrease it.*/ limit = (kexec_image_type == KEXEC_TYPE_CRASH) ? &load_limit_panic : &load_limit_reboot; mutex_lock(&limit->mutex); if (!limit->limit) { mutex_unlock(&limit->mutex); return false; } if (limit->limit != -1) limit->limit--; mutex_unlock(&limit->mutex); return true; } /* * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. */ int kernel_kexec(void) { int error = 0; if (!kexec_trylock()) return -EBUSY; if (!kexec_image) { error = -EINVAL; goto Unlock; } #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { /* * This flow is analogous to hibernation flows that occur * before creating an image and before jumping from the * restore kernel to the image one, so it uses the same * device callbacks as those two flows. */ pm_prepare_console(); error = freeze_processes(); if (error) { error = -EBUSY; goto Restore_console; } console_suspend_all(); error = dpm_suspend_start(PMSG_FREEZE); if (error) goto Resume_console; /* * dpm_suspend_end() must be called after dpm_suspend_start() * to complete the transition, like in the hibernation flows * mentioned above. */ error = dpm_suspend_end(PMSG_FREEZE); if (error) goto Resume_devices; error = suspend_disable_secondary_cpus(); if (error) goto Enable_cpus; local_irq_disable(); error = syscore_suspend(); if (error) goto Enable_irqs; } else #endif { kexec_in_progress = true; kernel_restart_prepare("kexec reboot"); migrate_to_reboot_cpu(); syscore_shutdown(); /* * migrate_to_reboot_cpu() disables CPU hotplug assuming that * no further code needs to use CPU hotplug (which is true in * the reboot case). However, the kexec path depends on using * CPU hotplug again; so re-enable it here. */ cpu_hotplug_enable(); pr_notice("Starting new kernel\n"); machine_shutdown(); } kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_kexec(kexec_image); #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { /* * This flow is analogous to hibernation flows that occur after * creating an image and after the image kernel has got control * back, and in case the devices have been reset or otherwise * manipulated in the meantime, it uses the device callbacks * used by the latter. */ syscore_resume(); Enable_irqs: local_irq_enable(); Enable_cpus: suspend_enable_secondary_cpus(); dpm_resume_start(PMSG_RESTORE); Resume_devices: dpm_resume_end(PMSG_RESTORE); Resume_console: console_resume_all(); thaw_processes(); Restore_console: pm_restore_console(); } #endif Unlock: kexec_unlock(); return error; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved */ #include "autofs_i.h" static const char *autofs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct autofs_sb_info *sbi; struct autofs_info *ino; if (!dentry) return ERR_PTR(-ECHILD); sbi = autofs_sbi(dentry->d_sb); ino = autofs_dentry_ino(dentry); if (ino && !autofs_oz_mode(sbi)) ino->last_used = jiffies; return d_inode(dentry)->i_private; } const struct inode_operations autofs_symlink_inode_operations = { .get_link = autofs_get_link }; |
| 239 40 9 40 60 233 233 233 10 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 | /* * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/in.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/ipv6.h> #include "rds_single_path.h" #include "rds.h" #include "loop.h" static DEFINE_SPINLOCK(loop_conns_lock); static LIST_HEAD(loop_conns); static atomic_t rds_loop_unloading = ATOMIC_INIT(0); static void rds_loop_set_unloading(void) { atomic_set(&rds_loop_unloading, 1); } static bool rds_loop_is_unloading(struct rds_connection *conn) { return atomic_read(&rds_loop_unloading) != 0; } /* * This 'loopback' transport is a special case for flows that originate * and terminate on the same machine. * * Connection build-up notices if the destination address is thought of * as a local address by a transport. At that time it decides to use the * loopback transport instead of the bound transport of the sending socket. * * The loopback transport's sending path just hands the sent rds_message * straight to the receiving path via an embedded rds_incoming. */ /* * Usually a message transits both the sender and receiver's conns as it * flows to the receiver. In the loopback case, though, the receive path * is handed the sending conn so the sense of the addresses is reversed. */ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, unsigned int hdr_off, unsigned int sg, unsigned int off) { struct scatterlist *sgp = &rm->data.op_sg[sg]; int ret = sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len); /* Do not send cong updates to loopback */ if (rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); ret = min_t(int, ret, sgp->length - conn->c_xmit_data_off); goto out; } BUG_ON(hdr_off || sg || off); rds_inc_init(&rm->m_inc, conn, &conn->c_laddr); /* For the embedded inc. Matching put is in loop_inc_free() */ rds_message_addref(rm); rds_recv_incoming(conn, &conn->c_laddr, &conn->c_faddr, &rm->m_inc, GFP_KERNEL); rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence), NULL); rds_inc_put(&rm->m_inc); out: return ret; } /* * See rds_loop_xmit(). Since our inc is embedded in the rm, we * make sure the rm lives at least until the inc is done. */ static void rds_loop_inc_free(struct rds_incoming *inc) { struct rds_message *rm = container_of(inc, struct rds_message, m_inc); rds_message_put(rm); } /* we need to at least give the thread something to succeed */ static int rds_loop_recv_path(struct rds_conn_path *cp) { return 0; } struct rds_loop_connection { struct list_head loop_node; struct rds_connection *conn; }; /* * Even the loopback transport needs to keep track of its connections, * so it can call rds_conn_destroy() on them on exit. N.B. there are * 1+ loopback addresses (127.*.*.*) so it's not a bug to have * multiple loopback conns allocated, although rather useless. */ static int rds_loop_conn_alloc(struct rds_connection *conn, gfp_t gfp) { struct rds_loop_connection *lc; unsigned long flags; lc = kzalloc(sizeof(struct rds_loop_connection), gfp); if (!lc) return -ENOMEM; INIT_LIST_HEAD(&lc->loop_node); lc->conn = conn; conn->c_transport_data = lc; spin_lock_irqsave(&loop_conns_lock, flags); list_add_tail(&lc->loop_node, &loop_conns); spin_unlock_irqrestore(&loop_conns_lock, flags); return 0; } static void rds_loop_conn_free(void *arg) { struct rds_loop_connection *lc = arg; unsigned long flags; rdsdebug("lc %p\n", lc); spin_lock_irqsave(&loop_conns_lock, flags); list_del(&lc->loop_node); spin_unlock_irqrestore(&loop_conns_lock, flags); kfree(lc); } static int rds_loop_conn_path_connect(struct rds_conn_path *cp) { rds_connect_complete(cp->cp_conn); return 0; } static void rds_loop_conn_path_shutdown(struct rds_conn_path *cp) { } void rds_loop_exit(void) { struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); rds_loop_set_unloading(); synchronize_rcu(); /* avoid calling conn_destroy with irqs off */ spin_lock_irq(&loop_conns_lock); list_splice(&loop_conns, &tmp_list); INIT_LIST_HEAD(&loop_conns); spin_unlock_irq(&loop_conns_lock); list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { WARN_ON(lc->conn->c_passive); rds_conn_destroy(lc->conn); } } static void rds_loop_kill_conns(struct net *net) { struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); spin_lock_irq(&loop_conns_lock); list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) { struct net *c_net = read_pnet(&lc->conn->c_net); if (net != c_net) continue; list_move_tail(&lc->loop_node, &tmp_list); } spin_unlock_irq(&loop_conns_lock); list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { WARN_ON(lc->conn->c_passive); rds_conn_destroy(lc->conn); } } static void __net_exit rds_loop_exit_net(struct net *net) { rds_loop_kill_conns(net); } static struct pernet_operations rds_loop_net_ops = { .exit = rds_loop_exit_net, }; int rds_loop_net_init(void) { return register_pernet_device(&rds_loop_net_ops); } void rds_loop_net_exit(void) { unregister_pernet_device(&rds_loop_net_ops); } /* * This is missing .xmit_* because loop doesn't go through generic * rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and * .laddr_check are missing because transport.c doesn't iterate over * rds_loop_transport. */ struct rds_transport rds_loop_transport = { .xmit = rds_loop_xmit, .recv_path = rds_loop_recv_path, .conn_alloc = rds_loop_conn_alloc, .conn_free = rds_loop_conn_free, .conn_path_connect = rds_loop_conn_path_connect, .conn_path_shutdown = rds_loop_conn_path_shutdown, .inc_copy_to_user = rds_message_inc_copy_to_user, .inc_free = rds_loop_inc_free, .t_name = "loopback", .t_type = RDS_TRANS_LOOP, .t_unloading = rds_loop_is_unloading, }; |
| 173 36 147 159 159 191 190 2 2 151 1 3 8 46 12 43 114 114 2 102 65 46 33 23 91 211 211 211 205 147 154 4 65 6 162 40 170 4 51 18 18 2 4 150 25 146 6 5 152 152 155 1 154 153 153 14 14 14 47 39 17 47 10 47 47 48 48 48 12 39 4 33 28 4 4 47 51 6 47 12 4 8 5 1 4 6 1 1 4 4 25 25 25 3 22 25 1 25 14 12 25 23 4 25 2 1 1 1 4 4 5 211 1 1 2 4 34 173 113 69 65 1 1 1 5 5 12 53 13 3 12 12 1 1 3 1 8 8 8 6 1 1 4 12 2 10 32 32 4 2 4 1 2 6 1 2 1 2 10 3 2 11 1 1 4 2 2 1 3 5 2 40 1 2 2 5 22 31 3 30 1 1 3 6 1 1 2 15 13 13 5 27 19 20 57 57 57 1 3 4 11 15 3 25 25 1 24 6 2 19 2 20 33 5 6 7 19 15 11 63 1 2 1 4 25 33 66 4 62 4 1 1 17 17 8 4 4 8 6 8 8 3 3 3 259 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware vSockets Driver * * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. */ /* Implementation notes: * * - There are two kinds of sockets: those created by user action (such as * calling socket(2)) and those created by incoming connection request packets. * * - There are two "global" tables, one for bound sockets (sockets that have * specified an address that they are responsible for) and one for connected * sockets (sockets that have established a connection with another socket). * These tables are "global" in that all sockets on the system are placed * within them. - Note, though, that the bound table contains an extra entry * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in * that list. The bound table is used solely for lookup of sockets when packets * are received and that's not necessary for SOCK_DGRAM sockets since we create * a datagram handle for each and need not perform a lookup. Keeping SOCK_DGRAM * sockets out of the bound hash buckets will reduce the chance of collisions * when looking for SOCK_STREAM sockets and prevents us from having to check the * socket type in the hash table lookups. * * - Sockets created by user action will either be "client" sockets that * initiate a connection or "server" sockets that listen for connections; we do * not support simultaneous connects (two "client" sockets connecting). * * - "Server" sockets are referred to as listener sockets throughout this * implementation because they are in the TCP_LISTEN state. When a * connection request is received (the second kind of socket mentioned above), * we create a new socket and refer to it as a pending socket. These pending * sockets are placed on the pending connection list of the listener socket. * When future packets are received for the address the listener socket is * bound to, we check if the source of the packet is from one that has an * existing pending connection. If it does, we process the packet for the * pending socket. When that socket reaches the connected state, it is removed * from the listener socket's pending list and enqueued in the listener * socket's accept queue. Callers of accept(2) will accept connected sockets * from the listener socket's accept queue. If the socket cannot be accepted * for some reason then it is marked rejected. Once the connection is * accepted, it is owned by the user process and the responsibility for cleanup * falls with that user process. * * - It is possible that these pending sockets will never reach the connected * state; in fact, we may never receive another packet after the connection * request. Because of this, we must schedule a cleanup function to run in the * future, after some amount of time passes where a connection should have been * established. This function ensures that the socket is off all lists so it * cannot be retrieved, then drops all references to the socket so it is cleaned * up (sock_put() -> sk_free() -> our sk_destruct implementation). Note this * function will also cleanup rejected sockets, those that reach the connected * state but leave it before they have been accepted. * * - Lock ordering for pending or accept queue sockets is: * * lock_sock(listener); * lock_sock_nested(pending, SINGLE_DEPTH_NESTING); * * Using explicit nested locking keeps lockdep happy since normally only one * lock of a given class may be taken at a time. * * - Sockets created by user action will be cleaned up when the user process * calls close(2), causing our release implementation to be called. Our release * implementation will perform some cleanup then drop the last reference so our * sk_destruct implementation is invoked. Our sk_destruct implementation will * perform additional cleanup that's common for both types of sockets. * * - A socket's reference count is what ensures that the structure won't be * freed. Each entry in a list (such as the "global" bound and connected tables * and the listener socket's pending list and connected queue) ensures a * reference. When we defer work until process context and pass a socket as our * argument, we must ensure the reference count is increased to ensure the * socket isn't freed before the function is run; the deferred function will * then drop the reference. * * - sk->sk_state uses the TCP state constants because they are widely used by * other address families and exposed to userspace tools like ss(8): * * TCP_CLOSE - unconnected * TCP_SYN_SENT - connecting * TCP_ESTABLISHED - connected * TCP_CLOSING - disconnecting * TCP_LISTEN - listening */ #include <linux/compat.h> #include <linux/types.h> #include <linux/bitops.h> #include <linux/cred.h> #include <linux/errqueue.h> #include <linux/init.h> #include <linux/io.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/net.h> #include <linux/poll.h> #include <linux/random.h> #include <linux/skbuff.h> #include <linux/smp.h> #include <linux/socket.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> #include <net/af_vsock.h> #include <uapi/linux/vm_sockets.h> #include <uapi/asm-generic/ioctls.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); static void vsock_close(struct sock *sk, long timeout); /* Protocol family. */ struct proto vsock_proto = { .name = "AF_VSOCK", .owner = THIS_MODULE, .obj_size = sizeof(struct vsock_sock), .close = vsock_close, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = vsock_bpf_update_proto, #endif }; /* The default peer timeout indicates how long we will wait for a peer response * to a control message. */ #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) #define VSOCK_DEFAULT_BUFFER_SIZE (1024 * 256) #define VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256) #define VSOCK_DEFAULT_BUFFER_MIN_SIZE 128 /* Transport used for host->guest communication */ static const struct vsock_transport *transport_h2g; /* Transport used for guest->host communication */ static const struct vsock_transport *transport_g2h; /* Transport used for DGRAM communication */ static const struct vsock_transport *transport_dgram; /* Transport used for local communication */ static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex); /**** UTILS ****/ /* Each bound VSocket is stored in the bind hash table and each connected * VSocket is stored in the connected hash table. * * Unbound sockets are all put on the same list attached to the end of the hash * table (vsock_unbound_sockets). Bound sockets are added to the hash table in * the bucket that their local address hashes to (vsock_bound_sockets(addr) * represents the list that addr hashes to). * * Specifically, we initialize the vsock_bind_table array to a size of * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function * mods with VSOCK_HASH_SIZE to ensure this. */ #define MAX_PORT_RETRIES 24 #define VSOCK_HASH(addr) ((addr)->svm_port % VSOCK_HASH_SIZE) #define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)]) #define vsock_unbound_sockets (&vsock_bind_table[VSOCK_HASH_SIZE]) /* XXX This can probably be implemented in a better way. */ #define VSOCK_CONN_HASH(src, dst) \ (((src)->svm_cid ^ (dst)->svm_port) % VSOCK_HASH_SIZE) #define vsock_connected_sockets(src, dst) \ (&vsock_connected_table[VSOCK_CONN_HASH(src, dst)]) #define vsock_connected_sockets_vsk(vsk) \ vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr) struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; EXPORT_SYMBOL_GPL(vsock_bind_table); struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; EXPORT_SYMBOL_GPL(vsock_connected_table); DEFINE_SPINLOCK(vsock_table_lock); EXPORT_SYMBOL_GPL(vsock_table_lock); /* Autobind this socket to the local address if necessary. */ static int vsock_auto_bind(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); struct sockaddr_vm local_addr; if (vsock_addr_bound(&vsk->local_addr)) return 0; vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); return __vsock_bind(sk, &local_addr); } static void vsock_init_tables(void) { int i; for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++) INIT_LIST_HEAD(&vsock_bind_table[i]); for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) INIT_LIST_HEAD(&vsock_connected_table[i]); } static void __vsock_insert_bound(struct list_head *list, struct vsock_sock *vsk) { sock_hold(&vsk->sk); list_add(&vsk->bound_table, list); } static void __vsock_insert_connected(struct list_head *list, struct vsock_sock *vsk) { sock_hold(&vsk->sk); list_add(&vsk->connected_table, list); } static void __vsock_remove_bound(struct vsock_sock *vsk) { list_del_init(&vsk->bound_table); sock_put(&vsk->sk); } static void __vsock_remove_connected(struct vsock_sock *vsk) { list_del_init(&vsk->connected_table); sock_put(&vsk->sk); } static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) { if (vsock_addr_equals_addr(addr, &vsk->local_addr)) return sk_vsock(vsk); if (addr->svm_port == vsk->local_addr.svm_port && (vsk->local_addr.svm_cid == VMADDR_CID_ANY || addr->svm_cid == VMADDR_CID_ANY)) return sk_vsock(vsk); } return NULL; } static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { if (vsock_addr_equals_addr(src, &vsk->remote_addr) && dst->svm_port == vsk->local_addr.svm_port) { return sk_vsock(vsk); } } return NULL; } static void vsock_insert_unbound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); __vsock_insert_bound(vsock_unbound_sockets, vsk); spin_unlock_bh(&vsock_table_lock); } void vsock_insert_connected(struct vsock_sock *vsk) { struct list_head *list = vsock_connected_sockets( &vsk->remote_addr, &vsk->local_addr); spin_lock_bh(&vsock_table_lock); __vsock_insert_connected(list, vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_insert_connected); void vsock_remove_bound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); if (__vsock_in_bound_table(vsk)) __vsock_remove_bound(vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_remove_bound); void vsock_remove_connected(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); if (__vsock_in_connected_table(vsk)) __vsock_remove_connected(vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_remove_connected); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) { struct sock *sk; spin_lock_bh(&vsock_table_lock); sk = __vsock_find_bound_socket(addr); if (sk) sock_hold(sk); spin_unlock_bh(&vsock_table_lock); return sk; } EXPORT_SYMBOL_GPL(vsock_find_bound_socket); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst) { struct sock *sk; spin_lock_bh(&vsock_table_lock); sk = __vsock_find_connected_socket(src, dst); if (sk) sock_hold(sk); spin_unlock_bh(&vsock_table_lock); return sk; } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) { /* Transport reassignment must not remove the binding. */ if (sock_flag(sk_vsock(vsk), SOCK_DEAD)) vsock_remove_bound(vsk); vsock_remove_connected(vsk); } EXPORT_SYMBOL_GPL(vsock_remove_sock); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)) { int i; spin_lock_bh(&vsock_table_lock); for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { struct vsock_sock *vsk; list_for_each_entry(vsk, &vsock_connected_table[i], connected_table) { if (vsk->transport != transport) continue; fn(sk_vsock(vsk)); } } spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_for_each_connected_socket); void vsock_add_pending(struct sock *listener, struct sock *pending) { struct vsock_sock *vlistener; struct vsock_sock *vpending; vlistener = vsock_sk(listener); vpending = vsock_sk(pending); sock_hold(pending); sock_hold(listener); list_add_tail(&vpending->pending_links, &vlistener->pending_links); } EXPORT_SYMBOL_GPL(vsock_add_pending); void vsock_remove_pending(struct sock *listener, struct sock *pending) { struct vsock_sock *vpending = vsock_sk(pending); list_del_init(&vpending->pending_links); sock_put(listener); sock_put(pending); } EXPORT_SYMBOL_GPL(vsock_remove_pending); void vsock_enqueue_accept(struct sock *listener, struct sock *connected) { struct vsock_sock *vlistener; struct vsock_sock *vconnected; vlistener = vsock_sk(listener); vconnected = vsock_sk(connected); sock_hold(connected); sock_hold(listener); list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue); } EXPORT_SYMBOL_GPL(vsock_enqueue_accept); static bool vsock_use_local_transport(unsigned int remote_cid) { if (!transport_local) return false; if (remote_cid == VMADDR_CID_LOCAL) return true; if (transport_g2h) { return remote_cid == transport_g2h->get_local_cid(); } else { return remote_cid == VMADDR_CID_HOST; } } static void vsock_deassign_transport(struct vsock_sock *vsk) { if (!vsk->transport) return; vsk->transport->destruct(vsk); module_put(vsk->transport->module); vsk->transport = NULL; } /* Assign a transport to a socket and call the .init transport callback. * * Note: for connection oriented socket this must be called when vsk->remote_addr * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if * g2h is not loaded, will use local transport; * - remote CID <= VMADDR_CID_HOST or h2g is not loaded or remote flags field * includes VMADDR_FLAG_TO_HOST flag value, will use guest->host transport; * - remote CID > VMADDR_CID_HOST will use host->guest transport; */ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) { const struct vsock_transport *new_transport; struct sock *sk = sk_vsock(vsk); unsigned int remote_cid = vsk->remote_addr.svm_cid; __u8 remote_flags; int ret; /* If the packet is coming with the source and destination CIDs higher * than VMADDR_CID_HOST, then a vsock channel where all the packets are * forwarded to the host should be established. Then the host will * need to forward the packets to the guest. * * The flag is set on the (listen) receive path (psk is not NULL). On * the connect path the flag can be set by the user space application. */ if (psk && vsk->local_addr.svm_cid > VMADDR_CID_HOST && vsk->remote_addr.svm_cid > VMADDR_CID_HOST) vsk->remote_addr.svm_flags |= VMADDR_FLAG_TO_HOST; remote_flags = vsk->remote_addr.svm_flags; switch (sk->sk_type) { case SOCK_DGRAM: new_transport = transport_dgram; break; case SOCK_STREAM: case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g || (remote_flags & VMADDR_FLAG_TO_HOST)) new_transport = transport_g2h; else new_transport = transport_h2g; break; default: return -ESOCKTNOSUPPORT; } if (vsk->transport) { if (vsk->transport == new_transport) return 0; /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we * have already held the sock lock. In the other cases, this * function is called on a new socket which is not assigned to * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); /* transport's release() and destruct() can touch some socket * state, since we are reassigning the socket to a new transport * during vsock_connect(), let's reset these fields to have a * clean state. */ sock_reset_flag(sk, SOCK_DONE); sk->sk_state = TCP_CLOSE; vsk->peer_shutdown = 0; } /* We increase the module refcnt to prevent the transport unloading * while there are open sockets assigned to it. */ if (!new_transport || !try_module_get(new_transport->module)) return -ENODEV; if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || !new_transport->seqpacket_allow(remote_cid)) { module_put(new_transport->module); return -ESOCKTNOSUPPORT; } } ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); return ret; } vsk->transport = new_transport; return 0; } EXPORT_SYMBOL_GPL(vsock_assign_transport); bool vsock_find_cid(unsigned int cid) { if (transport_g2h && cid == transport_g2h->get_local_cid()) return true; if (transport_h2g && cid == VMADDR_CID_HOST) return true; if (transport_local && cid == VMADDR_CID_LOCAL) return true; return false; } EXPORT_SYMBOL_GPL(vsock_find_cid); static struct sock *vsock_dequeue_accept(struct sock *listener) { struct vsock_sock *vlistener; struct vsock_sock *vconnected; vlistener = vsock_sk(listener); if (list_empty(&vlistener->accept_queue)) return NULL; vconnected = list_entry(vlistener->accept_queue.next, struct vsock_sock, accept_queue); list_del_init(&vconnected->accept_queue); sock_put(listener); /* The caller will need a reference on the connected socket so we let * it call sock_put(). */ return sk_vsock(vconnected); } static bool vsock_is_accept_queue_empty(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); return list_empty(&vsk->accept_queue); } static bool vsock_is_pending(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); return !list_empty(&vsk->pending_links); } static int vsock_send_shutdown(struct sock *sk, int mode) { struct vsock_sock *vsk = vsock_sk(sk); if (!vsk->transport) return -ENODEV; return vsk->transport->shutdown(vsk, mode); } static void vsock_pending_work(struct work_struct *work) { struct sock *sk; struct sock *listener; struct vsock_sock *vsk; bool cleanup; vsk = container_of(work, struct vsock_sock, pending_work.work); sk = sk_vsock(vsk); listener = vsk->listener; cleanup = true; lock_sock(listener); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (vsock_is_pending(sk)) { vsock_remove_pending(listener, sk); sk_acceptq_removed(listener); } else if (!vsk->rejected) { /* We are not on the pending list and accept() did not reject * us, so we must have been accepted by our user process. We * just need to drop our references to the sockets and be on * our way. */ cleanup = false; goto out; } /* We need to remove ourself from the global connected sockets list so * incoming packets can't find this socket, and to reduce the reference * count. */ vsock_remove_connected(vsk); sk->sk_state = TCP_CLOSE; out: release_sock(sk); release_sock(listener); if (cleanup) sock_put(sk); sock_put(sk); sock_put(listener); } /**** SOCKET OPERATIONS ****/ static int __vsock_bind_connectible(struct vsock_sock *vsk, struct sockaddr_vm *addr) { static u32 port; struct sockaddr_vm new_addr; if (!port) port = get_random_u32_above(LAST_RESERVED_PORT); vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); if (addr->svm_port == VMADDR_PORT_ANY) { bool found = false; unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { if (port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; if (!__vsock_find_bound_socket(&new_addr)) { found = true; break; } } if (!found) return -EADDRNOTAVAIL; } else { /* If port is in reserved range, ensure caller * has necessary privileges. */ if (addr->svm_port <= LAST_RESERVED_PORT && !capable(CAP_NET_BIND_SERVICE)) { return -EACCES; } if (__vsock_find_bound_socket(&new_addr)) return -EADDRINUSE; } vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); /* Remove connection oriented sockets from the unbound list and add them * to the hash table for easy lookup by its address. The unbound list * is simply an extra entry at the end of the hash table, a trick used * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); return 0; } static int __vsock_bind_dgram(struct vsock_sock *vsk, struct sockaddr_vm *addr) { return vsk->transport->dgram_bind(vsk, addr); } static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) { struct vsock_sock *vsk = vsock_sk(sk); int retval; /* First ensure this socket isn't already bound. */ if (vsock_addr_bound(&vsk->local_addr)) return -EINVAL; /* Now bind to the provided address or select appropriate values if * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY). Note that * like AF_INET prevents binding to a non-local IP address (in most * cases), we only allow binding to a local CID. */ if (addr->svm_cid != VMADDR_CID_ANY && !vsock_find_cid(addr->svm_cid)) return -EADDRNOTAVAIL; switch (sk->sk_socket->type) { case SOCK_STREAM: case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; case SOCK_DGRAM: retval = __vsock_bind_dgram(vsk, addr); break; default: retval = -EINVAL; break; } return retval; } static void vsock_connect_timeout(struct work_struct *work); static struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, gfp_t priority, unsigned short type, int kern) { struct sock *sk; struct vsock_sock *psk; struct vsock_sock *vsk; sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto, kern); if (!sk) return NULL; sock_init_data(sock, sk); /* sk->sk_type is normally set in sock_init_data, but only if sock is * non-NULL. We make sure that our sockets always have a type by * setting it here if needed. */ if (!sock) sk->sk_type = type; vsk = vsock_sk(sk); vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); sk->sk_destruct = vsock_sk_destruct; sk->sk_backlog_rcv = vsock_queue_rcv_skb; sock_reset_flag(sk, SOCK_DONE); INIT_LIST_HEAD(&vsk->bound_table); INIT_LIST_HEAD(&vsk->connected_table); vsk->listener = NULL; INIT_LIST_HEAD(&vsk->pending_links); INIT_LIST_HEAD(&vsk->accept_queue); vsk->rejected = false; vsk->sent_request = false; vsk->ignore_connecting_rst = false; vsk->peer_shutdown = 0; INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout); INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work); psk = parent ? vsock_sk(parent) : NULL; if (parent) { vsk->trusted = psk->trusted; vsk->owner = get_cred(psk->owner); vsk->connect_timeout = psk->connect_timeout; vsk->buffer_size = psk->buffer_size; vsk->buffer_min_size = psk->buffer_min_size; vsk->buffer_max_size = psk->buffer_max_size; security_sk_clone(parent, sk); } else { vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE; vsk->buffer_min_size = VSOCK_DEFAULT_BUFFER_MIN_SIZE; vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE; } return sk; } static bool sock_type_connectible(u16 type) { return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); } static void __vsock_release(struct sock *sk, int level) { struct vsock_sock *vsk; struct sock *pending; vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); /* Indicate to vsock_remove_sock() that the socket is being released and * can be removed from the bound_table. Unlike transport reassignment * case, where the socket must remain bound despite vsock_remove_sock() * being called from the transport release() callback. */ sock_set_flag(sk, SOCK_DEAD); if (vsk->transport) vsk->transport->release(vsk); else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; skb_queue_purge(&sk->sk_receive_queue); /* Clean up any sockets that never were accepted. */ while ((pending = vsock_dequeue_accept(sk)) != NULL) { __vsock_release(pending, SINGLE_DEPTH_NESTING); sock_put(pending); } release_sock(sk); sock_put(sk); } static void vsock_sk_destruct(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); /* Flush MSG_ZEROCOPY leftovers. */ __skb_queue_purge(&sk->sk_error_queue); vsock_deassign_transport(vsk); /* When clearing these addresses, there's no need to set the family and * possibly register the address family with the kernel. */ vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); put_cred(vsk->owner); } static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; err = sock_queue_rcv_skb(sk, skb); if (err) kfree_skb(skb); return err; } struct sock *vsock_create_connected(struct sock *parent) { return __vsock_create(sock_net(parent), NULL, parent, GFP_KERNEL, parent->sk_type, 0); } EXPORT_SYMBOL_GPL(vsock_create_connected); s64 vsock_stream_has_data(struct vsock_sock *vsk) { if (WARN_ON(!vsk->transport)) return 0; return vsk->transport->stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_data); s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); if (WARN_ON(!vsk->transport)) return 0; if (sk->sk_type == SOCK_SEQPACKET) return vsk->transport->seqpacket_has_data(vsk); else return vsock_stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_connectible_has_data); s64 vsock_stream_has_space(struct vsock_sock *vsk) { if (WARN_ON(!vsk->transport)) return 0; return vsk->transport->stream_has_space(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_space); void vsock_data_ready(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); if (vsock_stream_has_data(vsk) >= sk->sk_rcvlowat || sock_flag(sk, SOCK_DONE)) sk->sk_data_ready(sk); } EXPORT_SYMBOL_GPL(vsock_data_ready); /* Dummy callback required by sockmap. * See unconditional call of saved_close() in sock_map_close(). */ static void vsock_close(struct sock *sk, long timeout) { } static int vsock_release(struct socket *sock) { struct sock *sk = sock->sk; if (!sk) return 0; sk->sk_prot->close(sk, 0); __vsock_release(sk, 0); sock->sk = NULL; sock->state = SS_FREE; return 0; } static int vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { int err; struct sock *sk; struct sockaddr_vm *vm_addr; sk = sock->sk; if (vsock_addr_cast(addr, addr_len, &vm_addr) != 0) return -EINVAL; lock_sock(sk); err = __vsock_bind(sk, vm_addr); release_sock(sk); return err; } static int vsock_getname(struct socket *sock, struct sockaddr *addr, int peer) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *vm_addr; sk = sock->sk; vsk = vsock_sk(sk); err = 0; lock_sock(sk); if (peer) { if (sock->state != SS_CONNECTED) { err = -ENOTCONN; goto out; } vm_addr = &vsk->remote_addr; } else { vm_addr = &vsk->local_addr; } if (!vm_addr) { err = -EINVAL; goto out; } /* sys_getsockname() and sys_getpeername() pass us a * MAX_SOCK_ADDR-sized buffer and don't set addr_len. Unfortunately * that macro is defined in socket.c instead of .h, so we hardcode its * value here. */ BUILD_BUG_ON(sizeof(*vm_addr) > 128); memcpy(addr, vm_addr, sizeof(*vm_addr)); err = sizeof(*vm_addr); out: release_sock(sk); return err; } static int vsock_shutdown(struct socket *sock, int mode) { int err; struct sock *sk; /* User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode * here like the other address families do. Note also that the * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3), * which is what we want. */ mode++; if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; /* If this is a connection oriented socket and it is not connected then * bail out immediately. If it is a DGRAM socket then we must first * kick the socket so that it wakes up from any sleeping calls, for * example recv(), and then afterwards return the error. */ sk = sock->sk; lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; err = 0; } /* Receive and send shutdowns are treated alike. */ mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN); if (mode) { sk->sk_shutdown |= mode; sk->sk_state_change(sk); if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } } out: release_sock(sk); return err; } static __poll_t vsock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk; __poll_t mask; struct vsock_sock *vsk; sk = sock->sk; vsk = vsock_sk(sk); poll_wait(file, sk_sleep(sk), wait); mask = 0; if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) /* Signify that there has been an error on this socket. */ mask |= EPOLLERR; /* INET sockets treat local write shutdown and peer write shutdown as a * case of EPOLLHUP set. */ if ((sk->sk_shutdown == SHUTDOWN_MASK) || ((sk->sk_shutdown & SEND_SHUTDOWN) && (vsk->peer_shutdown & SEND_SHUTDOWN))) { mask |= EPOLLHUP; } if (sk->sk_shutdown & RCV_SHUTDOWN || vsk->peer_shutdown & SEND_SHUTDOWN) { mask |= EPOLLRDHUP; } if (sk_is_readable(sk)) mask |= EPOLLIN | EPOLLRDNORM; if (sock->type == SOCK_DGRAM) { /* For datagram sockets we can read if there is something in * the queue and write as long as the socket isn't shutdown for * sending. */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { mask |= EPOLLIN | EPOLLRDNORM; } if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; lock_sock(sk); transport = vsk->transport; /* Listening sockets that have connections in their accept * queue can be read. */ if (sk->sk_state == TCP_LISTEN && !vsock_is_accept_queue_empty(sk)) mask |= EPOLLIN | EPOLLRDNORM; /* If there is something in the queue then we can read. */ if (transport && transport->stream_is_active(vsk) && !(sk->sk_shutdown & RCV_SHUTDOWN)) { bool data_ready_now = false; int target = sock_rcvlowat(sk, 0, INT_MAX); int ret = transport->notify_poll_in( vsk, target, &data_ready_now); if (ret < 0) { mask |= EPOLLERR; } else { if (data_ready_now) mask |= EPOLLIN | EPOLLRDNORM; } } /* Sockets whose connections have been closed, reset, or * terminated should also be considered read, and we check the * shutdown flag for that. */ if (sk->sk_shutdown & RCV_SHUTDOWN || vsk->peer_shutdown & SEND_SHUTDOWN) { mask |= EPOLLIN | EPOLLRDNORM; } /* Connected sockets that can produce data can be written. */ if (transport && sk->sk_state == TCP_ESTABLISHED) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { bool space_avail_now = false; int ret = transport->notify_poll_out( vsk, 1, &space_avail_now); if (ret < 0) { mask |= EPOLLERR; } else { if (space_avail_now) /* Remove EPOLLWRBAND since INET * sockets are not setting it. */ mask |= EPOLLOUT | EPOLLWRNORM; } } } /* Simulate INET socket poll behaviors, which sets * EPOLLOUT|EPOLLWRNORM when peer is closed and nothing to read, * but local send is not shutdown. */ if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM; } release_sock(sk); } return mask; } static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor) { struct vsock_sock *vsk = vsock_sk(sk); if (WARN_ON_ONCE(!vsk->transport)) return -ENODEV; return vsk->transport->read_skb(vsk, read_actor); } static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; const struct vsock_transport *transport; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* For now, MSG_DONTWAIT is always assumed... */ err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); transport = vsk->transport; err = vsock_auto_bind(vsk); if (err) goto out; /* If the provided message contains an address, use that. Otherwise * fall back on the socket's remote handle (if it has been connected). */ if (msg->msg_name && vsock_addr_cast(msg->msg_name, msg->msg_namelen, &remote_addr) == 0) { /* Ensure this address is of the right type and is a valid * destination. */ if (remote_addr->svm_cid == VMADDR_CID_ANY) remote_addr->svm_cid = transport->get_local_cid(); if (!vsock_addr_bound(remote_addr)) { err = -EINVAL; goto out; } } else if (sock->state == SS_CONNECTED) { remote_addr = &vsk->remote_addr; if (remote_addr->svm_cid == VMADDR_CID_ANY) remote_addr->svm_cid = transport->get_local_cid(); /* XXX Should connect() or this function ensure remote_addr is * bound? */ if (!vsock_addr_bound(&vsk->remote_addr)) { err = -EINVAL; goto out; } } else { err = -EINVAL; goto out; } if (!transport->dgram_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; } err = transport->dgram_enqueue(vsk, remote_addr, msg, len); out: release_sock(sk); return err; } static int vsock_dgram_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; sk = sock->sk; vsk = vsock_sk(sk); err = vsock_addr_cast(addr, addr_len, &remote_addr); if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) { lock_sock(sk); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); sock->state = SS_UNCONNECTED; release_sock(sk); return 0; } else if (err != 0) return -EINVAL; lock_sock(sk); err = vsock_auto_bind(vsk); if (err) goto out; if (!vsk->transport->dgram_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; } memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); sock->state = SS_CONNECTED; /* sock map disallows redirection of non-TCP sockets with sk_state != * TCP_ESTABLISHED (see sock_map_redirect_allowed()), so we set * TCP_ESTABLISHED here to allow redirection of connected vsock dgrams. * * This doesn't seem to be abnormal state for datagram sockets, as the * same approach can be see in other datagram socket types as well * (such as unix sockets). */ sk->sk_state = TCP_ESTABLISHED; out: release_sock(sk); return err; } int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct vsock_sock *vsk = vsock_sk(sk); return vsk->transport->dgram_dequeue(vsk, msg, len, flags); } int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL struct sock *sk = sock->sk; const struct proto *prot; prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); static int vsock_do_ioctl(struct socket *sock, unsigned int cmd, int __user *arg) { struct sock *sk = sock->sk; struct vsock_sock *vsk; int ret; vsk = vsock_sk(sk); switch (cmd) { case SIOCOUTQ: { ssize_t n_bytes; if (!vsk->transport || !vsk->transport->unsent_bytes) { ret = -EOPNOTSUPP; break; } if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) { ret = -EINVAL; break; } n_bytes = vsk->transport->unsent_bytes(vsk); if (n_bytes < 0) { ret = n_bytes; break; } ret = put_user(n_bytes, arg); break; } default: ret = -ENOIOCTLCMD; } return ret; } static int vsock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int ret; lock_sock(sock->sk); ret = vsock_do_ioctl(sock, cmd, (int __user *)arg); release_sock(sock->sk); return ret; } static const struct proto_ops vsock_dgram_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = vsock_ioctl, .listen = sock_no_listen, .shutdown = vsock_shutdown, .sendmsg = vsock_dgram_sendmsg, .recvmsg = vsock_dgram_recvmsg, .mmap = sock_no_mmap, .read_skb = vsock_read_skb, }; static int vsock_transport_cancel_pkt(struct vsock_sock *vsk) { const struct vsock_transport *transport = vsk->transport; if (!transport || !transport->cancel_pkt) return -EOPNOTSUPP; return transport->cancel_pkt(vsk); } static void vsock_connect_timeout(struct work_struct *work) { struct sock *sk; struct vsock_sock *vsk; vsk = container_of(work, struct vsock_sock, connect_work.work); sk = sk_vsock(vsk); lock_sock(sk); if (sk->sk_state == TCP_SYN_SENT && (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_socket->state = SS_UNCONNECTED; sk->sk_err = ETIMEDOUT; sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); sock_put(sk); } static int vsock_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { int err; struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; struct sockaddr_vm *remote_addr; long timeout; DEFINE_WAIT(wait); err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); /* XXX AF_UNSPEC should make us disconnect like AF_INET. */ switch (sock->state) { case SS_CONNECTED: err = -EISCONN; goto out; case SS_DISCONNECTING: err = -EINVAL; goto out; case SS_CONNECTING: /* This continues on so we can move sock into the SS_CONNECTED * state once the connection has completed (at which point err * will be set to zero also). Otherwise, we will either wait * for the connection or return -EALREADY should this be a * non-blocking call. */ err = -EALREADY; if (flags & O_NONBLOCK) goto out; break; default: if ((sk->sk_state == TCP_LISTEN) || vsock_addr_cast(addr, addr_len, &remote_addr) != 0) { err = -EINVAL; goto out; } /* Set the remote address that we are connecting to. */ memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); err = vsock_assign_transport(vsk, NULL); if (err) goto out; transport = vsk->transport; /* The hypervisor and well-known contexts do not have socket * endpoints. */ if (!transport || !transport->stream_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -ENETUNREACH; goto out; } if (vsock_msgzerocopy_allow(transport)) { set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); } else if (sock_flag(sk, SOCK_ZEROCOPY)) { /* If this option was set before 'connect()', * when transport was unknown, check that this * feature is supported here. */ err = -EOPNOTSUPP; goto out; } err = vsock_auto_bind(vsk); if (err) goto out; sk->sk_state = TCP_SYN_SENT; err = transport->connect(vsk); if (err < 0) goto out; /* sk_err might have been set as a result of an earlier * (failed) connect attempt. */ sk->sk_err = 0; /* Mark sock as connecting and set the error code to in * progress in case this is a non-blocking connect. */ sock->state = SS_CONNECTING; err = -EINPROGRESS; } /* The receive path will handle all communication until we are able to * enter the connected state. Here we wait for the connection to be * completed or a notification of an error. */ timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* If the socket is already closing or it is in an error state, there * is no point in waiting. */ while (sk->sk_state != TCP_ESTABLISHED && sk->sk_state != TCP_CLOSING && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection * attempt, in case the peer doesn't respond in a * timely manner. We hold on to the socket until the * timeout fires. */ sock_hold(sk); /* If the timeout function is already scheduled, * reschedule it, then ungrab the socket refcount to * keep it balanced. */ if (mod_delayed_work(system_wq, &vsk->connect_work, timeout)) sock_put(sk); /* Skip ahead to preserve error code set above. */ goto out_wait; } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } if (sk->sk_err) { err = -sk->sk_err; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; } else { err = 0; } out_wait: finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; } static int vsock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *listener; int err; struct sock *connected; struct vsock_sock *vconnected; long timeout; DEFINE_WAIT(wait); err = 0; listener = sock->sk; lock_sock(listener); if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } if (listener->sk_state != TCP_LISTEN) { err = -EINVAL; goto out; } /* Wait for children sockets to appear; these are the new sockets * created upon connection establishment. */ timeout = sock_rcvtimeo(listener, arg->flags & O_NONBLOCK); prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); while ((connected = vsock_dequeue_accept(listener)) == NULL && listener->sk_err == 0) { release_sock(listener); timeout = schedule_timeout(timeout); finish_wait(sk_sleep(listener), &wait); lock_sock(listener); if (signal_pending(current)) { err = sock_intr_errno(timeout); goto out; } else if (timeout == 0) { err = -EAGAIN; goto out; } prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(listener), &wait); if (listener->sk_err) err = -listener->sk_err; if (connected) { sk_acceptq_removed(listener); lock_sock_nested(connected, SINGLE_DEPTH_NESTING); vconnected = vsock_sk(connected); /* If the listener socket has received an error, then we should * reject this socket and return. Note that we simply mark the * socket rejected, drop our reference, and let the cleanup * function handle the cleanup; the fact that we found it in * the listener's accept queue guarantees that the cleanup * function hasn't run yet. */ if (err) { vconnected->rejected = true; } else { newsock->state = SS_CONNECTED; sock_graft(connected, newsock); if (vsock_msgzerocopy_allow(vconnected->transport)) set_bit(SOCK_SUPPORT_ZC, &connected->sk_socket->flags); } release_sock(connected); sock_put(connected); } out: release_sock(listener); return err; } static int vsock_listen(struct socket *sock, int backlog) { int err; struct sock *sk; struct vsock_sock *vsk; sk = sock->sk; lock_sock(sk); if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } if (sock->state != SS_UNCONNECTED) { err = -EINVAL; goto out; } vsk = vsock_sk(sk); if (!vsock_addr_bound(&vsk->local_addr)) { err = -EINVAL; goto out; } sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; err = 0; out: release_sock(sk); return err; } static void vsock_update_buffer_size(struct vsock_sock *vsk, const struct vsock_transport *transport, u64 val) { if (val > vsk->buffer_max_size) val = vsk->buffer_max_size; if (val < vsk->buffer_min_size) val = vsk->buffer_min_size; if (val != vsk->buffer_size && transport && transport->notify_buffer_size) transport->notify_buffer_size(vsk, &val); vsk->buffer_size = val; } static int vsock_connectible_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { int err; struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; u64 val; if (level != AF_VSOCK && level != SOL_SOCKET) return -ENOPROTOOPT; #define COPY_IN(_v) \ do { \ if (optlen < sizeof(_v)) { \ err = -EINVAL; \ goto exit; \ } \ if (copy_from_sockptr(&_v, optval, sizeof(_v)) != 0) { \ err = -EFAULT; \ goto exit; \ } \ } while (0) err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); transport = vsk->transport; if (level == SOL_SOCKET) { int zerocopy; if (optname != SO_ZEROCOPY) { release_sock(sk); return sock_setsockopt(sock, level, optname, optval, optlen); } /* Use 'int' type here, because variable to * set this option usually has this type. */ COPY_IN(zerocopy); if (zerocopy < 0 || zerocopy > 1) { err = -EINVAL; goto exit; } if (transport && !vsock_msgzerocopy_allow(transport)) { err = -EOPNOTSUPP; goto exit; } sock_valbool_flag(sk, SOCK_ZEROCOPY, zerocopy); goto exit; } switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: COPY_IN(val); vsock_update_buffer_size(vsk, transport, val); break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: COPY_IN(val); vsk->buffer_max_size = val; vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: COPY_IN(val); vsk->buffer_min_size = val; vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { struct __kernel_sock_timeval tv; err = sock_copy_user_timeval(&tv, optval, optlen, optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); if (err) break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; } else { err = -ERANGE; } break; } default: err = -ENOPROTOOPT; break; } #undef COPY_IN exit: release_sock(sk); return err; } static int vsock_connectible_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct vsock_sock *vsk = vsock_sk(sk); union { u64 val64; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; } v; int lv = sizeof(v.val64); int len; if (level != AF_VSOCK) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; memset(&v, 0, sizeof(v)); switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: v.val64 = vsk->buffer_size; break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: v.val64 = vsk->buffer_max_size; break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: v.val64 = vsk->buffer_min_size; break; case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: lv = sock_get_timeout(vsk->connect_timeout, &v, optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; default: return -ENOPROTOOPT; } if (len < lv) return -EINVAL; if (len > lv) len = lv; if (copy_to_user(optval, &v, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; ssize_t total_written; long timeout; int err; struct vsock_transport_send_notify_data send_data; DEFINE_WAIT_FUNC(wait, woken_wake_function); sk = sock->sk; vsk = vsock_sk(sk); total_written = 0; err = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; lock_sock(sk); transport = vsk->transport; /* Callers should not provide a destination with connection oriented * sockets. */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; } /* Send data only if both sides are not shutdown in the direction. */ if (sk->sk_shutdown & SEND_SHUTDOWN || vsk->peer_shutdown & RCV_SHUTDOWN) { err = -EPIPE; goto out; } if (!transport || sk->sk_state != TCP_ESTABLISHED || !vsock_addr_bound(&vsk->local_addr)) { err = -ENOTCONN; goto out; } if (!vsock_addr_bound(&vsk->remote_addr)) { err = -EDESTADDRREQ; goto out; } if (msg->msg_flags & MSG_ZEROCOPY && !vsock_msgzerocopy_allow(transport)) { err = -EOPNOTSUPP; goto out; } /* Wait for room in the produce queue to enqueue our user's data. */ timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = transport->notify_send_init(vsk, &send_data); if (err < 0) goto out; while (total_written < len) { ssize_t written; add_wait_queue(sk_sleep(sk), &wait); while (vsock_stream_has_space(vsk) == 0 && sk->sk_err == 0 && !(sk->sk_shutdown & SEND_SHUTDOWN) && !(vsk->peer_shutdown & RCV_SHUTDOWN)) { /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } err = transport->notify_send_pre_block(vsk, &send_data); if (err < 0) { remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } release_sock(sk); timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } else if (timeout == 0) { err = -EAGAIN; remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } } remove_wait_queue(sk_sleep(sk), &wait); /* These checks occur both as part of and after the loop * conditional since we need to check before and after * sleeping. */ if (sk->sk_err) { err = -sk->sk_err; goto out_err; } else if ((sk->sk_shutdown & SEND_SHUTDOWN) || (vsk->peer_shutdown & RCV_SHUTDOWN)) { err = -EPIPE; goto out_err; } err = transport->notify_send_pre_enqueue(vsk, &send_data); if (err < 0) goto out_err; /* Note that enqueue will only write as many bytes as are free * in the produce queue, so we don't need to ensure len is * smaller than the queue size. It is the caller's * responsibility to check how many bytes we were able to send. */ if (sk->sk_type == SOCK_SEQPACKET) { written = transport->seqpacket_enqueue(vsk, msg, len - total_written); } else { written = transport->stream_enqueue(vsk, msg, len - total_written); } if (written < 0) { err = written; goto out_err; } total_written += written; err = transport->notify_send_post_enqueue( vsk, written, &send_data); if (err < 0) goto out_err; } out_err: if (total_written > 0) { /* Return number of written bytes only if: * 1) SOCK_STREAM socket. * 2) SOCK_SEQPACKET socket when whole buffer is sent. */ if (sk->sk_type == SOCK_STREAM || total_written == len) err = total_written; } out: if (sk->sk_type == SOCK_STREAM) err = sk_stream_error(sk, msg->msg_flags, err); release_sock(sk); return err; } static int vsock_connectible_wait_data(struct sock *sk, struct wait_queue_entry *wait, long timeout, struct vsock_transport_recv_notify_data *recv_data, size_t target) { const struct vsock_transport *transport; struct vsock_sock *vsk; s64 data; int err; vsk = vsock_sk(sk); err = 0; transport = vsk->transport; while (1) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); data = vsock_connectible_has_data(vsk); if (data != 0) break; if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) || (vsk->peer_shutdown & SEND_SHUTDOWN)) { break; } /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; break; } if (recv_data) { err = transport->notify_recv_pre_block(vsk, target, recv_data); if (err < 0) break; } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); break; } else if (timeout == 0) { err = -EAGAIN; break; } } finish_wait(sk_sleep(sk), wait); if (err) return err; /* Internal transport error when checking for available * data. XXX This should be changed to a connection * reset in a later change. */ if (data < 0) return -ENOMEM; return data; } static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct vsock_transport_recv_notify_data recv_data; const struct vsock_transport *transport; struct vsock_sock *vsk; ssize_t copied; size_t target; long timeout; int err; DEFINE_WAIT(wait); vsk = vsock_sk(sk); transport = vsk->transport; /* We must not copy less than target bytes into the user's buffer * before returning successfully, so we wait for the consume queue to * have that much data to consume before dequeueing. Note that this * makes it impossible to handle cases where target is greater than the * queue size. */ target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); if (target >= transport->stream_rcvhiwat(vsk)) { err = -ENOMEM; goto out; } timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); copied = 0; err = transport->notify_recv_init(vsk, target, &recv_data); if (err < 0) goto out; while (1) { ssize_t read; err = vsock_connectible_wait_data(sk, &wait, timeout, &recv_data, target); if (err <= 0) break; err = transport->notify_recv_pre_dequeue(vsk, target, &recv_data); if (err < 0) break; read = transport->stream_dequeue(vsk, msg, len - copied, flags); if (read < 0) { err = read; break; } copied += read; err = transport->notify_recv_post_dequeue(vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) goto out; if (read >= target || flags & MSG_PEEK) break; target -= read; } if (sk->sk_err) err = -sk->sk_err; else if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; if (copied > 0) err = copied; out: return err; } static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { const struct vsock_transport *transport; struct vsock_sock *vsk; ssize_t msg_len; long timeout; int err = 0; DEFINE_WAIT(wait); vsk = vsock_sk(sk); transport = vsk->transport; timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); if (err <= 0) goto out; msg_len = transport->seqpacket_dequeue(vsk, msg, flags); if (msg_len < 0) { err = msg_len; goto out; } if (sk->sk_err) { err = -sk->sk_err; } else if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; } else { /* User sets MSG_TRUNC, so return real length of * packet. */ if (flags & MSG_TRUNC) err = msg_len; else err = len - msg_data_left(msg); /* Always set MSG_TRUNC if real length of packet is * bigger than user's buffer. */ if (msg_len > len) msg->msg_flags |= MSG_TRUNC; } out: return err; } int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; int err; sk = sock->sk; if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_VSOCK, VSOCK_RECVERR); vsk = vsock_sk(sk); err = 0; lock_sock(sk); transport = vsk->transport; if (!transport || sk->sk_state != TCP_ESTABLISHED) { /* Recvmsg is supposed to return 0 if a peer performs an * orderly shutdown. Differentiate between that case and when a * peer has not connected or a local shutdown occurred with the * SOCK_DONE flag. */ if (sock_flag(sk, SOCK_DONE)) err = 0; else err = -ENOTCONN; goto out; } if (flags & MSG_OOB) { err = -EOPNOTSUPP; goto out; } /* We don't check peer_shutdown flag here since peer may actually shut * down, but there can be data in the queue that a local socket can * receive. */ if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; goto out; } /* It is valid on Linux to pass in a zero-length receive buffer. This * is not an error. We may as well bail out now. */ if (!len) { err = 0; goto out; } if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); return err; } int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL struct sock *sk = sock->sk; const struct proto *prot; prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif return __vsock_connectible_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) { const struct vsock_transport *transport; struct vsock_sock *vsk; vsk = vsock_sk(sk); if (val > vsk->buffer_size) return -EINVAL; transport = vsk->transport; if (transport && transport->notify_set_rcvlowat) { int err; err = transport->notify_set_rcvlowat(vsk, val); if (err) return err; } WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); return 0; } static const struct proto_ops vsock_stream_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, .getsockopt = vsock_connectible_getsockopt, .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .set_rcvlowat = vsock_set_rcvlowat, .read_skb = vsock_read_skb, }; static const struct proto_ops vsock_seqpacket_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, .getsockopt = vsock_connectible_getsockopt, .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .read_skb = vsock_read_skb, }; static int vsock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct vsock_sock *vsk; struct sock *sk; int ret; if (!sock) return -EINVAL; if (protocol && protocol != PF_VSOCK) return -EPROTONOSUPPORT; switch (sock->type) { case SOCK_DGRAM: sock->ops = &vsock_dgram_ops; break; case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; case SOCK_SEQPACKET: sock->ops = &vsock_seqpacket_ops; break; default: return -ESOCKTNOSUPPORT; } sock->state = SS_UNCONNECTED; sk = __vsock_create(net, sock, NULL, GFP_KERNEL, 0, kern); if (!sk) return -ENOMEM; vsk = vsock_sk(sk); if (sock->type == SOCK_DGRAM) { ret = vsock_assign_transport(vsk, NULL); if (ret < 0) { sock->sk = NULL; sock_put(sk); return ret; } } /* SOCK_DGRAM doesn't have 'setsockopt' callback set in its * proto_ops, so there is no handler for custom logic. */ if (sock_type_connectible(sock->type)) set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); vsock_insert_unbound(vsk); return 0; } static const struct net_proto_family vsock_family_ops = { .family = AF_VSOCK, .create = vsock_create, .owner = THIS_MODULE, }; static long vsock_dev_do_ioctl(struct file *filp, unsigned int cmd, void __user *ptr) { u32 __user *p = ptr; u32 cid = VMADDR_CID_ANY; int retval = 0; switch (cmd) { case IOCTL_VM_SOCKETS_GET_LOCAL_CID: /* To be compatible with the VMCI behavior, we prioritize the * guest CID instead of well-know host CID (VMADDR_CID_HOST). */ if (transport_g2h) cid = transport_g2h->get_local_cid(); else if (transport_h2g) cid = transport_h2g->get_local_cid(); if (put_user(cid, p) != 0) retval = -EFAULT; break; default: retval = -ENOIOCTLCMD; } return retval; } static long vsock_dev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return vsock_dev_do_ioctl(filp, cmd, (void __user *)arg); } #ifdef CONFIG_COMPAT static long vsock_dev_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return vsock_dev_do_ioctl(filp, cmd, compat_ptr(arg)); } #endif static const struct file_operations vsock_device_ops = { .owner = THIS_MODULE, .unlocked_ioctl = vsock_dev_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = vsock_dev_compat_ioctl, #endif .open = nonseekable_open, }; static struct miscdevice vsock_device = { .name = "vsock", .fops = &vsock_device_ops, }; static int __init vsock_init(void) { int err = 0; vsock_init_tables(); vsock_proto.owner = THIS_MODULE; vsock_device.minor = MISC_DYNAMIC_MINOR; err = misc_register(&vsock_device); if (err) { pr_err("Failed to register misc device\n"); goto err_reset_transport; } err = proto_register(&vsock_proto, 1); /* we want our slab */ if (err) { pr_err("Cannot register vsock protocol\n"); goto err_deregister_misc; } err = sock_register(&vsock_family_ops); if (err) { pr_err("could not register af_vsock (%d) address family: %d\n", AF_VSOCK, err); goto err_unregister_proto; } vsock_bpf_build_proto(); return 0; err_unregister_proto: proto_unregister(&vsock_proto); err_deregister_misc: misc_deregister(&vsock_device); err_reset_transport: return err; } static void __exit vsock_exit(void) { misc_deregister(&vsock_device); sock_unregister(AF_VSOCK); proto_unregister(&vsock_proto); } const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk) { return vsk->transport; } EXPORT_SYMBOL_GPL(vsock_core_get_transport); int vsock_core_register(const struct vsock_transport *t, int features) { const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local; int err = mutex_lock_interruptible(&vsock_register_mutex); if (err) return err; t_h2g = transport_h2g; t_g2h = transport_g2h; t_dgram = transport_dgram; t_local = transport_local; if (features & VSOCK_TRANSPORT_F_H2G) { if (t_h2g) { err = -EBUSY; goto err_busy; } t_h2g = t; } if (features & VSOCK_TRANSPORT_F_G2H) { if (t_g2h) { err = -EBUSY; goto err_busy; } t_g2h = t; } if (features & VSOCK_TRANSPORT_F_DGRAM) { if (t_dgram) { err = -EBUSY; goto err_busy; } t_dgram = t; } if (features & VSOCK_TRANSPORT_F_LOCAL) { if (t_local) { err = -EBUSY; goto err_busy; } t_local = t; } transport_h2g = t_h2g; transport_g2h = t_g2h; transport_dgram = t_dgram; transport_local = t_local; err_busy: mutex_unlock(&vsock_register_mutex); return err; } EXPORT_SYMBOL_GPL(vsock_core_register); void vsock_core_unregister(const struct vsock_transport *t) { mutex_lock(&vsock_register_mutex); if (transport_h2g == t) transport_h2g = NULL; if (transport_g2h == t) transport_g2h = NULL; if (transport_dgram == t) transport_dgram = NULL; if (transport_local == t) transport_local = NULL; mutex_unlock(&vsock_register_mutex); } EXPORT_SYMBOL_GPL(vsock_core_unregister); module_init(vsock_init); module_exit(vsock_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); MODULE_VERSION("1.0.2.0-k"); MODULE_LICENSE("GPL v2"); |
| 30 30 1 1 24 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 | // SPDX-License-Identifier: GPL-2.0-only /* iptables module for using new netfilter netlink queue * * (C) 2005 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_NFQUEUE.h> #include <net/netfilter/nf_queue.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet forwarding to netlink"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_NFQUEUE"); MODULE_ALIAS("ip6t_NFQUEUE"); MODULE_ALIAS("arpt_NFQUEUE"); static u32 jhash_initval __read_mostly; static unsigned int nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info *tinfo = par->targinfo; return NF_QUEUE_NR(tinfo->queuenum); } static unsigned int nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v1 *info = par->targinfo; u32 queue = info->queuenum; if (info->queues_total > 1) { queue = nfqueue_hash(skb, queue, info->queues_total, xt_family(par), jhash_initval); } return NF_QUEUE_NR(queue); } static unsigned int nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v2 *info = par->targinfo; unsigned int ret = nfqueue_tg_v1(skb, par); if (info->bypass) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; return ret; } static int nfqueue_tg_check(const struct xt_tgchk_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 maxid; init_hashrandom(&jhash_initval); if (info->queues_total == 0) { pr_info_ratelimited("number of total queues is 0\n"); return -EINVAL; } maxid = info->queues_total - 1 + info->queuenum; if (maxid > 0xffff) { pr_info_ratelimited("number of queues (%u) out of range (got %u)\n", info->queues_total, maxid); return -ERANGE; } if (par->target->revision == 2 && info->flags > 1) return -EINVAL; if (par->target->revision == 3 && info->flags & ~NFQ_FLAG_MASK) return -EINVAL; return 0; } static unsigned int nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 queue = info->queuenum; int ret; if (info->queues_total > 1) { if (info->flags & NFQ_FLAG_CPU_FANOUT) { int cpu = smp_processor_id(); queue = info->queuenum + cpu % info->queues_total; } else { queue = nfqueue_hash(skb, queue, info->queues_total, xt_family(par), jhash_initval); } } ret = NF_QUEUE_NR(queue); if (info->flags & NFQ_FLAG_BYPASS) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; return ret; } static struct xt_target nfqueue_tg_reg[] __read_mostly = { { .name = "NFQUEUE", .family = NFPROTO_UNSPEC, .target = nfqueue_tg, .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v1, .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 2, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v2, .targetsize = sizeof(struct xt_NFQ_info_v2), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 3, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v3, .targetsize = sizeof(struct xt_NFQ_info_v3), .me = THIS_MODULE, }, }; static int __init nfqueue_tg_init(void) { return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } static void __exit nfqueue_tg_exit(void) { xt_unregister_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } module_init(nfqueue_tg_init); module_exit(nfqueue_tg_exit); |
| 55 1 3 3 53 53 53 79 79 79 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ #include "network-coding.h" #include "main.h" #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_packet.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> #include "hash.h" #include "log.h" #include "originator.h" #include "routing.h" #include "send.h" #include "tvlv.h" static struct lock_class_key batadv_nc_coding_hash_lock_class_key; static struct lock_class_key batadv_nc_decoding_hash_lock_class_key; static void batadv_nc_worker(struct work_struct *work); static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); /** * batadv_nc_init() - one-time initialization for network coding * * Return: 0 on success or negative error number in case of failure */ int __init batadv_nc_init(void) { /* Register our packet type */ return batadv_recv_handler_register(BATADV_CODED, batadv_nc_recv_coded_packet); } /** * batadv_nc_start_timer() - initialise the nc periodic worker * @bat_priv: the bat priv with all the mesh interface information */ static void batadv_nc_start_timer(struct batadv_priv *bat_priv) { queue_delayed_work(batadv_event_workqueue, &bat_priv->nc.work, msecs_to_jiffies(10)); } /** * batadv_nc_tvlv_container_update() - update the network coding tvlv container * after network coding setting change * @bat_priv: the bat priv with all the mesh interface information */ static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv) { char nc_mode; nc_mode = atomic_read(&bat_priv->network_coding); switch (nc_mode) { case 0: batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_NC, 1); break; case 1: batadv_tvlv_container_register(bat_priv, BATADV_TVLV_NC, 1, NULL, 0); break; } } /** * batadv_nc_status_update() - update the network coding tvlv container after * network coding setting change * @net_dev: the mesh interface net device */ void batadv_nc_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); batadv_nc_tvlv_container_update(bat_priv); } /** * batadv_nc_tvlv_ogm_handler_v1() - process incoming nc tvlv container * @bat_priv: the bat priv with all the mesh interface information * @orig: the orig_node of the ogm * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) * @tvlv_value: tvlv buffer containing the gateway data * @tvlv_value_len: tvlv buffer length */ static void batadv_nc_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len) { if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) clear_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities); else set_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities); } /** * batadv_nc_mesh_init() - initialise coding hash table and start housekeeping * @bat_priv: the bat priv with all the mesh interface information * * Return: 0 on success or negative error number in case of failure */ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) { bat_priv->nc.timestamp_fwd_flush = jiffies; bat_priv->nc.timestamp_sniffed_purge = jiffies; if (bat_priv->nc.coding_hash || bat_priv->nc.decoding_hash) return 0; bat_priv->nc.coding_hash = batadv_hash_new(128); if (!bat_priv->nc.coding_hash) goto err; batadv_hash_set_lock_class(bat_priv->nc.coding_hash, &batadv_nc_coding_hash_lock_class_key); bat_priv->nc.decoding_hash = batadv_hash_new(128); if (!bat_priv->nc.decoding_hash) { batadv_hash_destroy(bat_priv->nc.coding_hash); goto err; } batadv_hash_set_lock_class(bat_priv->nc.decoding_hash, &batadv_nc_decoding_hash_lock_class_key); INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); batadv_nc_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_nc_tvlv_ogm_handler_v1, NULL, NULL, BATADV_TVLV_NC, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_nc_tvlv_container_update(bat_priv); return 0; err: return -ENOMEM; } /** * batadv_nc_init_bat_priv() - initialise the nc specific bat_priv variables * @bat_priv: the bat priv with all the mesh interface information */ void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) { atomic_set(&bat_priv->network_coding, 0); bat_priv->nc.min_tq = 200; bat_priv->nc.max_fwd_delay = 10; bat_priv->nc.max_buffer_time = 200; } /** * batadv_nc_init_orig() - initialise the nc fields of an orig_node * @orig_node: the orig_node which is going to be initialised */ void batadv_nc_init_orig(struct batadv_orig_node *orig_node) { INIT_LIST_HEAD(&orig_node->in_coding_list); INIT_LIST_HEAD(&orig_node->out_coding_list); spin_lock_init(&orig_node->in_coding_list_lock); spin_lock_init(&orig_node->out_coding_list_lock); } /** * batadv_nc_node_release() - release nc_node from lists and queue for free * after rcu grace period * @ref: kref pointer of the nc_node */ static void batadv_nc_node_release(struct kref *ref) { struct batadv_nc_node *nc_node; nc_node = container_of(ref, struct batadv_nc_node, refcount); batadv_orig_node_put(nc_node->orig_node); kfree_rcu(nc_node, rcu); } /** * batadv_nc_node_put() - decrement the nc_node refcounter and possibly * release it * @nc_node: nc_node to be free'd */ static void batadv_nc_node_put(struct batadv_nc_node *nc_node) { if (!nc_node) return; kref_put(&nc_node->refcount, batadv_nc_node_release); } /** * batadv_nc_path_release() - release nc_path from lists and queue for free * after rcu grace period * @ref: kref pointer of the nc_path */ static void batadv_nc_path_release(struct kref *ref) { struct batadv_nc_path *nc_path; nc_path = container_of(ref, struct batadv_nc_path, refcount); kfree_rcu(nc_path, rcu); } /** * batadv_nc_path_put() - decrement the nc_path refcounter and possibly * release it * @nc_path: nc_path to be free'd */ static void batadv_nc_path_put(struct batadv_nc_path *nc_path) { if (!nc_path) return; kref_put(&nc_path->refcount, batadv_nc_path_release); } /** * batadv_nc_packet_free() - frees nc packet * @nc_packet: the nc packet to free * @dropped: whether the packet is freed because is dropped */ static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet, bool dropped) { if (dropped) kfree_skb(nc_packet->skb); else consume_skb(nc_packet->skb); batadv_nc_path_put(nc_packet->nc_path); kfree(nc_packet); } /** * batadv_nc_to_purge_nc_node() - checks whether an nc node has to be purged * @bat_priv: the bat priv with all the mesh interface information * @nc_node: the nc node to check * * Return: true if the entry has to be purged now, false otherwise */ static bool batadv_nc_to_purge_nc_node(struct batadv_priv *bat_priv, struct batadv_nc_node *nc_node) { if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) return true; return batadv_has_timed_out(nc_node->last_seen, BATADV_NC_NODE_TIMEOUT); } /** * batadv_nc_to_purge_nc_path_coding() - checks whether an nc path has timed out * @bat_priv: the bat priv with all the mesh interface information * @nc_path: the nc path to check * * Return: true if the entry has to be purged now, false otherwise */ static bool batadv_nc_to_purge_nc_path_coding(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path) { if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) return true; /* purge the path when no packets has been added for 10 times the * max_fwd_delay time */ return batadv_has_timed_out(nc_path->last_valid, bat_priv->nc.max_fwd_delay * 10); } /** * batadv_nc_to_purge_nc_path_decoding() - checks whether an nc path has timed * out * @bat_priv: the bat priv with all the mesh interface information * @nc_path: the nc path to check * * Return: true if the entry has to be purged now, false otherwise */ static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path) { if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) return true; /* purge the path when no packets has been added for 10 times the * max_buffer time */ return batadv_has_timed_out(nc_path->last_valid, bat_priv->nc.max_buffer_time * 10); } /** * batadv_nc_purge_orig_nc_nodes() - go through list of nc nodes and purge stale * entries * @bat_priv: the bat priv with all the mesh interface information * @list: list of nc nodes * @lock: nc node list lock * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the nc node as argument and has to return * a boolean value: true if the entry has to be deleted, false * otherwise */ static void batadv_nc_purge_orig_nc_nodes(struct batadv_priv *bat_priv, struct list_head *list, spinlock_t *lock, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_node *)) { struct batadv_nc_node *nc_node, *nc_node_tmp; /* For each nc_node in list */ spin_lock_bh(lock); list_for_each_entry_safe(nc_node, nc_node_tmp, list, list) { /* if an helper function has been passed as parameter, * ask it if the entry has to be purged or not */ if (to_purge && !to_purge(bat_priv, nc_node)) continue; batadv_dbg(BATADV_DBG_NC, bat_priv, "Removing nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); list_del_rcu(&nc_node->list); batadv_nc_node_put(nc_node); } spin_unlock_bh(lock); } /** * batadv_nc_purge_orig() - purges all nc node data attached of the given * originator * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig_node with the nc node entries to be purged * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the nc node as argument and has to return * a boolean value: true is the entry has to be deleted, false * otherwise */ void batadv_nc_purge_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_node *)) { /* Check ingoing nc_node's of this orig_node */ batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->in_coding_list, &orig_node->in_coding_list_lock, to_purge); /* Check outgoing nc_node's of this orig_node */ batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->out_coding_list, &orig_node->out_coding_list_lock, to_purge); } /** * batadv_nc_purge_orig_hash() - traverse entire originator hash to check if * they have timed out nc nodes * @bat_priv: the bat priv with all the mesh interface information */ static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node; u32 i; if (!hash) return; /* For each orig_node */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) batadv_nc_purge_orig(bat_priv, orig_node, batadv_nc_to_purge_nc_node); rcu_read_unlock(); } } /** * batadv_nc_purge_paths() - traverse all nc paths part of the hash and remove * unused ones * @bat_priv: the bat priv with all the mesh interface information * @hash: hash table containing the nc paths to check * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the nc node as argument and has to return * a boolean value: true is the entry has to be deleted, false * otherwise */ static void batadv_nc_purge_paths(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_path *)) { struct hlist_head *head; struct hlist_node *node_tmp; struct batadv_nc_path *nc_path; spinlock_t *lock; /* Protects lists in hash */ u32 i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; lock = &hash->list_locks[i]; /* For each nc_path in this bin */ spin_lock_bh(lock); hlist_for_each_entry_safe(nc_path, node_tmp, head, hash_entry) { /* if an helper function has been passed as parameter, * ask it if the entry has to be purged or not */ if (to_purge && !to_purge(bat_priv, nc_path)) continue; /* purging an non-empty nc_path should never happen, but * is observed under high CPU load. Delay the purging * until next iteration to allow the packet_list to be * emptied first. */ if (!unlikely(list_empty(&nc_path->packet_list))) { net_ratelimited_function(printk, KERN_WARNING "Skipping free of non-empty nc_path (%pM -> %pM)!\n", nc_path->prev_hop, nc_path->next_hop); continue; } /* nc_path is unused, so remove it */ batadv_dbg(BATADV_DBG_NC, bat_priv, "Remove nc_path %pM -> %pM\n", nc_path->prev_hop, nc_path->next_hop); hlist_del_rcu(&nc_path->hash_entry); batadv_nc_path_put(nc_path); } spin_unlock_bh(lock); } } /** * batadv_nc_hash_key_gen() - computes the nc_path hash key * @key: buffer to hold the final hash key * @src: source ethernet mac address going into the hash key * @dst: destination ethernet mac address going into the hash key */ static void batadv_nc_hash_key_gen(struct batadv_nc_path *key, const char *src, const char *dst) { memcpy(key->prev_hop, src, sizeof(key->prev_hop)); memcpy(key->next_hop, dst, sizeof(key->next_hop)); } /** * batadv_nc_hash_choose() - compute the hash value for an nc path * @data: data to hash * @size: size of the hash table * * Return: the selected index in the hash table for the given data. */ static u32 batadv_nc_hash_choose(const void *data, u32 size) { const struct batadv_nc_path *nc_path = data; u32 hash = 0; hash = jhash(&nc_path->prev_hop, sizeof(nc_path->prev_hop), hash); hash = jhash(&nc_path->next_hop, sizeof(nc_path->next_hop), hash); return hash % size; } /** * batadv_nc_hash_compare() - comparing function used in the network coding hash * tables * @node: node in the local table * @data2: second object to compare the node to * * Return: true if the two entry are the same, false otherwise */ static bool batadv_nc_hash_compare(const struct hlist_node *node, const void *data2) { const struct batadv_nc_path *nc_path1, *nc_path2; nc_path1 = container_of(node, struct batadv_nc_path, hash_entry); nc_path2 = data2; /* Return 1 if the two keys are identical */ if (!batadv_compare_eth(nc_path1->prev_hop, nc_path2->prev_hop)) return false; if (!batadv_compare_eth(nc_path1->next_hop, nc_path2->next_hop)) return false; return true; } /** * batadv_nc_hash_find() - search for an existing nc path and return it * @hash: hash table containing the nc path * @data: search key * * Return: the nc_path if found, NULL otherwise. */ static struct batadv_nc_path * batadv_nc_hash_find(struct batadv_hashtable *hash, void *data) { struct hlist_head *head; struct batadv_nc_path *nc_path, *nc_path_tmp = NULL; int index; if (!hash) return NULL; index = batadv_nc_hash_choose(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, head, hash_entry) { if (!batadv_nc_hash_compare(&nc_path->hash_entry, data)) continue; if (!kref_get_unless_zero(&nc_path->refcount)) continue; nc_path_tmp = nc_path; break; } rcu_read_unlock(); return nc_path_tmp; } /** * batadv_nc_send_packet() - send non-coded packet and free nc_packet struct * @nc_packet: the nc packet to send */ static void batadv_nc_send_packet(struct batadv_nc_packet *nc_packet) { batadv_send_unicast_skb(nc_packet->skb, nc_packet->neigh_node); nc_packet->skb = NULL; batadv_nc_packet_free(nc_packet, false); } /** * batadv_nc_sniffed_purge() - Checks timestamp of given sniffed nc_packet. * @bat_priv: the bat priv with all the mesh interface information * @nc_path: the nc path the packet belongs to * @nc_packet: the nc packet to be checked * * Checks whether the given sniffed (overheard) nc_packet has hit its buffering * timeout. If so, the packet is no longer kept and the entry deleted from the * queue. Has to be called with the appropriate locks. * * Return: false as soon as the entry in the fifo queue has not been timed out * yet and true otherwise. */ static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path, struct batadv_nc_packet *nc_packet) { unsigned long timeout = bat_priv->nc.max_buffer_time; bool res = false; lockdep_assert_held(&nc_path->packet_list_lock); /* Packets are added to tail, so the remaining packets did not time * out and we can stop processing the current queue */ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE && !batadv_has_timed_out(nc_packet->timestamp, timeout)) goto out; /* purge nc packet */ list_del(&nc_packet->list); batadv_nc_packet_free(nc_packet, true); res = true; out: return res; } /** * batadv_nc_fwd_flush() - Checks the timestamp of the given nc packet. * @bat_priv: the bat priv with all the mesh interface information * @nc_path: the nc path the packet belongs to * @nc_packet: the nc packet to be checked * * Checks whether the given nc packet has hit its forward timeout. If so, the * packet is no longer delayed, immediately sent and the entry deleted from the * queue. Has to be called with the appropriate locks. * * Return: false as soon as the entry in the fifo queue has not been timed out * yet and true otherwise. */ static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv, struct batadv_nc_path *nc_path, struct batadv_nc_packet *nc_packet) { unsigned long timeout = bat_priv->nc.max_fwd_delay; lockdep_assert_held(&nc_path->packet_list_lock); /* Packets are added to tail, so the remaining packets did not time * out and we can stop processing the current queue */ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE && !batadv_has_timed_out(nc_packet->timestamp, timeout)) return false; /* Send packet */ batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, nc_packet->skb->len + ETH_HLEN); list_del(&nc_packet->list); batadv_nc_send_packet(nc_packet); return true; } /** * batadv_nc_process_nc_paths() - traverse given nc packet pool and free timed * out nc packets * @bat_priv: the bat priv with all the mesh interface information * @hash: to be processed hash table * @process_fn: Function called to process given nc packet. Should return true * to encourage this function to proceed with the next packet. * Otherwise the rest of the current queue is skipped. */ static void batadv_nc_process_nc_paths(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, bool (*process_fn)(struct batadv_priv *, struct batadv_nc_path *, struct batadv_nc_packet *)) { struct hlist_head *head; struct batadv_nc_packet *nc_packet, *nc_packet_tmp; struct batadv_nc_path *nc_path; bool ret; int i; if (!hash) return; /* Loop hash table bins */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; /* Loop coding paths */ rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, head, hash_entry) { /* Loop packets */ spin_lock_bh(&nc_path->packet_list_lock); list_for_each_entry_safe(nc_packet, nc_packet_tmp, &nc_path->packet_list, list) { ret = process_fn(bat_priv, nc_path, nc_packet); if (!ret) break; } spin_unlock_bh(&nc_path->packet_list_lock); } rcu_read_unlock(); } } /** * batadv_nc_worker() - periodic task for housekeeping related to network * coding * @work: kernel work struct */ static void batadv_nc_worker(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv_nc *priv_nc; struct batadv_priv *bat_priv; unsigned long timeout; delayed_work = to_delayed_work(work); priv_nc = container_of(delayed_work, struct batadv_priv_nc, work); bat_priv = container_of(priv_nc, struct batadv_priv, nc); batadv_nc_purge_orig_hash(bat_priv); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, batadv_nc_to_purge_nc_path_coding); batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, batadv_nc_to_purge_nc_path_decoding); timeout = bat_priv->nc.max_fwd_delay; if (batadv_has_timed_out(bat_priv->nc.timestamp_fwd_flush, timeout)) { batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.coding_hash, batadv_nc_fwd_flush); bat_priv->nc.timestamp_fwd_flush = jiffies; } if (batadv_has_timed_out(bat_priv->nc.timestamp_sniffed_purge, bat_priv->nc.max_buffer_time)) { batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.decoding_hash, batadv_nc_sniffed_purge); bat_priv->nc.timestamp_sniffed_purge = jiffies; } /* Schedule a new check */ batadv_nc_start_timer(bat_priv); } /** * batadv_can_nc_with_orig() - checks whether the given orig node is suitable * for coding or not * @bat_priv: the bat priv with all the mesh interface information * @orig_node: neighboring orig node which may be used as nc candidate * @ogm_packet: incoming ogm packet also used for the checks * * Return: true if: * 1) The OGM must have the most recent sequence number. * 2) The TTL must be decremented by one and only one. * 3) The OGM must be received from the first hop from orig_node. * 4) The TQ value of the OGM must be above bat_priv->nc.min_tq. */ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_ogm_packet *ogm_packet) { struct batadv_orig_ifinfo *orig_ifinfo; u32 last_real_seqno; u8 last_ttl; orig_ifinfo = batadv_orig_ifinfo_get(orig_node, BATADV_IF_DEFAULT); if (!orig_ifinfo) return false; last_ttl = orig_ifinfo->last_ttl; last_real_seqno = orig_ifinfo->last_real_seqno; batadv_orig_ifinfo_put(orig_ifinfo); if (last_real_seqno != ntohl(ogm_packet->seqno)) return false; if (last_ttl != ogm_packet->ttl + 1) return false; if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender)) return false; if (ogm_packet->tq < bat_priv->nc.min_tq) return false; return true; } /** * batadv_nc_find_nc_node() - search for an existing nc node and return it * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet * (can be equal to orig_node) * @in_coding: traverse incoming or outgoing network coding list * * Return: the nc_node if found, NULL otherwise. */ static struct batadv_nc_node * batadv_nc_find_nc_node(struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, bool in_coding) { struct batadv_nc_node *nc_node, *nc_node_out = NULL; struct list_head *list; if (in_coding) list = &orig_neigh_node->in_coding_list; else list = &orig_neigh_node->out_coding_list; /* Traverse list of nc_nodes to orig_node */ rcu_read_lock(); list_for_each_entry_rcu(nc_node, list, list) { if (!batadv_compare_eth(nc_node->addr, orig_node->orig)) continue; if (!kref_get_unless_zero(&nc_node->refcount)) continue; /* Found a match */ nc_node_out = nc_node; break; } rcu_read_unlock(); return nc_node_out; } /** * batadv_nc_get_nc_node() - retrieves an nc node or creates the entry if it was * not found * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet * (can be equal to orig_node) * @in_coding: traverse incoming or outgoing network coding list * * Return: the nc_node if found or created, NULL in case of an error. */ static struct batadv_nc_node * batadv_nc_get_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, bool in_coding) { struct batadv_nc_node *nc_node; spinlock_t *lock; /* Used to lock list selected by "int in_coding" */ struct list_head *list; /* Select ingoing or outgoing coding node */ if (in_coding) { lock = &orig_neigh_node->in_coding_list_lock; list = &orig_neigh_node->in_coding_list; } else { lock = &orig_neigh_node->out_coding_list_lock; list = &orig_neigh_node->out_coding_list; } spin_lock_bh(lock); /* Check if nc_node is already added */ nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding); /* Node found */ if (nc_node) goto unlock; nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC); if (!nc_node) goto unlock; /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); kref_init(&nc_node->refcount); ether_addr_copy(nc_node->addr, orig_node->orig); kref_get(&orig_neigh_node->refcount); nc_node->orig_node = orig_neigh_node; batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n", nc_node->addr, nc_node->orig_node->orig); /* Add nc_node to orig_node */ kref_get(&nc_node->refcount); list_add_tail_rcu(&nc_node->list, list); unlock: spin_unlock_bh(lock); return nc_node; } /** * batadv_nc_update_nc_node() - updates stored incoming and outgoing nc node * structs (best called on incoming OGMs) * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet * (can be equal to orig_node) * @ogm_packet: incoming ogm packet * @is_single_hop_neigh: orig_node is a single hop neighbor */ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, struct batadv_ogm_packet *ogm_packet, int is_single_hop_neigh) { struct batadv_nc_node *in_nc_node = NULL; struct batadv_nc_node *out_nc_node = NULL; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* check if orig node is network coding enabled */ if (!test_bit(BATADV_ORIG_CAPA_HAS_NC, &orig_node->capabilities)) goto out; /* accept ogms from 'good' neighbors and single hop neighbors */ if (!batadv_can_nc_with_orig(bat_priv, orig_node, ogm_packet) && !is_single_hop_neigh) goto out; /* Add orig_node as in_nc_node on hop */ in_nc_node = batadv_nc_get_nc_node(bat_priv, orig_node, orig_neigh_node, true); if (!in_nc_node) goto out; in_nc_node->last_seen = jiffies; /* Add hop as out_nc_node on orig_node */ out_nc_node = batadv_nc_get_nc_node(bat_priv, orig_neigh_node, orig_node, false); if (!out_nc_node) goto out; out_nc_node->last_seen = jiffies; out: batadv_nc_node_put(in_nc_node); batadv_nc_node_put(out_nc_node); } /** * batadv_nc_get_path() - get existing nc_path or allocate a new one * @bat_priv: the bat priv with all the mesh interface information * @hash: hash table containing the nc path * @src: ethernet source address - first half of the nc path search key * @dst: ethernet destination address - second half of the nc path search key * * Return: pointer to nc_path if the path was found or created, returns NULL * on error. */ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, u8 *src, u8 *dst) { int hash_added; struct batadv_nc_path *nc_path, nc_path_key; batadv_nc_hash_key_gen(&nc_path_key, src, dst); /* Search for existing nc_path */ nc_path = batadv_nc_hash_find(hash, (void *)&nc_path_key); if (nc_path) { /* Set timestamp to delay removal of nc_path */ nc_path->last_valid = jiffies; return nc_path; } /* No existing nc_path was found; create a new */ nc_path = kzalloc(sizeof(*nc_path), GFP_ATOMIC); if (!nc_path) return NULL; /* Initialize nc_path */ INIT_LIST_HEAD(&nc_path->packet_list); spin_lock_init(&nc_path->packet_list_lock); kref_init(&nc_path->refcount); nc_path->last_valid = jiffies; ether_addr_copy(nc_path->next_hop, dst); ether_addr_copy(nc_path->prev_hop, src); batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n", nc_path->prev_hop, nc_path->next_hop); /* Add nc_path to hash table */ kref_get(&nc_path->refcount); hash_added = batadv_hash_add(hash, batadv_nc_hash_compare, batadv_nc_hash_choose, &nc_path_key, &nc_path->hash_entry); if (hash_added < 0) { kfree(nc_path); return NULL; } return nc_path; } /** * batadv_nc_random_weight_tq() - scale the receivers TQ-value to avoid unfair * selection of a receiver with slightly lower TQ than the other * @tq: to be weighted tq value * * Return: scaled tq value */ static u8 batadv_nc_random_weight_tq(u8 tq) { /* randomize the estimated packet loss (max TQ - estimated TQ) */ u8 rand_tq = get_random_u32_below(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; } /** * batadv_nc_memxor() - XOR destination with source * @dst: byte array to XOR into * @src: byte array to XOR from * @len: length of destination array */ static void batadv_nc_memxor(char *dst, const char *src, unsigned int len) { unsigned int i; for (i = 0; i < len; ++i) dst[i] ^= src[i]; } /** * batadv_nc_code_packets() - code a received unicast_packet with an nc packet * into a coded_packet and send it * @bat_priv: the bat priv with all the mesh interface information * @skb: data skb to forward * @ethhdr: pointer to the ethernet header inside the skb * @nc_packet: structure containing the packet to the skb can be coded with * @neigh_node: next hop to forward packet to * * Return: true if both packets are consumed, false otherwise. */ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct sk_buff *skb, struct ethhdr *ethhdr, struct batadv_nc_packet *nc_packet, struct batadv_neigh_node *neigh_node) { u8 tq_weighted_neigh, tq_weighted_coding, tq_tmp; struct sk_buff *skb_dest, *skb_src; struct batadv_unicast_packet *packet1; struct batadv_unicast_packet *packet2; struct batadv_coded_packet *coded_packet; struct batadv_neigh_node *neigh_tmp, *router_neigh, *first_dest; struct batadv_neigh_node *router_coding = NULL, *second_dest; struct batadv_neigh_ifinfo *router_neigh_ifinfo = NULL; struct batadv_neigh_ifinfo *router_coding_ifinfo = NULL; u8 *first_source, *second_source; __be32 packet_id1, packet_id2; size_t count; bool res = false; int coding_len; int unicast_size = sizeof(*packet1); int coded_size = sizeof(*coded_packet); int header_add = coded_size - unicast_size; /* TODO: do we need to consider the outgoing interface for * coded packets? */ router_neigh = batadv_orig_router_get(neigh_node->orig_node, BATADV_IF_DEFAULT); if (!router_neigh) goto out; router_neigh_ifinfo = batadv_neigh_ifinfo_get(router_neigh, BATADV_IF_DEFAULT); if (!router_neigh_ifinfo) goto out; neigh_tmp = nc_packet->neigh_node; router_coding = batadv_orig_router_get(neigh_tmp->orig_node, BATADV_IF_DEFAULT); if (!router_coding) goto out; router_coding_ifinfo = batadv_neigh_ifinfo_get(router_coding, BATADV_IF_DEFAULT); if (!router_coding_ifinfo) goto out; tq_tmp = router_neigh_ifinfo->bat_iv.tq_avg; tq_weighted_neigh = batadv_nc_random_weight_tq(tq_tmp); tq_tmp = router_coding_ifinfo->bat_iv.tq_avg; tq_weighted_coding = batadv_nc_random_weight_tq(tq_tmp); /* Select one destination for the MAC-header dst-field based on * weighted TQ-values. */ if (tq_weighted_neigh >= tq_weighted_coding) { /* Destination from nc_packet is selected for MAC-header */ first_dest = nc_packet->neigh_node; first_source = nc_packet->nc_path->prev_hop; second_dest = neigh_node; second_source = ethhdr->h_source; packet1 = (struct batadv_unicast_packet *)nc_packet->skb->data; packet2 = (struct batadv_unicast_packet *)skb->data; packet_id1 = nc_packet->packet_id; packet_id2 = batadv_skb_crc32(skb, skb->data + sizeof(*packet2)); } else { /* Destination for skb is selected for MAC-header */ first_dest = neigh_node; first_source = ethhdr->h_source; second_dest = nc_packet->neigh_node; second_source = nc_packet->nc_path->prev_hop; packet1 = (struct batadv_unicast_packet *)skb->data; packet2 = (struct batadv_unicast_packet *)nc_packet->skb->data; packet_id1 = batadv_skb_crc32(skb, skb->data + sizeof(*packet1)); packet_id2 = nc_packet->packet_id; } /* Instead of zero padding the smallest data buffer, we * code into the largest. */ if (skb->len <= nc_packet->skb->len) { skb_dest = nc_packet->skb; skb_src = skb; } else { skb_dest = skb; skb_src = nc_packet->skb; } /* coding_len is used when decoding the packet shorter packet */ coding_len = skb_src->len - unicast_size; if (skb_linearize(skb_dest) < 0 || skb_linearize(skb_src) < 0) goto out; skb_push(skb_dest, header_add); coded_packet = (struct batadv_coded_packet *)skb_dest->data; skb_reset_mac_header(skb_dest); coded_packet->packet_type = BATADV_CODED; coded_packet->version = BATADV_COMPAT_VERSION; coded_packet->ttl = packet1->ttl; /* Info about first unicast packet */ ether_addr_copy(coded_packet->first_source, first_source); ether_addr_copy(coded_packet->first_orig_dest, packet1->dest); coded_packet->first_crc = packet_id1; coded_packet->first_ttvn = packet1->ttvn; /* Info about second unicast packet */ ether_addr_copy(coded_packet->second_dest, second_dest->addr); ether_addr_copy(coded_packet->second_source, second_source); ether_addr_copy(coded_packet->second_orig_dest, packet2->dest); coded_packet->second_crc = packet_id2; coded_packet->second_ttl = packet2->ttl; coded_packet->second_ttvn = packet2->ttvn; coded_packet->coded_len = htons(coding_len); /* This is where the magic happens: Code skb_src into skb_dest */ batadv_nc_memxor(skb_dest->data + coded_size, skb_src->data + unicast_size, coding_len); /* Update counters accordingly */ if (BATADV_SKB_CB(skb_src)->decoded && BATADV_SKB_CB(skb_dest)->decoded) { /* Both packets are recoded */ count = skb_src->len + ETH_HLEN; count += skb_dest->len + ETH_HLEN; batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE, 2); batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, count); } else if (!BATADV_SKB_CB(skb_src)->decoded && !BATADV_SKB_CB(skb_dest)->decoded) { /* Both packets are newly coded */ count = skb_src->len + ETH_HLEN; count += skb_dest->len + ETH_HLEN; batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE, 2); batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, count); } else if (BATADV_SKB_CB(skb_src)->decoded && !BATADV_SKB_CB(skb_dest)->decoded) { /* skb_src recoded and skb_dest is newly coded */ batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, skb_src->len + ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, skb_dest->len + ETH_HLEN); } else if (!BATADV_SKB_CB(skb_src)->decoded && BATADV_SKB_CB(skb_dest)->decoded) { /* skb_src is newly coded and skb_dest is recoded */ batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, skb_src->len + ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, skb_dest->len + ETH_HLEN); } /* skb_src is now coded into skb_dest, so free it */ consume_skb(skb_src); /* avoid duplicate free of skb from nc_packet */ nc_packet->skb = NULL; batadv_nc_packet_free(nc_packet, false); /* Send the coded packet and return true */ batadv_send_unicast_skb(skb_dest, first_dest); res = true; out: batadv_neigh_node_put(router_neigh); batadv_neigh_node_put(router_coding); batadv_neigh_ifinfo_put(router_neigh_ifinfo); batadv_neigh_ifinfo_put(router_coding_ifinfo); return res; } /** * batadv_nc_skb_coding_possible() - true if a decoded skb is available at dst. * @skb: data skb to forward * @dst: destination mac address of the other skb to code with * @src: source mac address of skb * * Whenever we network code a packet we have to check whether we received it in * a network coded form. If so, we may not be able to use it for coding because * some neighbors may also have received (overheard) the packet in the network * coded form without being able to decode it. It is hard to know which of the * neighboring nodes was able to decode the packet, therefore we can only * re-code the packet if the source of the previous encoded packet is involved. * Since the source encoded the packet we can be certain it has all necessary * decode information. * * Return: true if coding of a decoded packet is allowed. */ static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, u8 *dst, u8 *src) { if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src)) return false; return true; } /** * batadv_nc_path_search() - Find the coding path matching in_nc_node and * out_nc_node to retrieve a buffered packet that can be used for coding. * @bat_priv: the bat priv with all the mesh interface information * @in_nc_node: pointer to skb next hop's neighbor nc node * @out_nc_node: pointer to skb source's neighbor nc node * @skb: data skb to forward * @eth_dst: next hop mac address of skb * * Return: true if coding of a decoded skb is allowed. */ static struct batadv_nc_packet * batadv_nc_path_search(struct batadv_priv *bat_priv, struct batadv_nc_node *in_nc_node, struct batadv_nc_node *out_nc_node, struct sk_buff *skb, u8 *eth_dst) { struct batadv_nc_path *nc_path, nc_path_key; struct batadv_nc_packet *nc_packet_out = NULL; struct batadv_nc_packet *nc_packet, *nc_packet_tmp; struct batadv_hashtable *hash = bat_priv->nc.coding_hash; int idx; if (!hash) return NULL; /* Create almost path key */ batadv_nc_hash_key_gen(&nc_path_key, in_nc_node->addr, out_nc_node->addr); idx = batadv_nc_hash_choose(&nc_path_key, hash->size); /* Check for coding opportunities in this nc_path */ rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, &hash->table[idx], hash_entry) { if (!batadv_compare_eth(nc_path->prev_hop, in_nc_node->addr)) continue; if (!batadv_compare_eth(nc_path->next_hop, out_nc_node->addr)) continue; spin_lock_bh(&nc_path->packet_list_lock); if (list_empty(&nc_path->packet_list)) { spin_unlock_bh(&nc_path->packet_list_lock); continue; } list_for_each_entry_safe(nc_packet, nc_packet_tmp, &nc_path->packet_list, list) { if (!batadv_nc_skb_coding_possible(nc_packet->skb, eth_dst, in_nc_node->addr)) continue; /* Coding opportunity is found! */ list_del(&nc_packet->list); nc_packet_out = nc_packet; break; } spin_unlock_bh(&nc_path->packet_list_lock); break; } rcu_read_unlock(); return nc_packet_out; } /** * batadv_nc_skb_src_search() - Loops through the list of neighboring nodes of * the skb's sender (may be equal to the originator). * @bat_priv: the bat priv with all the mesh interface information * @skb: data skb to forward * @eth_dst: next hop mac address of skb * @eth_src: source mac address of skb * @in_nc_node: pointer to skb next hop's neighbor nc node * * Return: an nc packet if a suitable coding packet was found, NULL otherwise. */ static struct batadv_nc_packet * batadv_nc_skb_src_search(struct batadv_priv *bat_priv, struct sk_buff *skb, u8 *eth_dst, u8 *eth_src, struct batadv_nc_node *in_nc_node) { struct batadv_orig_node *orig_node; struct batadv_nc_node *out_nc_node; struct batadv_nc_packet *nc_packet = NULL; orig_node = batadv_orig_hash_find(bat_priv, eth_src); if (!orig_node) return NULL; rcu_read_lock(); list_for_each_entry_rcu(out_nc_node, &orig_node->out_coding_list, list) { /* Check if the skb is decoded and if recoding is possible */ if (!batadv_nc_skb_coding_possible(skb, out_nc_node->addr, eth_src)) continue; /* Search for an opportunity in this nc_path */ nc_packet = batadv_nc_path_search(bat_priv, in_nc_node, out_nc_node, skb, eth_dst); if (nc_packet) break; } rcu_read_unlock(); batadv_orig_node_put(orig_node); return nc_packet; } /** * batadv_nc_skb_store_before_coding() - set the ethernet src and dst of the * unicast skb before it is stored for use in later decoding * @bat_priv: the bat priv with all the mesh interface information * @skb: data skb to store * @eth_dst_new: new destination mac address of skb */ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv, struct sk_buff *skb, u8 *eth_dst_new) { struct ethhdr *ethhdr; /* Copy skb header to change the mac header */ skb = pskb_copy_for_clone(skb, GFP_ATOMIC); if (!skb) return; /* Set the mac header as if we actually sent the packet uncoded */ ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, ethhdr->h_dest); ether_addr_copy(ethhdr->h_dest, eth_dst_new); /* Set data pointer to MAC header to mimic packets from our tx path */ skb_push(skb, ETH_HLEN); /* Add the packet to the decoding packet pool */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* batadv_nc_skb_store_for_decoding() clones the skb, so we must free * our ref */ consume_skb(skb); } /** * batadv_nc_skb_dst_search() - Loops through list of neighboring nodes to dst. * @skb: data skb to forward * @neigh_node: next hop to forward packet to * @ethhdr: pointer to the ethernet header inside the skb * * Loops through the list of neighboring nodes the next hop has a good * connection to (receives OGMs with a sufficient quality). We need to find a * neighbor of our next hop that potentially sent a packet which our next hop * also received (overheard) and has stored for later decoding. * * Return: true if the skb was consumed (encoded packet sent) or false otherwise */ static bool batadv_nc_skb_dst_search(struct sk_buff *skb, struct batadv_neigh_node *neigh_node, struct ethhdr *ethhdr) { struct net_device *netdev = neigh_node->if_incoming->mesh_iface; struct batadv_priv *bat_priv = netdev_priv(netdev); struct batadv_orig_node *orig_node = neigh_node->orig_node; struct batadv_nc_node *nc_node; struct batadv_nc_packet *nc_packet = NULL; rcu_read_lock(); list_for_each_entry_rcu(nc_node, &orig_node->in_coding_list, list) { /* Search for coding opportunity with this in_nc_node */ nc_packet = batadv_nc_skb_src_search(bat_priv, skb, neigh_node->addr, ethhdr->h_source, nc_node); /* Opportunity was found, so stop searching */ if (nc_packet) break; } rcu_read_unlock(); if (!nc_packet) return false; /* Save packets for later decoding */ batadv_nc_skb_store_before_coding(bat_priv, skb, neigh_node->addr); batadv_nc_skb_store_before_coding(bat_priv, nc_packet->skb, nc_packet->neigh_node->addr); /* Code and send packets */ if (batadv_nc_code_packets(bat_priv, skb, ethhdr, nc_packet, neigh_node)) return true; /* out of mem ? Coding failed - we have to free the buffered packet * to avoid memleaks. The skb passed as argument will be dealt with * by the calling function. */ batadv_nc_send_packet(nc_packet); return false; } /** * batadv_nc_skb_add_to_path() - buffer skb for later encoding / decoding * @skb: skb to add to path * @nc_path: path to add skb to * @neigh_node: next hop to forward packet to * @packet_id: checksum to identify packet * * Return: true if the packet was buffered or false in case of an error. */ static bool batadv_nc_skb_add_to_path(struct sk_buff *skb, struct batadv_nc_path *nc_path, struct batadv_neigh_node *neigh_node, __be32 packet_id) { struct batadv_nc_packet *nc_packet; nc_packet = kzalloc(sizeof(*nc_packet), GFP_ATOMIC); if (!nc_packet) return false; /* Initialize nc_packet */ nc_packet->timestamp = jiffies; nc_packet->packet_id = packet_id; nc_packet->skb = skb; nc_packet->neigh_node = neigh_node; nc_packet->nc_path = nc_path; /* Add coding packet to list */ spin_lock_bh(&nc_path->packet_list_lock); list_add_tail(&nc_packet->list, &nc_path->packet_list); spin_unlock_bh(&nc_path->packet_list_lock); return true; } /** * batadv_nc_skb_forward() - try to code a packet or add it to the coding packet * buffer * @skb: data skb to forward * @neigh_node: next hop to forward packet to * * Return: true if the skb was consumed (encoded packet sent) or false otherwise */ bool batadv_nc_skb_forward(struct sk_buff *skb, struct batadv_neigh_node *neigh_node) { const struct net_device *netdev = neigh_node->if_incoming->mesh_iface; struct batadv_priv *bat_priv = netdev_priv(netdev); struct batadv_unicast_packet *packet; struct batadv_nc_path *nc_path; struct ethhdr *ethhdr = eth_hdr(skb); __be32 packet_id; u8 *payload; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* We only handle unicast packets */ payload = skb_network_header(skb); packet = (struct batadv_unicast_packet *)payload; if (packet->packet_type != BATADV_UNICAST) goto out; /* Try to find a coding opportunity and send the skb if one is found */ if (batadv_nc_skb_dst_search(skb, neigh_node, ethhdr)) return true; /* Find or create a nc_path for this src-dst pair */ nc_path = batadv_nc_get_path(bat_priv, bat_priv->nc.coding_hash, ethhdr->h_source, neigh_node->addr); if (!nc_path) goto out; /* Add skb to nc_path */ packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet)); if (!batadv_nc_skb_add_to_path(skb, nc_path, neigh_node, packet_id)) goto free_nc_path; /* Packet is consumed */ return true; free_nc_path: batadv_nc_path_put(nc_path); out: /* Packet is not consumed */ return false; } /** * batadv_nc_skb_store_for_decoding() - save a clone of the skb which can be * used when decoding coded packets * @bat_priv: the bat priv with all the mesh interface information * @skb: data skb to store */ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_unicast_packet *packet; struct batadv_nc_path *nc_path; struct ethhdr *ethhdr = eth_hdr(skb); __be32 packet_id; u8 *payload; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* Check for supported packet type */ payload = skb_network_header(skb); packet = (struct batadv_unicast_packet *)payload; if (packet->packet_type != BATADV_UNICAST) goto out; /* Find existing nc_path or create a new */ nc_path = batadv_nc_get_path(bat_priv, bat_priv->nc.decoding_hash, ethhdr->h_source, ethhdr->h_dest); if (!nc_path) goto out; /* Clone skb and adjust skb->data to point at batman header */ skb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb)) goto free_nc_path; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) goto free_skb; if (unlikely(!skb_pull_rcsum(skb, ETH_HLEN))) goto free_skb; /* Add skb to nc_path */ packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet)); if (!batadv_nc_skb_add_to_path(skb, nc_path, NULL, packet_id)) goto free_skb; batadv_inc_counter(bat_priv, BATADV_CNT_NC_BUFFER); return; free_skb: kfree_skb(skb); free_nc_path: batadv_nc_path_put(nc_path); out: return; } /** * batadv_nc_skb_store_sniffed_unicast() - check if a received unicast packet * should be saved in the decoding buffer and, if so, store it there * @bat_priv: the bat priv with all the mesh interface information * @skb: unicast skb to store */ void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct ethhdr *ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return; /* Set data pointer to MAC header to mimic packets from our tx path */ skb_push(skb, ETH_HLEN); batadv_nc_skb_store_for_decoding(bat_priv, skb); } /** * batadv_nc_skb_decode_packet() - decode given skb using the decode data stored * in nc_packet * @bat_priv: the bat priv with all the mesh interface information * @skb: unicast skb to decode * @nc_packet: decode data needed to decode the skb * * Return: pointer to decoded unicast packet if the packet was decoded or NULL * in case of an error. */ static struct batadv_unicast_packet * batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_nc_packet *nc_packet) { const int h_size = sizeof(struct batadv_unicast_packet); const int h_diff = sizeof(struct batadv_coded_packet) - h_size; struct batadv_unicast_packet *unicast_packet; struct batadv_coded_packet coded_packet_tmp; struct ethhdr *ethhdr, ethhdr_tmp; u8 *orig_dest, ttl, ttvn; unsigned int coding_len; int err; /* Save headers temporarily */ memcpy(&coded_packet_tmp, skb->data, sizeof(coded_packet_tmp)); memcpy(ðhdr_tmp, skb_mac_header(skb), sizeof(ethhdr_tmp)); if (skb_cow(skb, 0) < 0) return NULL; if (unlikely(!skb_pull_rcsum(skb, h_diff))) return NULL; /* Data points to batman header, so set mac header 14 bytes before * and network to data */ skb_set_mac_header(skb, -ETH_HLEN); skb_reset_network_header(skb); /* Reconstruct original mac header */ ethhdr = eth_hdr(skb); *ethhdr = ethhdr_tmp; /* Select the correct unicast header information based on the location * of our mac address in the coded_packet header */ if (batadv_is_my_mac(bat_priv, coded_packet_tmp.second_dest)) { /* If we are the second destination the packet was overheard, * so the Ethernet address must be copied to h_dest and * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST */ ether_addr_copy(ethhdr->h_dest, coded_packet_tmp.second_dest); skb->pkt_type = PACKET_HOST; orig_dest = coded_packet_tmp.second_orig_dest; ttl = coded_packet_tmp.second_ttl; ttvn = coded_packet_tmp.second_ttvn; } else { orig_dest = coded_packet_tmp.first_orig_dest; ttl = coded_packet_tmp.ttl; ttvn = coded_packet_tmp.first_ttvn; } coding_len = ntohs(coded_packet_tmp.coded_len); if (coding_len > skb->len) return NULL; /* Here the magic is reversed: * extract the missing packet from the received coded packet */ batadv_nc_memxor(skb->data + h_size, nc_packet->skb->data + h_size, coding_len); /* Resize decoded skb if decoded with larger packet */ if (nc_packet->skb->len > coding_len + h_size) { err = pskb_trim_rcsum(skb, coding_len + h_size); if (err) return NULL; } /* Create decoded unicast packet */ unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->packet_type = BATADV_UNICAST; unicast_packet->version = BATADV_COMPAT_VERSION; unicast_packet->ttl = ttl; ether_addr_copy(unicast_packet->dest, orig_dest); unicast_packet->ttvn = ttvn; batadv_nc_packet_free(nc_packet, false); return unicast_packet; } /** * batadv_nc_find_decoding_packet() - search through buffered decoding data to * find the data needed to decode the coded packet * @bat_priv: the bat priv with all the mesh interface information * @ethhdr: pointer to the ethernet header inside the coded packet * @coded: coded packet we try to find decode data for * * Return: pointer to nc packet if the needed data was found or NULL otherwise. */ static struct batadv_nc_packet * batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv, struct ethhdr *ethhdr, struct batadv_coded_packet *coded) { struct batadv_hashtable *hash = bat_priv->nc.decoding_hash; struct batadv_nc_packet *tmp_nc_packet, *nc_packet = NULL; struct batadv_nc_path *nc_path, nc_path_key; u8 *dest, *source; __be32 packet_id; int index; if (!hash) return NULL; /* Select the correct packet id based on the location of our mac-addr */ dest = ethhdr->h_source; if (!batadv_is_my_mac(bat_priv, coded->second_dest)) { source = coded->second_source; packet_id = coded->second_crc; } else { source = coded->first_source; packet_id = coded->first_crc; } batadv_nc_hash_key_gen(&nc_path_key, source, dest); index = batadv_nc_hash_choose(&nc_path_key, hash->size); /* Search for matching coding path */ rcu_read_lock(); hlist_for_each_entry_rcu(nc_path, &hash->table[index], hash_entry) { /* Find matching nc_packet */ spin_lock_bh(&nc_path->packet_list_lock); list_for_each_entry(tmp_nc_packet, &nc_path->packet_list, list) { if (packet_id == tmp_nc_packet->packet_id) { list_del(&tmp_nc_packet->list); nc_packet = tmp_nc_packet; break; } } spin_unlock_bh(&nc_path->packet_list_lock); if (nc_packet) break; } rcu_read_unlock(); if (!nc_packet) batadv_dbg(BATADV_DBG_NC, bat_priv, "No decoding packet found for %u\n", packet_id); return nc_packet; } /** * batadv_nc_recv_coded_packet() - try to decode coded packet and enqueue the * resulting unicast packet * @skb: incoming coded packet * @recv_if: pointer to interface this packet was received on * * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP * otherwise. */ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface); struct batadv_unicast_packet *unicast_packet; struct batadv_coded_packet *coded_packet; struct batadv_nc_packet *nc_packet; struct ethhdr *ethhdr; int hdr_size = sizeof(*coded_packet); /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto free_skb; /* Make sure we can access (and remove) header */ if (unlikely(!pskb_may_pull(skb, hdr_size))) goto free_skb; coded_packet = (struct batadv_coded_packet *)skb->data; ethhdr = eth_hdr(skb); /* Verify frame is destined for us */ if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest) && !batadv_is_my_mac(bat_priv, coded_packet->second_dest)) goto free_skb; /* Update stat counter */ if (batadv_is_my_mac(bat_priv, coded_packet->second_dest)) batadv_inc_counter(bat_priv, BATADV_CNT_NC_SNIFFED); nc_packet = batadv_nc_find_decoding_packet(bat_priv, ethhdr, coded_packet); if (!nc_packet) { batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); goto free_skb; } /* Make skb's linear, because decoding accesses the entire buffer */ if (skb_linearize(skb) < 0) goto free_nc_packet; if (skb_linearize(nc_packet->skb) < 0) goto free_nc_packet; /* Decode the packet */ unicast_packet = batadv_nc_skb_decode_packet(bat_priv, skb, nc_packet); if (!unicast_packet) { batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); goto free_nc_packet; } /* Mark packet as decoded to do correct recoding when forwarding */ BATADV_SKB_CB(skb)->decoded = true; batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE); batadv_add_counter(bat_priv, BATADV_CNT_NC_DECODE_BYTES, skb->len + ETH_HLEN); return batadv_recv_unicast_packet(skb, recv_if); free_nc_packet: batadv_nc_packet_free(nc_packet, true); free_skb: kfree_skb(skb); return NET_RX_DROP; } /** * batadv_nc_mesh_free() - clean up network coding memory * @bat_priv: the bat priv with all the mesh interface information */ void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_NC, 1); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_NC, 1); cancel_delayed_work_sync(&bat_priv->nc.work); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); batadv_hash_destroy(bat_priv->nc.coding_hash); batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, NULL); batadv_hash_destroy(bat_priv->nc.decoding_hash); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _ASM_X86_INAT_H #define _ASM_X86_INAT_H /* * x86 instruction attributes * * Written by Masami Hiramatsu <mhiramat@redhat.com> */ #include <asm/inat_types.h> /* __ignore_sync_check__ */ /* * Internal bits. Don't use bitmasks directly, because these bits are * unstable. You should use checking functions. */ #define INAT_OPCODE_TABLE_SIZE 256 #define INAT_GROUP_TABLE_SIZE 8 /* Legacy last prefixes */ #define INAT_PFX_OPNDSZ 1 /* 0x66 */ /* LPFX1 */ #define INAT_PFX_REPE 2 /* 0xF3 */ /* LPFX2 */ #define INAT_PFX_REPNE 3 /* 0xF2 */ /* LPFX3 */ /* Other Legacy prefixes */ #define INAT_PFX_LOCK 4 /* 0xF0 */ #define INAT_PFX_CS 5 /* 0x2E */ #define INAT_PFX_DS 6 /* 0x3E */ #define INAT_PFX_ES 7 /* 0x26 */ #define INAT_PFX_FS 8 /* 0x64 */ #define INAT_PFX_GS 9 /* 0x65 */ #define INAT_PFX_SS 10 /* 0x36 */ #define INAT_PFX_ADDRSZ 11 /* 0x67 */ /* x86-64 REX prefix */ #define INAT_PFX_REX 12 /* 0x4X */ /* AVX VEX prefixes */ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ #define INAT_PFX_EVEX 15 /* EVEX prefix */ /* x86-64 REX2 prefix */ #define INAT_PFX_REX2 16 /* 0xD5 */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 /* Immediate size */ #define INAT_IMM_BYTE 1 #define INAT_IMM_WORD 2 #define INAT_IMM_DWORD 3 #define INAT_IMM_QWORD 4 #define INAT_IMM_PTR 5 #define INAT_IMM_VWORD32 6 #define INAT_IMM_VWORD 7 /* Legacy prefix */ #define INAT_PFX_OFFS 0 #define INAT_PFX_BITS 5 #define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1) #define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS) /* Escape opcodes */ #define INAT_ESC_OFFS (INAT_PFX_OFFS + INAT_PFX_BITS) #define INAT_ESC_BITS 2 #define INAT_ESC_MAX ((1 << INAT_ESC_BITS) - 1) #define INAT_ESC_MASK (INAT_ESC_MAX << INAT_ESC_OFFS) /* Group opcodes (1-16) */ #define INAT_GRP_OFFS (INAT_ESC_OFFS + INAT_ESC_BITS) #define INAT_GRP_BITS 5 #define INAT_GRP_MAX ((1 << INAT_GRP_BITS) - 1) #define INAT_GRP_MASK (INAT_GRP_MAX << INAT_GRP_OFFS) /* Immediates */ #define INAT_IMM_OFFS (INAT_GRP_OFFS + INAT_GRP_BITS) #define INAT_IMM_BITS 3 #define INAT_IMM_MASK (((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS) /* Flags */ #define INAT_FLAG_OFFS (INAT_IMM_OFFS + INAT_IMM_BITS) #define INAT_MODRM (1 << (INAT_FLAG_OFFS)) #define INAT_FORCE64 (1 << (INAT_FLAG_OFFS + 1)) #define INAT_SCNDIMM (1 << (INAT_FLAG_OFFS + 2)) #define INAT_MOFFSET (1 << (INAT_FLAG_OFFS + 3)) #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) #define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) #define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8)) #define INAT_REX2_VARIANT (1 << (INAT_FLAG_OFFS + 9)) #define INAT_EVEX_SCALABLE (1 << (INAT_FLAG_OFFS + 10)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) #define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) #define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) /* Identifiers for segment registers */ #define INAT_SEG_REG_IGNORE 0 #define INAT_SEG_REG_DEFAULT 1 #define INAT_SEG_REG_CS 2 #define INAT_SEG_REG_SS 3 #define INAT_SEG_REG_DS 4 #define INAT_SEG_REG_ES 5 #define INAT_SEG_REG_FS 6 #define INAT_SEG_REG_GS 7 /* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); extern int inat_get_last_prefix_id(insn_byte_t last_pfx); extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id, insn_attr_t esc_attr); extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id, insn_attr_t esc_attr); extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m, insn_byte_t vex_pp); /* Attribute checking functions */ static inline int inat_is_legacy_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; return attr && attr <= INAT_LGCPFX_MAX; } static inline int inat_is_address_size_prefix(insn_attr_t attr) { return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ; } static inline int inat_is_operand_size_prefix(insn_attr_t attr) { return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ; } static inline int inat_is_rex_prefix(insn_attr_t attr) { return (attr & INAT_PFX_MASK) == INAT_PFX_REX; } static inline int inat_is_rex2_prefix(insn_attr_t attr) { return (attr & INAT_PFX_MASK) == INAT_PFX_REX2; } static inline int inat_last_prefix_id(insn_attr_t attr) { if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX) return 0; else return attr & INAT_PFX_MASK; } static inline int inat_is_vex_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || attr == INAT_PFX_EVEX; } static inline int inat_is_evex_prefix(insn_attr_t attr) { return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; } static inline int inat_is_vex3_prefix(insn_attr_t attr) { return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3; } static inline int inat_is_escape(insn_attr_t attr) { return attr & INAT_ESC_MASK; } static inline int inat_escape_id(insn_attr_t attr) { return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS; } static inline int inat_is_group(insn_attr_t attr) { return attr & INAT_GRP_MASK; } static inline int inat_group_id(insn_attr_t attr) { return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS; } static inline int inat_group_common_attribute(insn_attr_t attr) { return attr & ~INAT_GRP_MASK; } static inline int inat_has_immediate(insn_attr_t attr) { return attr & INAT_IMM_MASK; } static inline int inat_immediate_size(insn_attr_t attr) { return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS; } static inline int inat_has_modrm(insn_attr_t attr) { return attr & INAT_MODRM; } static inline int inat_is_force64(insn_attr_t attr) { return attr & INAT_FORCE64; } static inline int inat_has_second_immediate(insn_attr_t attr) { return attr & INAT_SCNDIMM; } static inline int inat_has_moffset(insn_attr_t attr) { return attr & INAT_MOFFSET; } static inline int inat_has_variant(insn_attr_t attr) { return attr & INAT_VARIANT; } static inline int inat_accept_vex(insn_attr_t attr) { return attr & INAT_VEXOK; } static inline int inat_must_vex(insn_attr_t attr) { return attr & (INAT_VEXONLY | INAT_EVEXONLY); } static inline int inat_must_evex(insn_attr_t attr) { return attr & INAT_EVEXONLY; } static inline int inat_evex_scalable(insn_attr_t attr) { return attr & INAT_EVEX_SCALABLE; } #endif |
| 34 88 38 92 9 3 55 26 26 26 34 41 41 3 9 9 1 1 1 54 54 54 32 32 32 54 54 54 9 9 9 9 9 1 1 1 26 26 1 26 26 9 9 1 1 2 2 2 2 19 92 1 3 28 28 1 1 26 2 1 2 2 2 32 32 1 20 20 14 6 7 2 55 1 32 1 1 85 86 85 2 1 1 1 32 32 54 54 2 33 1 32 32 32 32 32 32 54 53 52 53 54 54 2 54 54 54 54 86 52 47 86 44 62 64 64 1 88 2 87 50 74 1 1 5 67 68 2 1 64 64 14 50 49 13 20 32 31 32 5 15 30 32 20 34 34 54 2 54 54 8 54 9 54 43 24 54 54 54 54 54 10 3 3 9 1 10 2 9 1 13 5 87 1 1 86 87 1 1 1 86 87 2 1 1 7 7 7 7 7 26 26 25 48 82 82 2 2 2 2 2 74 74 58 25 57 25 150 150 8 8 6 6 5 4 5 326 326 56 56 43 91 91 75 75 35 26 29 114 114 2 1 1 1 85 73 27 68 72 27 75 2 1 1 65 3 2 7 7 7 7 7 7 7 1 1 4 11 2 37 4 4 105 104 1 103 11 4 88 86 105 1 104 4 119 4 105 105 105 105 4 105 3 2 1 1 1 37 11 1 7 2 4 13 5 2 2 3 20 14 5 18 1 17 19 15 17 16 9 1 3 2 2 12 6 33 99 3 96 49 54 71 35 99 99 99 96 1 3 99 7 4 3 115 114 94 94 87 93 89 6 96 96 71 10 22 91 6 1 61 104 69 36 19 49 32 32 54 49 3793 3784 123 2 18 36 3 2 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/team/team.c - Network team device driver * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> */ #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/errno.h> #include <linux/ctype.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netpoll.h> #include <linux/if_vlan.h> #include <linux/if_arp.h> #include <linux/socket.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <net/genetlink.h> #include <net/netdev_lock.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <linux/if_team.h> #include "team_nl.h" #define DRV_NAME "team" /********** * Helpers **********/ static struct team_port *team_port_get_rtnl(const struct net_device *dev) { struct team_port *port = rtnl_dereference(dev->rx_handler_data); return netif_is_team_port(dev) ? port : NULL; } /* * Since the ability to change device address for open port device is tested in * team_port_add, this function can be called without control of return value */ static int __set_port_dev_addr(struct net_device *port_dev, const unsigned char *dev_addr) { struct sockaddr_storage addr; memcpy(addr.__data, dev_addr, port_dev->addr_len); addr.ss_family = port_dev->type; return dev_set_mac_address(port_dev, (struct sockaddr *)&addr, NULL); } static int team_port_set_orig_dev_addr(struct team_port *port) { return __set_port_dev_addr(port->dev, port->orig.dev_addr); } static int team_port_set_team_dev_addr(struct team *team, struct team_port *port) { return __set_port_dev_addr(port->dev, team->dev->dev_addr); } int team_modeop_port_enter(struct team *team, struct team_port *port) { return team_port_set_team_dev_addr(team, port); } EXPORT_SYMBOL(team_modeop_port_enter); void team_modeop_port_change_dev_addr(struct team *team, struct team_port *port) { team_port_set_team_dev_addr(team, port); } EXPORT_SYMBOL(team_modeop_port_change_dev_addr); static void team_lower_state_changed(struct team_port *port) { struct netdev_lag_lower_state_info info; info.link_up = port->linkup; info.tx_enabled = team_port_enabled(port); netdev_lower_state_changed(port->dev, &info); } static void team_refresh_port_linkup(struct team_port *port) { bool new_linkup = port->user.linkup_enabled ? port->user.linkup : port->state.linkup; if (port->linkup != new_linkup) { port->linkup = new_linkup; team_lower_state_changed(port); } } /******************* * Options handling *******************/ struct team_option_inst { /* One for each option instance */ struct list_head list; struct list_head tmp_list; struct team_option *option; struct team_option_inst_info info; bool changed; bool removed; }; static struct team_option *__team_find_option(struct team *team, const char *opt_name) { struct team_option *option; list_for_each_entry(option, &team->option_list, list) { if (strcmp(option->name, opt_name) == 0) return option; } return NULL; } static void __team_option_inst_del(struct team_option_inst *opt_inst) { list_del(&opt_inst->list); kfree(opt_inst); } static void __team_option_inst_del_option(struct team *team, struct team_option *option) { struct team_option_inst *opt_inst, *tmp; list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option == option) __team_option_inst_del(opt_inst); } } static int __team_option_inst_add(struct team *team, struct team_option *option, struct team_port *port) { struct team_option_inst *opt_inst; unsigned int array_size; unsigned int i; array_size = option->array_size; if (!array_size) array_size = 1; /* No array but still need one instance */ for (i = 0; i < array_size; i++) { opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); if (!opt_inst) return -ENOMEM; opt_inst->option = option; opt_inst->info.port = port; opt_inst->info.array_index = i; opt_inst->changed = true; opt_inst->removed = false; list_add_tail(&opt_inst->list, &team->option_inst_list); if (option->init) option->init(team, &opt_inst->info); } return 0; } static int __team_option_inst_add_option(struct team *team, struct team_option *option) { int err; if (!option->per_port) { err = __team_option_inst_add(team, option, NULL); if (err) goto inst_del_option; } return 0; inst_del_option: __team_option_inst_del_option(team, option); return err; } static void __team_option_inst_mark_removed_option(struct team *team, struct team_option *option) { struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->option == option) { opt_inst->changed = true; opt_inst->removed = true; } } } static void __team_option_inst_del_port(struct team *team, struct team_port *port) { struct team_option_inst *opt_inst, *tmp; list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option->per_port && opt_inst->info.port == port) __team_option_inst_del(opt_inst); } } static int __team_option_inst_add_port(struct team *team, struct team_port *port) { struct team_option *option; int err; list_for_each_entry(option, &team->option_list, list) { if (!option->per_port) continue; err = __team_option_inst_add(team, option, port); if (err) goto inst_del_port; } return 0; inst_del_port: __team_option_inst_del_port(team, port); return err; } static void __team_option_inst_mark_removed_port(struct team *team, struct team_port *port) { struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->info.port == port) { opt_inst->changed = true; opt_inst->removed = true; } } } static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) { int i; struct team_option **dst_opts; int err; dst_opts = kcalloc(option_count, sizeof(struct team_option *), GFP_KERNEL); if (!dst_opts) return -ENOMEM; for (i = 0; i < option_count; i++, option++) { if (__team_find_option(team, option->name)) { err = -EEXIST; goto alloc_rollback; } dst_opts[i] = kmemdup(option, sizeof(*option), GFP_KERNEL); if (!dst_opts[i]) { err = -ENOMEM; goto alloc_rollback; } } for (i = 0; i < option_count; i++) { err = __team_option_inst_add_option(team, dst_opts[i]); if (err) goto inst_rollback; list_add_tail(&dst_opts[i]->list, &team->option_list); } kfree(dst_opts); return 0; inst_rollback: for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); list_del(&dst_opts[i]->list); } i = option_count; alloc_rollback: for (i--; i >= 0; i--) kfree(dst_opts[i]); kfree(dst_opts); return err; } static void __team_options_mark_removed(struct team *team, const struct team_option *option, size_t option_count) { int i; for (i = 0; i < option_count; i++, option++) { struct team_option *del_opt; del_opt = __team_find_option(team, option->name); if (del_opt) __team_option_inst_mark_removed_option(team, del_opt); } } static void __team_options_unregister(struct team *team, const struct team_option *option, size_t option_count) { int i; for (i = 0; i < option_count; i++, option++) { struct team_option *del_opt; del_opt = __team_find_option(team, option->name); if (del_opt) { __team_option_inst_del_option(team, del_opt); list_del(&del_opt->list); kfree(del_opt); } } } static void __team_options_change_check(struct team *team); int team_options_register(struct team *team, const struct team_option *option, size_t option_count) { int err; err = __team_options_register(team, option, option_count); if (err) return err; __team_options_change_check(team); return 0; } EXPORT_SYMBOL(team_options_register); void team_options_unregister(struct team *team, const struct team_option *option, size_t option_count) { __team_options_mark_removed(team, option, option_count); __team_options_change_check(team); __team_options_unregister(team, option, option_count); } EXPORT_SYMBOL(team_options_unregister); static int team_option_get(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { if (!opt_inst->option->getter) return -EOPNOTSUPP; opt_inst->option->getter(team, ctx); return 0; } static int team_option_set(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { if (!opt_inst->option->setter) return -EOPNOTSUPP; return opt_inst->option->setter(team, ctx); } void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info) { struct team_option_inst *opt_inst; opt_inst = container_of(opt_inst_info, struct team_option_inst, info); opt_inst->changed = true; } EXPORT_SYMBOL(team_option_inst_set_change); void team_options_change_check(struct team *team) { __team_options_change_check(team); } EXPORT_SYMBOL(team_options_change_check); /**************** * Mode handling ****************/ static LIST_HEAD(mode_list); static DEFINE_SPINLOCK(mode_list_lock); struct team_mode_item { struct list_head list; const struct team_mode *mode; }; static struct team_mode_item *__find_mode(const char *kind) { struct team_mode_item *mitem; list_for_each_entry(mitem, &mode_list, list) { if (strcmp(mitem->mode->kind, kind) == 0) return mitem; } return NULL; } static bool is_good_mode_name(const char *name) { while (*name != '\0') { if (!isalpha(*name) && !isdigit(*name) && *name != '_') return false; name++; } return true; } int team_mode_register(const struct team_mode *mode) { int err = 0; struct team_mode_item *mitem; if (!is_good_mode_name(mode->kind) || mode->priv_size > TEAM_MODE_PRIV_SIZE) return -EINVAL; mitem = kmalloc(sizeof(*mitem), GFP_KERNEL); if (!mitem) return -ENOMEM; spin_lock(&mode_list_lock); if (__find_mode(mode->kind)) { err = -EEXIST; kfree(mitem); goto unlock; } mitem->mode = mode; list_add_tail(&mitem->list, &mode_list); unlock: spin_unlock(&mode_list_lock); return err; } EXPORT_SYMBOL(team_mode_register); void team_mode_unregister(const struct team_mode *mode) { struct team_mode_item *mitem; spin_lock(&mode_list_lock); mitem = __find_mode(mode->kind); if (mitem) { list_del_init(&mitem->list); kfree(mitem); } spin_unlock(&mode_list_lock); } EXPORT_SYMBOL(team_mode_unregister); static const struct team_mode *team_mode_get(const char *kind) { struct team_mode_item *mitem; const struct team_mode *mode = NULL; if (!try_module_get(THIS_MODULE)) return NULL; spin_lock(&mode_list_lock); mitem = __find_mode(kind); if (!mitem) { spin_unlock(&mode_list_lock); request_module("team-mode-%s", kind); spin_lock(&mode_list_lock); mitem = __find_mode(kind); } if (mitem) { mode = mitem->mode; if (!try_module_get(mode->owner)) mode = NULL; } spin_unlock(&mode_list_lock); module_put(THIS_MODULE); return mode; } static void team_mode_put(const struct team_mode *mode) { module_put(mode->owner); } static bool team_dummy_transmit(struct team *team, struct sk_buff *skb) { dev_kfree_skb_any(skb); return false; } static rx_handler_result_t team_dummy_receive(struct team *team, struct team_port *port, struct sk_buff *skb) { return RX_HANDLER_ANOTHER; } static const struct team_mode __team_no_mode = { .kind = "*NOMODE*", }; static bool team_is_mode_set(struct team *team) { return team->mode != &__team_no_mode; } static void team_set_no_mode(struct team *team) { team->user_carrier_enabled = false; team->mode = &__team_no_mode; } static void team_adjust_ops(struct team *team) { /* * To avoid checks in rx/tx skb paths, ensure here that non-null and * correct ops are always set. */ if (!team->en_port_count || !team_is_mode_set(team) || !team->mode->ops->transmit) team->ops.transmit = team_dummy_transmit; else team->ops.transmit = team->mode->ops->transmit; if (!team->en_port_count || !team_is_mode_set(team) || !team->mode->ops->receive) team->ops.receive = team_dummy_receive; else team->ops.receive = team->mode->ops->receive; } /* * We can benefit from the fact that it's ensured no port is present * at the time of mode change. Therefore no packets are in fly so there's no * need to set mode operations in any special way. */ static int __team_change_mode(struct team *team, const struct team_mode *new_mode) { /* Check if mode was previously set and do cleanup if so */ if (team_is_mode_set(team)) { void (*exit_op)(struct team *team) = team->ops.exit; /* Clear ops area so no callback is called any longer */ memset(&team->ops, 0, sizeof(struct team_mode_ops)); team_adjust_ops(team); if (exit_op) exit_op(team); team_mode_put(team->mode); team_set_no_mode(team); /* zero private data area */ memset(&team->mode_priv, 0, sizeof(struct team) - offsetof(struct team, mode_priv)); } if (!new_mode) return 0; if (new_mode->ops->init) { int err; err = new_mode->ops->init(team); if (err) return err; } team->mode = new_mode; memcpy(&team->ops, new_mode->ops, sizeof(struct team_mode_ops)); team_adjust_ops(team); return 0; } static int team_change_mode(struct team *team, const char *kind) { const struct team_mode *new_mode; struct net_device *dev = team->dev; int err; if (!list_empty(&team->port_list)) { netdev_err(dev, "No ports can be present during mode change\n"); return -EBUSY; } if (team_is_mode_set(team) && strcmp(team->mode->kind, kind) == 0) { netdev_err(dev, "Unable to change to the same mode the team is in\n"); return -EINVAL; } new_mode = team_mode_get(kind); if (!new_mode) { netdev_err(dev, "Mode \"%s\" not found\n", kind); return -EINVAL; } err = __team_change_mode(team, new_mode); if (err) { netdev_err(dev, "Failed to change to mode \"%s\"\n", kind); team_mode_put(new_mode); return err; } netdev_info(dev, "Mode changed to \"%s\"\n", kind); return 0; } /********************* * Peers notification *********************/ static void team_notify_peers_work(struct work_struct *work) { struct team *team; int val; team = container_of(work, struct team, notify_peers.dw.work); if (!rtnl_trylock()) { schedule_delayed_work(&team->notify_peers.dw, 0); return; } val = atomic_dec_if_positive(&team->notify_peers.count_pending); if (val < 0) { rtnl_unlock(); return; } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev); rtnl_unlock(); if (val) schedule_delayed_work(&team->notify_peers.dw, msecs_to_jiffies(team->notify_peers.interval)); } static void team_notify_peers(struct team *team) { if (!team->notify_peers.count || !netif_running(team->dev)) return; atomic_add(team->notify_peers.count, &team->notify_peers.count_pending); schedule_delayed_work(&team->notify_peers.dw, 0); } static void team_notify_peers_init(struct team *team) { INIT_DELAYED_WORK(&team->notify_peers.dw, team_notify_peers_work); } static void team_notify_peers_fini(struct team *team) { cancel_delayed_work_sync(&team->notify_peers.dw); } /******************************* * Send multicast group rejoins *******************************/ static void team_mcast_rejoin_work(struct work_struct *work) { struct team *team; int val; team = container_of(work, struct team, mcast_rejoin.dw.work); if (!rtnl_trylock()) { schedule_delayed_work(&team->mcast_rejoin.dw, 0); return; } val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending); if (val < 0) { rtnl_unlock(); return; } call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev); rtnl_unlock(); if (val) schedule_delayed_work(&team->mcast_rejoin.dw, msecs_to_jiffies(team->mcast_rejoin.interval)); } static void team_mcast_rejoin(struct team *team) { if (!team->mcast_rejoin.count || !netif_running(team->dev)) return; atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending); schedule_delayed_work(&team->mcast_rejoin.dw, 0); } static void team_mcast_rejoin_init(struct team *team) { INIT_DELAYED_WORK(&team->mcast_rejoin.dw, team_mcast_rejoin_work); } static void team_mcast_rejoin_fini(struct team *team) { cancel_delayed_work_sync(&team->mcast_rejoin.dw); } /************************ * Rx path frame handler ************************/ /* note: already called with rcu_read_lock */ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct team_port *port; struct team *team; rx_handler_result_t res; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; port = team_port_get_rcu(skb->dev); team = port->team; if (!team_port_enabled(port)) { if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) /* link-local packets are mostly useful when stack receives them * with the link they arrive on. */ return RX_HANDLER_PASS; /* allow exact match delivery for disabled ports */ res = RX_HANDLER_EXACT; } else { res = team->ops.receive(team, port, skb); } if (res == RX_HANDLER_ANOTHER) { struct team_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->rx_packets); u64_stats_add(&pcpu_stats->rx_bytes, skb->len); if (skb->pkt_type == PACKET_MULTICAST) u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); skb->dev = team->dev; } else if (res == RX_HANDLER_EXACT) { this_cpu_inc(team->pcpu_stats->rx_nohandler); } else { this_cpu_inc(team->pcpu_stats->rx_dropped); } return res; } /************************************* * Multiqueue Tx port select override *************************************/ static int team_queue_override_init(struct team *team) { struct list_head *listarr; unsigned int queue_cnt = team->dev->num_tx_queues - 1; unsigned int i; if (!queue_cnt) return 0; listarr = kmalloc_array(queue_cnt, sizeof(struct list_head), GFP_KERNEL); if (!listarr) return -ENOMEM; team->qom_lists = listarr; for (i = 0; i < queue_cnt; i++) INIT_LIST_HEAD(listarr++); return 0; } static void team_queue_override_fini(struct team *team) { kfree(team->qom_lists); } static struct list_head *__team_get_qom_list(struct team *team, u16 queue_id) { return &team->qom_lists[queue_id - 1]; } /* * note: already called with rcu_read_lock */ static bool team_queue_override_transmit(struct team *team, struct sk_buff *skb) { struct list_head *qom_list; struct team_port *port; if (!team->queue_override_enabled || !skb->queue_mapping) return false; qom_list = __team_get_qom_list(team, skb->queue_mapping); list_for_each_entry_rcu(port, qom_list, qom_list) { if (!team_dev_queue_xmit(team, port, skb)) return true; } return false; } static void __team_queue_override_port_del(struct team *team, struct team_port *port) { if (!port->queue_id) return; list_del_rcu(&port->qom_list); } static bool team_queue_override_port_has_gt_prio_than(struct team_port *port, struct team_port *cur) { if (port->priority < cur->priority) return true; if (port->priority > cur->priority) return false; if (port->index < cur->index) return true; return false; } static void __team_queue_override_port_add(struct team *team, struct team_port *port) { struct team_port *cur; struct list_head *qom_list; struct list_head *node; if (!port->queue_id) return; qom_list = __team_get_qom_list(team, port->queue_id); node = qom_list; list_for_each_entry(cur, qom_list, qom_list) { if (team_queue_override_port_has_gt_prio_than(port, cur)) break; node = &cur->qom_list; } list_add_tail_rcu(&port->qom_list, node); } static void __team_queue_override_enabled_check(struct team *team) { struct team_port *port; bool enabled = false; list_for_each_entry(port, &team->port_list, list) { if (port->queue_id) { enabled = true; break; } } if (enabled == team->queue_override_enabled) return; netdev_dbg(team->dev, "%s queue override\n", enabled ? "Enabling" : "Disabling"); team->queue_override_enabled = enabled; } static void team_queue_override_port_prio_changed(struct team *team, struct team_port *port) { if (!port->queue_id || team_port_enabled(port)) return; __team_queue_override_port_del(team, port); __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } static void team_queue_override_port_change_queue_id(struct team *team, struct team_port *port, u16 new_queue_id) { if (team_port_enabled(port)) { __team_queue_override_port_del(team, port); port->queue_id = new_queue_id; __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } else { port->queue_id = new_queue_id; } } static void team_queue_override_port_add(struct team *team, struct team_port *port) { __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } static void team_queue_override_port_del(struct team *team, struct team_port *port) { __team_queue_override_port_del(team, port); __team_queue_override_enabled_check(team); } /**************** * Port handling ****************/ static bool team_port_find(const struct team *team, const struct team_port *port) { struct team_port *cur; list_for_each_entry(cur, &team->port_list, list) if (cur == port) return true; return false; } /* * Enable/disable port by adding to enabled port hashlist and setting * port->index (Might be racy so reader could see incorrect ifindex when * processing a flying packet, but that is not a problem). Write guarded * by team->lock. */ static void team_port_enable(struct team *team, struct team_port *port) { if (team_port_enabled(port)) return; port->index = team->en_port_count++; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); team_adjust_ops(team); team_queue_override_port_add(team, port); if (team->ops.port_enabled) team->ops.port_enabled(team, port); team_notify_peers(team); team_mcast_rejoin(team); team_lower_state_changed(port); } static void __reconstruct_port_hlist(struct team *team, int rm_index) { int i; struct team_port *port; for (i = rm_index + 1; i < team->en_port_count; i++) { port = team_get_port_by_index(team, i); hlist_del_rcu(&port->hlist); port->index--; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); } } static void team_port_disable(struct team *team, struct team_port *port) { if (!team_port_enabled(port)) return; if (team->ops.port_disabled) team->ops.port_disabled(team, port); hlist_del_rcu(&port->hlist); __reconstruct_port_hlist(team, port->index); port->index = -1; team->en_port_count--; team_queue_override_port_del(team, port); team_adjust_ops(team); team_lower_state_changed(port); } #define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_HIGHDMA | NETIF_F_LRO | \ NETIF_F_GSO_ENCAP_ALL) #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) static void __team_compute_features(struct team *team) { struct team_port *port; netdev_features_t vlan_features = TEAM_VLAN_FEATURES; netdev_features_t enc_features = TEAM_ENC_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; rcu_read_lock(); if (list_empty(&team->port_list)) goto done; vlan_features = netdev_base_features(vlan_features); enc_features = netdev_base_features(enc_features); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, TEAM_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, port->dev->hw_enc_features, TEAM_ENC_FEATURES); dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; team->dev->hard_header_len = max_hard_header_len; team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) team->dev->priv_flags |= IFF_XMIT_DST_RELEASE; } static void team_compute_features(struct team *team) { __team_compute_features(team); netdev_change_features(team->dev); } static int team_port_enter(struct team *team, struct team_port *port) { int err = 0; dev_hold(team->dev); if (team->ops.port_enter) { err = team->ops.port_enter(team, port); if (err) { netdev_err(team->dev, "Device %s failed to enter team mode\n", port->dev->name); goto err_port_enter; } } return 0; err_port_enter: dev_put(team->dev); return err; } static void team_port_leave(struct team *team, struct team_port *port) { if (team->ops.port_leave) team->ops.port_leave(team, port); dev_put(team->dev); } #ifdef CONFIG_NET_POLL_CONTROLLER static int __team_port_enable_netpoll(struct team_port *port) { struct netpoll *np; int err; np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) return -ENOMEM; err = __netpoll_setup(np, port->dev); if (err) { kfree(np); return err; } port->np = np; return err; } static int team_port_enable_netpoll(struct team_port *port) { if (!port->team->dev->npinfo) return 0; return __team_port_enable_netpoll(port); } static void team_port_disable_netpoll(struct team_port *port) { struct netpoll *np = port->np; if (!np) return; port->np = NULL; __netpoll_free(np); } #else static int team_port_enable_netpoll(struct team_port *port) { return 0; } static void team_port_disable_netpoll(struct team_port *port) { } #endif static int team_upper_dev_link(struct team *team, struct team_port *port, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; int err; lag_upper_info.tx_type = team->mode->lag_tx_type; lag_upper_info.hash_type = NETDEV_LAG_HASH_UNKNOWN; err = netdev_master_upper_dev_link(port->dev, team->dev, NULL, &lag_upper_info, extack); if (err) return err; port->dev->priv_flags |= IFF_TEAM_PORT; return 0; } static void team_upper_dev_unlink(struct team *team, struct team_port *port) { netdev_upper_dev_unlink(port->dev, team->dev); port->dev->priv_flags &= ~IFF_TEAM_PORT; } static void __team_port_change_port_added(struct team_port *port, bool linkup); static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev); static int team_port_add(struct team *team, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct net_device *dev = team->dev; struct team_port *port; char *portname = port_dev->name; int err; if (port_dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Loopback device can't be added as a team port"); netdev_err(dev, "Device %s is loopback device. Loopback devices can't be added as a team port\n", portname); return -EINVAL; } if (netif_is_team_port(port_dev)) { NL_SET_ERR_MSG(extack, "Device is already a port of a team device"); netdev_err(dev, "Device %s is already a port " "of a team device\n", portname); return -EBUSY; } if (dev == port_dev) { NL_SET_ERR_MSG(extack, "Cannot enslave team device to itself"); netdev_err(dev, "Cannot enslave team device to itself\n"); return -EINVAL; } if (netdev_has_upper_dev(dev, port_dev)) { NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface"); netdev_err(dev, "Device %s is already an upper device of the team interface\n", portname); return -EBUSY; } if (netdev_has_upper_dev(port_dev, dev)) { NL_SET_ERR_MSG(extack, "Device is already a lower device of the team interface"); netdev_err(dev, "Device %s is already a lower device of the team interface\n", portname); return -EBUSY; } if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); netdev_err(dev, "Device %s is VLAN challenged and team device has VLAN set up\n", portname); return -EPERM; } err = team_dev_type_check_change(dev, port_dev); if (err) return err; if (port_dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Device is up. Set it down before adding it as a team port"); netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n", portname); return -EBUSY; } port = kzalloc(sizeof(struct team_port) + team->mode->port_priv_size, GFP_KERNEL); if (!port) return -ENOMEM; port->dev = port_dev; port->team = team; INIT_LIST_HEAD(&port->qom_list); port->orig.mtu = port_dev->mtu; err = dev_set_mtu(port_dev, dev->mtu); if (err) { netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); goto err_set_mtu; } memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len); err = team_port_enter(team, port); if (err) { netdev_err(dev, "Device %s failed to enter team mode\n", portname); goto err_port_enter; } err = dev_open(port_dev, extack); if (err) { netdev_dbg(dev, "Device %s opening failed\n", portname); goto err_dev_open; } err = vlan_vids_add_by_dev(port_dev, dev); if (err) { netdev_err(dev, "Failed to add vlan ids to device %s\n", portname); goto err_vids_add; } err = team_port_enable_netpoll(port); if (err) { netdev_err(dev, "Failed to enable netpoll on device %s\n", portname); goto err_enable_netpoll; } if (!(dev->features & NETIF_F_LRO)) dev_disable_lro(port_dev); err = netdev_rx_handler_register(port_dev, team_handle_frame, port); if (err) { netdev_err(dev, "Device %s failed to register rx_handler\n", portname); goto err_handler_register; } err = team_upper_dev_link(team, port, extack); if (err) { netdev_err(dev, "Device %s failed to set upper link\n", portname); goto err_set_upper_link; } err = __team_option_inst_add_port(team, port); if (err) { netdev_err(dev, "Device %s failed to add per-port options\n", portname); goto err_option_port_add; } /* set promiscuity level to new slave */ if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(port_dev, 1); if (err) goto err_set_slave_promisc; } /* set allmulti level to new slave */ if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(port_dev, 1); if (err) { if (dev->flags & IFF_PROMISC) dev_set_promiscuity(port_dev, -1); goto err_set_slave_promisc; } } if (dev->flags & IFF_UP) { netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); netif_addr_unlock_bh(dev); } port->index = -1; list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); __team_compute_features(team); __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); return 0; err_set_slave_promisc: __team_option_inst_del_port(team, port); err_option_port_add: team_upper_dev_unlink(team, port); err_set_upper_link: netdev_rx_handler_unregister(port_dev); err_handler_register: team_port_disable_netpoll(port); err_enable_netpoll: vlan_vids_del_by_dev(port_dev, dev); err_vids_add: dev_close(port_dev); err_dev_open: team_port_leave(team, port); team_port_set_orig_dev_addr(port); err_port_enter: dev_set_mtu(port_dev, port->orig.mtu); err_set_mtu: kfree(port); return err; } static void __team_port_change_port_removed(struct team_port *port); static int team_port_del(struct team *team, struct net_device *port_dev) { struct net_device *dev = team->dev; struct team_port *port; char *portname = port_dev->name; port = team_port_get_rtnl(port_dev); if (!port || !team_port_find(team, port)) { netdev_err(dev, "Device %s does not act as a port of this team\n", portname); return -ENOENT; } team_port_disable(team, port); list_del_rcu(&port->list); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(port_dev, -1); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(port_dev, -1); team_upper_dev_unlink(team, port); netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); if (dev->flags & IFF_UP) { dev_uc_unsync(port_dev, dev); dev_mc_unsync(port_dev, dev); } dev_close(port_dev); team_port_leave(team, port); __team_option_inst_mark_removed_port(team, port); __team_options_change_check(team); __team_option_inst_del_port(team, port); __team_port_change_port_removed(port); team_port_set_orig_dev_addr(port); dev_set_mtu(port_dev, port->orig.mtu); kfree_rcu(port, rcu); netdev_info(dev, "Port device %s removed\n", portname); __team_compute_features(team); return 0; } /***************** * Net device ops *****************/ static void team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.str_val = team->mode->kind; } static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) { return team_change_mode(team, ctx->data.str_val); } static void team_notify_peers_count_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.count; } static int team_notify_peers_count_set(struct team *team, struct team_gsetter_ctx *ctx) { team->notify_peers.count = ctx->data.u32_val; return 0; } static void team_notify_peers_interval_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.interval; } static int team_notify_peers_interval_set(struct team *team, struct team_gsetter_ctx *ctx) { team->notify_peers.interval = ctx->data.u32_val; return 0; } static void team_mcast_rejoin_count_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.count; } static int team_mcast_rejoin_count_set(struct team *team, struct team_gsetter_ctx *ctx) { team->mcast_rejoin.count = ctx->data.u32_val; return 0; } static void team_mcast_rejoin_interval_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.interval; } static int team_mcast_rejoin_interval_set(struct team *team, struct team_gsetter_ctx *ctx) { team->mcast_rejoin.interval = ctx->data.u32_val; return 0; } static void team_port_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = team_port_enabled(port); } static int team_port_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; if (ctx->data.bool_val) team_port_enable(team, port); else team_port_disable(team, port); return 0; } static void team_user_linkup_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup; } static void __team_carrier_check(struct team *team); static int team_user_linkup_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; port->user.linkup = ctx->data.bool_val; team_refresh_port_linkup(port); __team_carrier_check(port->team); return 0; } static void team_user_linkup_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup_enabled; } static int team_user_linkup_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; port->user.linkup_enabled = ctx->data.bool_val; team_refresh_port_linkup(port); __team_carrier_check(port->team); return 0; } static void team_priority_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.s32_val = port->priority; } static int team_priority_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; s32 priority = ctx->data.s32_val; if (port->priority == priority) return 0; port->priority = priority; team_queue_override_port_prio_changed(team, port); return 0; } static void team_queue_id_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.u32_val = port->queue_id; } static int team_queue_id_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; u16 new_queue_id = ctx->data.u32_val; if (port->queue_id == new_queue_id) return 0; if (new_queue_id >= team->dev->real_num_tx_queues) return -EINVAL; team_queue_override_port_change_queue_id(team, port, new_queue_id); return 0; } static const struct team_option team_options[] = { { .name = "mode", .type = TEAM_OPTION_TYPE_STRING, .getter = team_mode_option_get, .setter = team_mode_option_set, }, { .name = "notify_peers_count", .type = TEAM_OPTION_TYPE_U32, .getter = team_notify_peers_count_get, .setter = team_notify_peers_count_set, }, { .name = "notify_peers_interval", .type = TEAM_OPTION_TYPE_U32, .getter = team_notify_peers_interval_get, .setter = team_notify_peers_interval_set, }, { .name = "mcast_rejoin_count", .type = TEAM_OPTION_TYPE_U32, .getter = team_mcast_rejoin_count_get, .setter = team_mcast_rejoin_count_set, }, { .name = "mcast_rejoin_interval", .type = TEAM_OPTION_TYPE_U32, .getter = team_mcast_rejoin_interval_get, .setter = team_mcast_rejoin_interval_set, }, { .name = "enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_port_en_option_get, .setter = team_port_en_option_set, }, { .name = "user_linkup", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_user_linkup_option_get, .setter = team_user_linkup_option_set, }, { .name = "user_linkup_enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_user_linkup_en_option_get, .setter = team_user_linkup_en_option_set, }, { .name = "priority", .type = TEAM_OPTION_TYPE_S32, .per_port = true, .getter = team_priority_option_get, .setter = team_priority_option_set, }, { .name = "queue_id", .type = TEAM_OPTION_TYPE_U32, .per_port = true, .getter = team_queue_id_option_get, .setter = team_queue_id_option_set, }, }; static int team_init(struct net_device *dev) { struct team *team = netdev_priv(dev); int i; int err; team->dev = dev; team_set_no_mode(team); team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) return -ENOMEM; for (i = 0; i < TEAM_PORT_HASHENTRIES; i++) INIT_HLIST_HEAD(&team->en_port_hlist[i]); INIT_LIST_HEAD(&team->port_list); err = team_queue_override_init(team); if (err) goto err_team_queue_override_init; team_adjust_ops(team); INIT_LIST_HEAD(&team->option_list); INIT_LIST_HEAD(&team->option_inst_list); team_notify_peers_init(team); team_mcast_rejoin_init(team); err = team_options_register(team, team_options, ARRAY_SIZE(team_options)); if (err) goto err_options_register; netif_carrier_off(dev); lockdep_register_key(&team->team_lock_key); __mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key); netdev_lockdep_set_classes(dev); return 0; err_options_register: team_mcast_rejoin_fini(team); team_notify_peers_fini(team); team_queue_override_fini(team); err_team_queue_override_init: free_percpu(team->pcpu_stats); return err; } static void team_uninit(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; struct team_port *tmp; mutex_lock(&team->lock); list_for_each_entry_safe(port, tmp, &team->port_list, list) team_port_del(team, port->dev); __team_change_mode(team, NULL); /* cleanup */ __team_options_unregister(team, team_options, ARRAY_SIZE(team_options)); team_mcast_rejoin_fini(team); team_notify_peers_fini(team); team_queue_override_fini(team); mutex_unlock(&team->lock); netdev_change_features(dev); lockdep_unregister_key(&team->team_lock_key); } static void team_destructor(struct net_device *dev) { struct team *team = netdev_priv(dev); free_percpu(team->pcpu_stats); } static int team_open(struct net_device *dev) { return 0; } static int team_close(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; list_for_each_entry(port, &team->port_list, list) { dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); } return 0; } /* * note: already called with rcu_read_lock */ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) { struct team *team = netdev_priv(dev); bool tx_success; unsigned int len = skb->len; tx_success = team_queue_override_transmit(team, skb); if (!tx_success) tx_success = team->ops.transmit(team, skb); if (tx_success) { struct team_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(team->pcpu_stats->tx_dropped); } return NETDEV_TX_OK; } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* * This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to * skb_tx_hash and will put the skbs in the queue we expect on their * way down to the team driver. */ u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* * Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; if (unlikely(txq >= dev->real_num_tx_queues)) { do { txq -= dev->real_num_tx_queues; } while (txq >= dev->real_num_tx_queues); } return txq; } static void team_change_rx_flags(struct net_device *dev, int change) { struct team *team = netdev_priv(dev); struct team_port *port; int inc; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { if (change & IFF_PROMISC) { inc = dev->flags & IFF_PROMISC ? 1 : -1; dev_set_promiscuity(port->dev, inc); } if (change & IFF_ALLMULTI) { inc = dev->flags & IFF_ALLMULTI ? 1 : -1; dev_set_allmulti(port->dev, inc); } } rcu_read_unlock(); } static void team_set_rx_mode(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { dev_uc_sync_multiple(port->dev, dev); dev_mc_sync_multiple(port->dev, dev); } rcu_read_unlock(); } static int team_set_mac_address(struct net_device *dev, void *p) { struct sockaddr *addr = p; struct team *team = netdev_priv(dev); struct team_port *port; if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; dev_addr_set(dev, addr->sa_data); mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) team->ops.port_change_dev_addr(team, port); mutex_unlock(&team->lock); return 0; } static int team_change_mtu(struct net_device *dev, int new_mtu) { struct team *team = netdev_priv(dev); struct team_port *port; int err; /* * Alhough this is reader, it's guarded by team lock. It's not possible * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); team->port_mtu_change_allowed = true; list_for_each_entry(port, &team->port_list, list) { err = dev_set_mtu(port->dev, new_mtu); if (err) { netdev_err(dev, "Device %s failed to change mtu", port->dev->name); goto unwind; } } team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); WRITE_ONCE(dev->mtu, new_mtu); return 0; unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) dev_set_mtu(port->dev, dev->mtu); team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); return err; } static void team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct team *team = netdev_priv(dev); struct team_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_dropped = 0, tx_dropped = 0, rx_nohandler = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(team->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* * rx_dropped, tx_dropped & rx_nohandler are u32, * updated without syncp protection. */ rx_dropped += READ_ONCE(p->rx_dropped); tx_dropped += READ_ONCE(p->tx_dropped); rx_nohandler += READ_ONCE(p->rx_nohandler); } stats->rx_dropped = rx_dropped; stats->tx_dropped = tx_dropped; stats->rx_nohandler = rx_nohandler; } static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct team *team = netdev_priv(dev); struct team_port *port; int err; /* * Alhough this is reader, it's guarded by team lock. It's not possible * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { err = vlan_vid_add(port->dev, proto, vid); if (err) goto unwind; } mutex_unlock(&team->lock); return 0; unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); mutex_unlock(&team->lock); return err; } static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct team *team = netdev_priv(dev); struct team_port *port; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); mutex_unlock(&team->lock); return 0; } #ifdef CONFIG_NET_POLL_CONTROLLER static void team_poll_controller(struct net_device *dev) { } static void __team_netpoll_cleanup(struct team *team) { struct team_port *port; list_for_each_entry(port, &team->port_list, list) team_port_disable_netpoll(port); } static void team_netpoll_cleanup(struct net_device *dev) { struct team *team = netdev_priv(dev); mutex_lock(&team->lock); __team_netpoll_cleanup(team); mutex_unlock(&team->lock); } static int team_netpoll_setup(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; int err = 0; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { err = __team_port_enable_netpoll(port); if (err) { __team_netpoll_cleanup(team); break; } } mutex_unlock(&team->lock); return err; } #endif static int team_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct team *team = netdev_priv(dev); int err; mutex_lock(&team->lock); err = team_port_add(team, port_dev, extack); mutex_unlock(&team->lock); if (!err) netdev_change_features(dev); return err; } static int team_del_slave(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); int err; mutex_lock(&team->lock); err = team_port_del(team, port_dev); mutex_unlock(&team->lock); if (err) return err; if (netif_is_team_master(port_dev)) { lockdep_unregister_key(&team->team_lock_key); lockdep_register_key(&team->team_lock_key); lockdep_set_class(&team->lock, &team->team_lock_key); } netdev_change_features(dev); return err; } static netdev_features_t team_fix_features(struct net_device *dev, netdev_features_t features) { struct team_port *port; struct team *team = netdev_priv(dev); netdev_features_t mask; mask = features; features = netdev_base_features(features); rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { features = netdev_increment_features(features, port->dev->features, mask); } rcu_read_unlock(); features = netdev_add_tso_features(features, mask); return features; } static int team_change_carrier(struct net_device *dev, bool new_carrier) { struct team *team = netdev_priv(dev); team->user_carrier_enabled = true; if (new_carrier) netif_carrier_on(dev); else netif_carrier_off(dev); return 0; } static const struct net_device_ops team_netdev_ops = { .ndo_init = team_init, .ndo_uninit = team_uninit, .ndo_open = team_open, .ndo_stop = team_close, .ndo_start_xmit = team_xmit, .ndo_select_queue = team_select_queue, .ndo_change_rx_flags = team_change_rx_flags, .ndo_set_rx_mode = team_set_rx_mode, .ndo_set_mac_address = team_set_mac_address, .ndo_change_mtu = team_change_mtu, .ndo_get_stats64 = team_get_stats64, .ndo_vlan_rx_add_vid = team_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = team_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = team_poll_controller, .ndo_netpoll_setup = team_netpoll_setup, .ndo_netpoll_cleanup = team_netpoll_cleanup, #endif .ndo_add_slave = team_add_slave, .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, .ndo_features_check = passthru_features_check, }; /*********************** * ethtool interface ***********************/ static void team_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); } static int team_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct team *team= netdev_priv(dev); unsigned long speed = 0; struct team_port *port; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { if (team_port_txable(port)) { if (port->state.speed != SPEED_UNKNOWN) speed += port->state.speed; if (cmd->base.duplex == DUPLEX_UNKNOWN && port->state.duplex != DUPLEX_UNKNOWN) cmd->base.duplex = port->state.duplex; } } rcu_read_unlock(); cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; } static const struct ethtool_ops team_ethtool_ops = { .get_drvinfo = team_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = team_ethtool_get_link_ksettings, }; /*********************** * rt netlink interface ***********************/ static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); if (port_dev->type == ARPHRD_ETHER) dev->header_ops = team->header_ops_cache; else dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; dev->addr_len = port_dev->addr_len; dev->mtu = port_dev->mtu; memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len); eth_hw_addr_inherit(dev, port_dev); if (port_dev->flags & IFF_POINTOPOINT) { dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } else if ((port_dev->flags & (IFF_BROADCAST | IFF_MULTICAST)) == (IFF_BROADCAST | IFF_MULTICAST)) { dev->flags |= (IFF_BROADCAST | IFF_MULTICAST); dev->flags &= ~(IFF_POINTOPOINT | IFF_NOARP); } } static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); char *portname = port_dev->name; int err; if (dev->type == port_dev->type) return 0; if (!list_empty(&team->port_list)) { netdev_err(dev, "Device %s is of different type\n", portname); return -EBUSY; } err = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, dev); err = notifier_to_errno(err); if (err) { netdev_err(dev, "Refused to change device type\n"); return err; } dev_uc_flush(dev); dev_mc_flush(dev); team_setup_by_port(dev, port_dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); return 0; } static void team_setup(struct net_device *dev) { struct team *team = netdev_priv(dev); ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; team->header_ops_cache = dev->header_ops; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = team_destructor; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_TEAM; /* * Indicate we support unicast address filtering. That way core won't * bring us to promisc mode in case a unicast addr is added. * Let this up to underlay drivers. */ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; dev->lltx = true; /* Don't allow team devices to change network namespaces. */ dev->netns_immutable = true; dev->features |= NETIF_F_GRO; dev->hw_features = TEAM_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } static int team_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **tb = params->tb; if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); return register_netdevice(dev); } static int team_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static unsigned int team_get_num_tx_queues(void) { return TEAM_DEFAULT_NUM_TX_QUEUES; } static unsigned int team_get_num_rx_queues(void) { return TEAM_DEFAULT_NUM_RX_QUEUES; } static struct rtnl_link_ops team_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct team), .setup = team_setup, .newlink = team_newlink, .validate = team_validate, .get_num_tx_queues = team_get_num_tx_queues, .get_num_rx_queues = team_get_num_rx_queues, }; /*********************************** * Generic netlink custom interface ***********************************/ static struct genl_family team_nl_family; int team_nl_noop_doit(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &team_nl_family, 0, TEAM_CMD_NOOP); if (!hdr) { err = -EMSGSIZE; goto err_msg_put; } genlmsg_end(msg, hdr); return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); err_msg_put: nlmsg_free(msg); return err; } /* * Netlink cmd functions should be locked by following two functions. * Since dev gets held here, that ensures dev won't disappear in between. */ static struct team *team_nl_team_get(struct genl_info *info) { struct net *net = genl_info_net(info); int ifindex; struct net_device *dev; struct team *team; if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX]) return NULL; ifindex = nla_get_u32(info->attrs[TEAM_ATTR_TEAM_IFINDEX]); dev = dev_get_by_index(net, ifindex); if (!dev || dev->netdev_ops != &team_netdev_ops) { dev_put(dev); return NULL; } team = netdev_priv(dev); mutex_lock(&team->lock); return team; } static void team_nl_team_put(struct team *team) { mutex_unlock(&team->lock); dev_put(team->dev); } typedef int team_nl_send_func_t(struct sk_buff *skb, struct team *team, u32 portid); static int team_nl_send_unicast(struct sk_buff *skb, struct team *team, u32 portid) { return genlmsg_unicast(dev_net(team->dev), skb, portid); } static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team, struct team_option_inst *opt_inst) { struct nlattr *option_item; struct team_option *option = opt_inst->option; struct team_option_inst_info *opt_inst_info = &opt_inst->info; struct team_gsetter_ctx ctx; int err; ctx.info = opt_inst_info; err = team_option_get(team, opt_inst, &ctx); if (err) return err; option_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_OPTION); if (!option_item) return -EMSGSIZE; if (nla_put_string(skb, TEAM_ATTR_OPTION_NAME, option->name)) goto nest_cancel; if (opt_inst_info->port && nla_put_u32(skb, TEAM_ATTR_OPTION_PORT_IFINDEX, opt_inst_info->port->dev->ifindex)) goto nest_cancel; if (opt_inst->option->array_size && nla_put_u32(skb, TEAM_ATTR_OPTION_ARRAY_INDEX, opt_inst_info->array_index)) goto nest_cancel; switch (option->type) { case TEAM_OPTION_TYPE_U32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.u32_val)) goto nest_cancel; break; case TEAM_OPTION_TYPE_STRING: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING)) goto nest_cancel; if (nla_put_string(skb, TEAM_ATTR_OPTION_DATA, ctx.data.str_val)) goto nest_cancel; break; case TEAM_OPTION_TYPE_BINARY: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_BINARY)) goto nest_cancel; if (nla_put(skb, TEAM_ATTR_OPTION_DATA, ctx.data.bin_val.len, ctx.data.bin_val.ptr)) goto nest_cancel; break; case TEAM_OPTION_TYPE_BOOL: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_FLAG)) goto nest_cancel; if (ctx.data.bool_val && nla_put_flag(skb, TEAM_ATTR_OPTION_DATA)) goto nest_cancel; break; case TEAM_OPTION_TYPE_S32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_S32)) goto nest_cancel; if (nla_put_s32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.s32_val)) goto nest_cancel; break; default: BUG(); } if (opt_inst->removed && nla_put_flag(skb, TEAM_ATTR_OPTION_REMOVED)) goto nest_cancel; if (opt_inst->changed) { if (nla_put_flag(skb, TEAM_ATTR_OPTION_CHANGED)) goto nest_cancel; opt_inst->changed = false; } nla_nest_end(skb, option_item); return 0; nest_cancel: nla_nest_cancel(skb, option_item); return -EMSGSIZE; } static int __send_and_alloc_skb(struct sk_buff **pskb, struct team *team, u32 portid, team_nl_send_func_t *send_func) { int err; if (*pskb) { err = send_func(*pskb, team, portid); if (err) return err; } *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!*pskb) return -ENOMEM; return 0; } static int team_nl_send_options_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct list_head *sel_opt_inst_list) { struct nlattr *option_list; struct nlmsghdr *nlh; void *hdr; struct team_option_inst *opt_inst; int err; struct sk_buff *skb = NULL; bool incomplete; int i; opt_inst = list_first_entry(sel_opt_inst_list, struct team_option_inst, tmp_list); start_again: err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; option_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_OPTION); if (!option_list) goto nla_put_failure; i = 0; incomplete = false; list_for_each_entry_from(opt_inst, sel_opt_inst_list, tmp_list) { err = team_nl_fill_one_option_get(skb, team, opt_inst); if (err) { if (err == -EMSGSIZE) { if (!i) goto errout; incomplete = true; break; } goto errout; } i++; } nla_nest_end(skb, option_list); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; goto send_done; } return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; errout: nlmsg_free(skb); return err; } int team_nl_options_get_doit(struct sk_buff *skb, struct genl_info *info) { struct team *team; struct team_option_inst *opt_inst; int err; LIST_HEAD(sel_opt_inst_list); team = team_nl_team_get(info); if (!team) return -EINVAL; list_for_each_entry(opt_inst, &team->option_inst_list, list) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); err = team_nl_send_options_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, &sel_opt_inst_list); team_nl_team_put(team); return err; } static int team_nl_send_event_options_get(struct team *team, struct list_head *sel_opt_inst_list); int team_nl_options_set_doit(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err = 0; int i; struct nlattr *nl_option; rtnl_lock(); team = team_nl_team_get(info); if (!team) { err = -EINVAL; goto rtnl_unlock; } err = -EINVAL; if (!info->attrs[TEAM_ATTR_LIST_OPTION]) { err = -EINVAL; goto team_put; } nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) { struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; bool opt_is_array = false; struct team_option_inst *opt_inst; char *opt_name; bool opt_found = false; if (nla_type(nl_option) != TEAM_ATTR_ITEM_OPTION) { err = -EINVAL; goto team_put; } err = nla_parse_nested_deprecated(opt_attrs, TEAM_ATTR_OPTION_MAX, nl_option, team_attr_option_nl_policy, info->extack); if (err) goto team_put; if (!opt_attrs[TEAM_ATTR_OPTION_NAME] || !opt_attrs[TEAM_ATTR_OPTION_TYPE]) { err = -EINVAL; goto team_put; } switch (nla_get_u8(opt_attrs[TEAM_ATTR_OPTION_TYPE])) { case NLA_U32: opt_type = TEAM_OPTION_TYPE_U32; break; case NLA_STRING: opt_type = TEAM_OPTION_TYPE_STRING; break; case NLA_BINARY: opt_type = TEAM_OPTION_TYPE_BINARY; break; case NLA_FLAG: opt_type = TEAM_OPTION_TYPE_BOOL; break; case NLA_S32: opt_type = TEAM_OPTION_TYPE_S32; break; default: goto team_put; } attr_data = opt_attrs[TEAM_ATTR_OPTION_DATA]; if (opt_type != TEAM_OPTION_TYPE_BOOL && !attr_data) { err = -EINVAL; goto team_put; } opt_name = nla_data(opt_attrs[TEAM_ATTR_OPTION_NAME]); attr = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; if (attr) opt_port_ifindex = nla_get_u32(attr); attr = opt_attrs[TEAM_ATTR_OPTION_ARRAY_INDEX]; if (attr) { opt_is_array = true; opt_array_index = nla_get_u32(attr); } list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct team_option *option = opt_inst->option; struct team_gsetter_ctx ctx; struct team_option_inst_info *opt_inst_info; int tmp_ifindex; opt_inst_info = &opt_inst->info; tmp_ifindex = opt_inst_info->port ? opt_inst_info->port->dev->ifindex : 0; if (option->type != opt_type || strcmp(option->name, opt_name) || tmp_ifindex != opt_port_ifindex || (option->array_size && !opt_is_array) || opt_inst_info->array_index != opt_array_index) continue; opt_found = true; ctx.info = opt_inst_info; switch (opt_type) { case TEAM_OPTION_TYPE_U32: ctx.data.u32_val = nla_get_u32(attr_data); break; case TEAM_OPTION_TYPE_STRING: if (nla_len(attr_data) > TEAM_STRING_MAX_LEN || !memchr(nla_data(attr_data), '\0', nla_len(attr_data))) { err = -EINVAL; goto team_put; } ctx.data.str_val = nla_data(attr_data); break; case TEAM_OPTION_TYPE_BINARY: ctx.data.bin_val.len = nla_len(attr_data); ctx.data.bin_val.ptr = nla_data(attr_data); break; case TEAM_OPTION_TYPE_BOOL: ctx.data.bool_val = attr_data ? true : false; break; case TEAM_OPTION_TYPE_S32: ctx.data.s32_val = nla_get_s32(attr_data); break; default: BUG(); } err = team_option_set(team, opt_inst, &ctx); if (err) goto team_put; opt_inst->changed = true; list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } err = team_nl_send_event_options_get(team, &opt_inst_list); if (err) break; } team_put: team_nl_team_put(team); rtnl_unlock: rtnl_unlock(); return err; } static int team_nl_fill_one_port_get(struct sk_buff *skb, struct team_port *port) { struct nlattr *port_item; port_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_PORT); if (!port_item) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex)) goto nest_cancel; if (port->changed) { if (nla_put_flag(skb, TEAM_ATTR_PORT_CHANGED)) goto nest_cancel; port->changed = false; } if ((port->removed && nla_put_flag(skb, TEAM_ATTR_PORT_REMOVED)) || (port->state.linkup && nla_put_flag(skb, TEAM_ATTR_PORT_LINKUP)) || nla_put_u32(skb, TEAM_ATTR_PORT_SPEED, port->state.speed) || nla_put_u8(skb, TEAM_ATTR_PORT_DUPLEX, port->state.duplex)) goto nest_cancel; nla_nest_end(skb, port_item); return 0; nest_cancel: nla_nest_cancel(skb, port_item); return -EMSGSIZE; } static int team_nl_send_port_list_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct team_port *one_port) { struct nlattr *port_list; struct nlmsghdr *nlh; void *hdr; struct team_port *port; int err; struct sk_buff *skb = NULL; bool incomplete; int i; port = list_first_entry_or_null(&team->port_list, struct team_port, list); start_again: err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_PORT_LIST_GET); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; port_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_PORT); if (!port_list) goto nla_put_failure; i = 0; incomplete = false; /* If one port is selected, called wants to send port list containing * only this port. Otherwise go through all listed ports and send all */ if (one_port) { err = team_nl_fill_one_port_get(skb, one_port); if (err) goto errout; } else if (port) { list_for_each_entry_from(port, &team->port_list, list) { err = team_nl_fill_one_port_get(skb, port); if (err) { if (err == -EMSGSIZE) { if (!i) goto errout; incomplete = true; break; } goto errout; } i++; } } nla_nest_end(skb, port_list); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; goto send_done; } return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; errout: nlmsg_free(skb); return err; } int team_nl_port_list_get_doit(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err; team = team_nl_team_get(info); if (!team) return -EINVAL; err = team_nl_send_port_list_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, NULL); team_nl_team_put(team); return err; } static const struct genl_multicast_group team_nl_mcgrps[] = { { .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME, }, }; static struct genl_family team_nl_family __ro_after_init = { .name = TEAM_GENL_NAME, .version = TEAM_GENL_VERSION, .maxattr = ARRAY_SIZE(team_nl_policy) - 1, .policy = team_nl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = team_nl_ops, .n_small_ops = ARRAY_SIZE(team_nl_ops), .resv_start_op = TEAM_CMD_PORT_LIST_GET + 1, .mcgrps = team_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(team_nl_mcgrps), }; static int team_nl_send_multicast(struct sk_buff *skb, struct team *team, u32 portid) { return genlmsg_multicast_netns(&team_nl_family, dev_net(team->dev), skb, 0, 0, GFP_KERNEL); } static int team_nl_send_event_options_get(struct team *team, struct list_head *sel_opt_inst_list) { return team_nl_send_options_get(team, 0, 0, 0, team_nl_send_multicast, sel_opt_inst_list); } static int team_nl_send_event_port_get(struct team *team, struct team_port *port) { return team_nl_send_port_list_get(team, 0, 0, 0, team_nl_send_multicast, port); } static int __init team_nl_init(void) { return genl_register_family(&team_nl_family); } static void __exit team_nl_fini(void) { genl_unregister_family(&team_nl_family); } /****************** * Change checkers ******************/ static void __team_options_change_check(struct team *team) { int err; struct team_option_inst *opt_inst; LIST_HEAD(sel_opt_inst_list); list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->changed) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); } err = team_nl_send_event_options_get(team, &sel_opt_inst_list); if (err && err != -ESRCH) netdev_warn(team->dev, "Failed to send options change via netlink (err %d)\n", err); } /* rtnl lock is held */ static void __team_port_change_send(struct team_port *port, bool linkup) { int err; port->changed = true; port->state.linkup = linkup; team_refresh_port_linkup(port); if (linkup) { struct ethtool_link_ksettings ecmd; err = __ethtool_get_link_ksettings(port->dev, &ecmd); if (!err) { port->state.speed = ecmd.base.speed; port->state.duplex = ecmd.base.duplex; goto send_event; } } port->state.speed = 0; port->state.duplex = 0; send_event: err = team_nl_send_event_port_get(port->team, port); if (err && err != -ESRCH) netdev_warn(port->team->dev, "Failed to send port change of device %s via netlink (err %d)\n", port->dev->name, err); } static void __team_carrier_check(struct team *team) { struct team_port *port; bool team_linkup; if (team->user_carrier_enabled) return; team_linkup = false; list_for_each_entry(port, &team->port_list, list) { if (port->linkup) { team_linkup = true; break; } } if (team_linkup) netif_carrier_on(team->dev); else netif_carrier_off(team->dev); } static void __team_port_change_check(struct team_port *port, bool linkup) { if (port->state.linkup != linkup) __team_port_change_send(port, linkup); __team_carrier_check(port->team); } static void __team_port_change_port_added(struct team_port *port, bool linkup) { __team_port_change_send(port, linkup); __team_carrier_check(port->team); } static void __team_port_change_port_removed(struct team_port *port) { port->removed = true; __team_port_change_send(port, false); __team_carrier_check(port->team); } static void team_port_change_check(struct team_port *port, bool linkup) { struct team *team = port->team; mutex_lock(&team->lock); __team_port_change_check(port, linkup); mutex_unlock(&team->lock); } /************************************ * Net device notifier event handler ************************************/ static int team_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct team_port *port; port = team_port_get_rtnl(dev); if (!port) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (netif_oper_up(dev)) team_port_change_check(port, true); break; case NETDEV_DOWN: team_port_change_check(port, false); break; case NETDEV_CHANGE: if (netif_running(port->dev)) team_port_change_check(port, !!netif_oper_up(port->dev)); break; case NETDEV_UNREGISTER: team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: if (!port->team->notifier_ctx) { port->team->notifier_ctx = true; team_compute_features(port->team); port->team->notifier_ctx = false; } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ if (!port->team->port_mtu_change_allowed) return NOTIFY_BAD; break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, port->team->dev); break; } return NOTIFY_DONE; } static struct notifier_block team_notifier_block __read_mostly = { .notifier_call = team_device_event, }; /*********************** * Module init and exit ***********************/ static int __init team_module_init(void) { int err; register_netdevice_notifier(&team_notifier_block); err = rtnl_link_register(&team_link_ops); if (err) goto err_rtnl_reg; err = team_nl_init(); if (err) goto err_nl_init; return 0; err_nl_init: rtnl_link_unregister(&team_link_ops); err_rtnl_reg: unregister_netdevice_notifier(&team_notifier_block); return err; } static void __exit team_module_exit(void) { team_nl_fini(); rtnl_link_unregister(&team_link_ops); unregister_netdevice_notifier(&team_notifier_block); } module_init(team_module_init); module_exit(team_module_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>"); MODULE_DESCRIPTION("Ethernet team device driver"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 320 320 256 256 160 8 159 23 3 32 26 27 14 3 3 31 31 25 32 1 126 125 32 27 32 28 164 1 164 485 486 1 23 168 226 265 14 23 23 15 19 23 24 1 292 134 270 74 254 16 269 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP CUBIC: Binary Increase Congestion control for TCP v2.3 * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of CUBIC TCP in * Sangtae Ha, Injong Rhee and Lisong Xu, * "CUBIC: A New TCP-Friendly High-Speed TCP Variant" * in ACM SIGOPS Operating System Review, July 2008. * Available from: * http://netsrv.csc.ncsu.edu/export/cubic_a_new_tcp_2008.pdf * * CUBIC integrates a new slow start algorithm, called HyStart. * The details of HyStart are presented in * Sangtae Ha and Injong Rhee, * "Taming the Elephants: New TCP Slow Start", NCSU TechReport 2008. * Available from: * http://netsrv.csc.ncsu.edu/export/hystart_techreport_2008.pdf * * All testing results are available from: * http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing * * Unless CUBIC is enabled and congestion window is large * this behaves the same as the original Reno. */ #include <linux/mm.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/module.h> #include <linux/math64.h> #include <net/tcp.h> #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta */ #define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ /* Two methods of hybrid slow start */ #define HYSTART_ACK_TRAIN 0x1 #define HYSTART_DELAY 0x2 /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 #define HYSTART_DELAY_MIN (4000U) /* 4 ms */ #define HYSTART_DELAY_MAX (16000U) /* 16 ms */ #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) static int fast_convergence __read_mostly = 1; static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh __read_mostly; static int bic_scale __read_mostly = 41; static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; static int hystart_ack_delta_us __read_mostly = 2000; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; static u64 cube_factor __read_mostly; /* Note parameters that are used for precomputing scale factors are read-only */ module_param(fast_convergence, int, 0644); MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); module_param(beta, int, 0644); MODULE_PARM_DESC(beta, "beta for multiplicative increase"); module_param(initial_ssthresh, int, 0644); MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold"); module_param(bic_scale, int, 0444); MODULE_PARM_DESC(bic_scale, "scale (scaled by 1024) value for bic function (bic_scale/1024)"); module_param(tcp_friendliness, int, 0644); MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness"); module_param(hystart, int, 0644); MODULE_PARM_DESC(hystart, "turn on/off hybrid slow start algorithm"); module_param(hystart_detect, int, 0644); MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); module_param(hystart_ack_delta_us, int, 0644); MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)"); /* BIC TCP Parameters */ struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ u32 delay_min; /* min delay (usec) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ u16 unused; u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ u32 round_start; /* beginning of each round */ u32 end_seq; /* end_seq of the round */ u32 last_ack; /* last time when the ACK spacing is close */ u32 curr_rtt; /* the minimum rtt of current round */ }; static inline void bictcp_reset(struct bictcp *ca) { memset(ca, 0, offsetof(struct bictcp, unused)); ca->found = 0; } static inline u32 bictcp_clock_us(const struct sock *sk) { return tcp_sk(sk)->tcp_mstamp; } static inline void bictcp_hystart_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; ca->curr_rtt = ~0U; ca->sample_cnt = 0; } __bpf_kfunc static void cubictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); if (hystart) bictcp_hystart_reset(sk); if (!hystart && initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } __bpf_kfunc static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. * Shift epoch_start to keep cwnd growth to cubic curve. */ if (ca->epoch_start && delta > 0) { ca->epoch_start += delta; if (after(ca->epoch_start, now)) ca->epoch_start = now; } return; } } /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% */ static u32 cubic_root(u64 a) { u32 x, b, shift; /* * cbrt(x) MSB values for x MSB values in [0..63]. * Precomputed then refined by hand - Willy Tarreau * * For x in [0..63], * v = cbrt(x << 18) - 1 * cbrt(x) = (v[x] + 10) >> 6 */ static const u8 v[] = { /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, }; b = fls64(a); if (b < 7) { /* a in [0..63] */ return ((u32)v[(u32)a] + 35) >> 6; } b = ((b * 84) >> 8) - 1; shift = (a >> (b * 3)); x = ((u32)(((u32)v[shift] + 10) << b)) >> 6; /* * Newton-Raphson iteration * 2 * x = ( 2 * x + a / x ) / 3 * k+1 k k */ x = (2 * x + (u32)div64_u64(a, (u64)x * (u64)(x - 1))); x = ((x * 341) >> 10); return x; } /* * Compute congestion window to use. */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) { u32 delta, bic_target, max_cnt; u64 offs, t; ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; /* The CUBIC function can update ca->cnt at most once per jiffy. * On all cwnd reduction events, ca->epoch_start is set to 0, * which will force a recalculation of ca->cnt. */ if (ca->epoch_start && tcp_jiffies32 == ca->last_time) goto tcp_friendliness; ca->last_cwnd = cwnd; ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) { ca->epoch_start = tcp_jiffies32; /* record beginning */ ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ if (ca->last_max_cwnd <= cwnd) { ca->bic_K = 0; ca->bic_origin_point = cwnd; } else { /* Compute new K based on * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) */ ca->bic_K = cubic_root(cube_factor * (ca->last_max_cwnd - cwnd)); ca->bic_origin_point = ca->last_max_cwnd; } } /* cubic function - calc*/ /* calculate c * time^3 / rtt, * while considering overflow in calculation of time^3 * (so time^3 is done by using 64 bit) * and without the support of division of 64bit numbers * (so all divisions are done by using 32 bit) * also NOTE the unit of those veriables * time = (t - K) / 2^bictcp_HZ * c = bic_scale >> 10 * rtt = (srtt >> 3) / HZ * !!! The following code does not have overflow problems, * if the cwnd < 1 million packets !!! */ t = (s32)(tcp_jiffies32 - ca->epoch_start); t += usecs_to_jiffies(ca->delay_min); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; else offs = t - ca->bic_K; /* c/rtt * (t-K)^3 */ delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); if (t < ca->bic_K) /* below origin*/ bic_target = ca->bic_origin_point - delta; else /* above origin*/ bic_target = ca->bic_origin_point + delta; /* cubic function - calc bictcp_cnt*/ if (bic_target > cwnd) { ca->cnt = cwnd / (bic_target - cwnd); } else { ca->cnt = 100 * cwnd; /* very small increment*/ } /* * The initial growth of cubic function may be too conservative * when the available bandwidth is still unknown. */ if (ca->last_max_cwnd == 0 && ca->cnt > 20) ca->cnt = 20; /* increase cwnd 5% per RTT */ tcp_friendliness: /* TCP Friendly */ if (tcp_friendliness) { u32 scale = beta_scale; delta = (cwnd * scale) >> 3; while (ca->ack_cnt > delta) { /* update tcp cwnd */ ca->ack_cnt -= delta; ca->tcp_cwnd++; } if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ delta = ca->tcp_cwnd - cwnd; max_cnt = cwnd / delta; if (ca->cnt > max_cnt) ca->cnt = max_cnt; } } /* The maximum rate of cwnd increase CUBIC allows is 1 packet per * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. */ ca->cnt = max(ca->cnt, 2U); } __bpf_kfunc static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } bictcp_update(ca, tcp_snd_cwnd(tp), acked); tcp_cong_avoid_ai(tp, ca->cnt, acked); } __bpf_kfunc static u32 cubictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->epoch_start = 0; /* end of epoch */ /* Wmax and fast convergence */ if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence) ca->last_max_cwnd = (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta)) / (2 * BICTCP_BETA_SCALE); else ca->last_max_cwnd = tcp_snd_cwnd(tp); return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } __bpf_kfunc static void cubictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); bictcp_hystart_reset(sk); } } /* Account for TSO/GRO delays. * Otherwise short RTT flows could get too small ssthresh, since during * slow start we begin with small TSO packets and ca->delay_min would * not account for long aggregation delay when TSO packets get bigger. * Ideally even with a very small RTT we would like to have at least one * TSO packet being sent and received by GRO, and another one in qdisc layer. * We apply another 100% factor because @rate is doubled at this point. * We cap the cushion to 1ms. */ static u32 hystart_ack_delay(const struct sock *sk) { unsigned long rate; rate = READ_ONCE(sk->sk_pacing_rate); if (!rate) return 0; return min_t(u64, USEC_PER_MSEC, div64_ul((u64)sk->sk_gso_max_size * 4 * USEC_PER_SEC, rate)); } static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 threshold; if (after(tp->snd_una, ca->end_seq)) bictcp_hystart_reset(sk); /* hystart triggers when cwnd is larger than some threshold */ if (tcp_snd_cwnd(tp) < hystart_low_window) return; if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); /* first detection parameter - ack-train detection */ if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; threshold = ca->delay_min + hystart_ack_delay(sk); /* Hystart ack train triggers if we get ack past * ca->delay_min/2. * Pacing might have delayed packets up to RTT/2 * during slow start. */ if (sk->sk_pacing_status == SK_PACING_NONE) threshold >>= 1; if ((s32)(now - ca->round_start) > threshold) { ca->found = 1; pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n", now - ca->round_start, threshold, ca->delay_min, hystart_ack_delay(sk), tcp_snd_cwnd(tp)); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINCWND, tcp_snd_cwnd(tp)); tp->snd_ssthresh = tcp_snd_cwnd(tp); } } } if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ if (ca->curr_rtt > delay) ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYDETECT); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYCWND, tcp_snd_cwnd(tp)); tp->snd_ssthresh = tcp_snd_cwnd(tp); } } } } __bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 delay; /* Some calls are for duplicates without timetamps */ if (sample->rtt_us < 0) return; /* Discard delay samples right after fast recovery */ if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; delay = sample->rtt_us; if (delay == 0) delay = 1; /* first time call or link delay decreases */ if (ca->delay_min == 0 || ca->delay_min > delay) ca->delay_min = delay; if (!ca->found && tcp_in_slow_start(tp) && hystart) hystart_update(sk, delay); } static struct tcp_congestion_ops cubictcp __read_mostly = { .init = cubictcp_init, .ssthresh = cubictcp_recalc_ssthresh, .cong_avoid = cubictcp_cong_avoid, .set_state = cubictcp_state, .undo_cwnd = tcp_reno_undo_cwnd, .cwnd_event = cubictcp_cwnd_event, .pkts_acked = cubictcp_acked, .owner = THIS_MODULE, .name = "cubic", }; BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) BTF_ID_FLAGS(func, cubictcp_init) BTF_ID_FLAGS(func, cubictcp_recalc_ssthresh) BTF_ID_FLAGS(func, cubictcp_cong_avoid) BTF_ID_FLAGS(func, cubictcp_state) BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { .owner = THIS_MODULE, .set = &tcp_cubic_check_kfunc_ids, }; static int __init cubictcp_register(void) { int ret; BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); /* Precompute a bunch of the scaling factors that are used per-packet * based on SRTT of 100ms */ beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 / (BICTCP_BETA_SCALE - beta); cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ /* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 * so K = cubic_root( (wmax-cwnd)*rtt/c ) * the unit of K is bictcp_HZ=2^10, not HZ * * c = bic_scale >> 10 * rtt = 100ms * * the following code has been designed and tested for * cwnd < 1 million packets * RTT < 100 seconds * HZ < 1,000,00 (corresponding to 10 nano-second) */ /* 1/c * 2^2*bictcp_HZ * srtt */ cube_factor = 1ull << (10+3*BICTCP_HZ); /* 2^40 */ /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_cubic_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&cubictcp); } static void __exit cubictcp_unregister(void) { tcp_unregister_congestion_control(&cubictcp); } module_init(cubictcp_register); module_exit(cubictcp_unregister); MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CUBIC TCP"); MODULE_VERSION("2.3"); |
| 2429 1895 2254 418 2245 2038 2037 1354 2040 2041 1415 2236 795 895 1975 6 1972 1733 1732 1 642 1625 1 1548 1627 1613 68 1615 1519 1865 68 1993 1398 790 1961 1336 771 2670 1647 1063 2033 1330 704 1748 1196 551 1452 1038 416 567 308 259 955 637 318 604 388 217 79 50 29 125 52 73 114 893 481 936 915 914 915 911 2 915 915 914 704 217 578 42 552 554 541 157 478 9 89 416 26 6 20 20 113 1 210 99 114 114 1880 13 1881 286 7 285 41 2 40 178 13 165 1 127 41 127 41 144 144 21 379 16 18 365 366 16 89 62 27 111 1413 1411 70 234 324 322 70 52 111 90 32 83 90 20 71 90 90 90 90 90 90 2184 2187 1275 1274 1275 1229 1229 684 626 64 1227 1229 23 19 2 2 24 1521 1821 1822 1821 1822 95 1 7 1 94 194 3 887 1718 124 9 1782 1767 1751 1749 75 6 7 77 52 143 59 1 9 394 39 1690 278 30 2 19 1 1 237 65 57 4 86 1 33 99 89 120 85 74 1 74 28 19 1 38 3 43 104 41 9 1 970 598 893 95 887 598 8 1651 8 8 830 714 164 96 73 162 4 656 224 5 1689 33 1453 261 264 263 170 91 1372 1 226 23 12 1583 4 1586 199 1395 130 1468 1507 16 70 80 3 1717 1714 5 1712 2 1 4 1705 102 1 103 103 1711 1696 1696 1693 1695 1696 1697 1695 1697 1695 1696 1695 1696 15 2 1 2 18 1 19 1 16 16 19 19 20 20 16 16 16 20 20 2 14 6 19 1 20 20 19 1 17 3 17 3 20 6 7 20 20 20 20 19 20 20 15 5 19 1 20 20 1479 76 130 12 29 1255 1238 1293 1271 23 1292 1357 122 667 666 666 688 21 666 667 666 667 661 90 368 204 1064 1079 735 344 1557 1572 1 1574 1574 1566 9 1570 4 1 1571 1561 11 1526 43 2 1567 1563 2 1563 4 5 1560 1044 97 1 422 784 780 1560 1217 392 907 472 201 1559 1475 85 1475 1433 225 1640 4 240 3 6 1523 2 12 185 195 6 195 619 621 31 25 6 6 620 621 1239 1430 16 190 1238 1239 1166 621 1240 1168 620 1093 75 75 75 75 75 75 75 75 75 75 1166 1168 1168 1167 1169 1116 4 46 1467 510 960 1229 796 331 1597 65 1477 184 1414 248 1419 244 1612 47 1445 104 113 1410 252 174 1487 158 1504 1661 1592 2 459 1 1131 1 3 3 60 1523 1558 1559 1556 70 1 1 673 900 1 18 1 1 12 6 1661 2 1661 2 1615 1 47 20 368 1273 1640 1571 59 8 1609 1 29 1 1589 48 9 1593 36 12 4 1611 1612 1584 1 1582 2 1580 1578 1578 1575 2 1575 842 737 1 1576 1575 1571 1575 1 1575 58 58 56 330 1 118 212 18 312 1313 1490 2 3 1 2 1484 1673 2 1 2 1 1 952 716 1 715 5 1595 1 2 1148 70 127 46 201 1604 1606 499 1 1107 2 2 4 1592 1436 34 1638 1673 1673 2 1665 1662 1661 1657 8 17 1639 36 9 3 10 7 17 1449 111 865 7 688 869 8 1331 58 215 1 9 1482 55 315 1114 1484 1100 385 1168 13 3 1392 75 154 1280 35 44 1389 20 1412 729 688 3 887 525 1341 1343 847 500 141 141 323 324 1342 1673 1662 9 1673 1342 540 1229 331 1674 97 31 1 65 6 41 5 4 9 9 49 9 2 47 47 9 9 1761 1762 115 1687 1762 1762 1762 1338 479 738 912 443 851 1761 1761 1762 1761 1762 1757 3 353 19 339 140 60 226 338 1 11 11 11 11 85 12 97 1 96 91 5 1 96 1 97 4 1 92 21 2 1 33 34 5 34 34 1 33 1 9 23 80 4 32 51 52 1 6 24 60 5 36 31 65 58 7 32 1 33 33 103 6 97 33 13 1 12 13 13 13 1 13 385 385 6 385 556 556 14 389 199 386 385 1 5 5 11 2 1 3 5 8 632 24 613 671 653 639 632 629 111 182 46 139 167 55 1 1 775 4 775 10 150 766 525 115 513 511 178 3 7 5 6 4 1 429 339 90 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/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/fs.h> #include <linux/time.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/parser.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/random.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/crc16.h> #include <linux/dax.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include <linux/unicode.h> #include <linux/part_stat.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/fsnotify.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "mballoc.h" #include "fsmap.h" #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> static struct ext4_lazy_init *ext4_li_info; static DEFINE_MUTEX(ext4_li_mtx); static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static void ext4_update_super(struct super_block *sb); static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum); static int ext4_validate_options(struct fs_context *fc); static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb); static void ext4_apply_options(struct fs_context *fc, struct super_block *sb); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param); static int ext4_get_tree(struct fs_context *fc); static int ext4_reconfigure(struct fs_context *fc); static void ext4_fc_free(struct fs_context *fc); static int ext4_init_fs_context(struct fs_context *fc); static void ext4_kill_sb(struct super_block *sb); static const struct fs_parameter_spec ext4_param_specs[]; /* * Lock ordering * * page fault path: * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start * -> page lock -> i_data_sem (rw) * * buffered write path: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> page lock -> * i_data_sem (rw) * * truncate: * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) -> * page lock * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start -> * i_data_sem (rw) * * direct IO: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw) * * writepages: * transaction start -> page lock(s) -> i_data_sem (rw) */ static const struct fs_context_operations ext4_context_ops = { .parse_param = ext4_parse_param, .get_tree = ext4_get_tree, .reconfigure = ext4_reconfigure, .free = ext4_fc_free, }; #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, .name = "ext2", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext2"); MODULE_ALIAS("ext2"); #define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type) #else #define IS_EXT2_SB(sb) (0) #endif static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext3"); MODULE_ALIAS("ext3"); #define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type) static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io, bool simu_fail) { if (simu_fail) { clear_buffer_uptodate(bh); unlock_buffer(bh); return; } /* * buffer's verified bit is no longer valid after reading from * disk again due to write out error, clear it to make sure we * recheck the buffer contents. */ clear_buffer_verified(bh); bh->b_end_io = end_io ? end_io : end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return; } __ext4_read_bh(bh, op_flags, end_io, simu_fail); } int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } __ext4_read_bh(bh, op_flags, end_io, simu_fail); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { lock_buffer(bh); if (!wait) { ext4_read_bh_nowait(bh, op_flags, NULL, false); return 0; } return ext4_read_bh(bh, op_flags, NULL, false); } /* * This works like __bread_gfp() except it uses ERR_PTR for error * returns. Currently with sb_bread it's impossible to distinguish * between ENOMEM and EIO situations (since both result in a NULL * return. */ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, sector_t block, blk_opf_t op_flags, gfp_t gfp) { struct buffer_head *bh; int ret; bh = sb_getblk_gfp(sb, block, gfp); if (bh == NULL) return ERR_PTR(-ENOMEM); if (ext4_buffer_uptodate(bh)) return bh; ret = ext4_read_bh_lock(bh, REQ_META | op_flags, true); if (ret) { put_bh(bh); return ERR_PTR(ret); } return bh; } struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) | __GFP_MOVABLE; return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS); return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN); if (likely(bh)) { if (trylock_buffer(bh)) ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false); brelse(bh); } } static int ext4_verify_csum_type(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } __le32 ext4_superblock_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct ext4_super_block, s_checksum); __u32 csum; csum = ext4_chksum(sbi, ~0, (char *)es, offset); return cpu_to_le32(csum); } static int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(sb, es); } void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (!ext4_has_feature_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(sb, es); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16); } void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count)); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16)); } void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16); } void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_itable_unused_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now) { now = clamp_val(now, 0, (1ull << 40) - 1); *lo = cpu_to_le32(lower_32_bits(now)); *hi = upper_32_bits(now); } static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) { return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo); } #define ext4_update_tstamp(es, tstamp) \ __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \ ktime_get_real_seconds()) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) /* * The ext4_maybe_update_superblock() function checks and updates the * superblock if needed. * * This function is designed to update the on-disk superblock only under * certain conditions to prevent excessive disk writes and unnecessary * waking of the disk from sleep. The superblock will be updated if: * 1. More than sbi->s_sb_update_sec (def: 1 hour) has passed since the last * superblock update * 2. More than sbi->s_sb_update_kb (def: 16MB) kbs have been written since the * last superblock update. * * @sb: The superblock */ static void ext4_maybe_update_superblock(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; journal_t *journal = sbi->s_journal; time64_t now; __u64 last_update; __u64 lifetime_write_kbytes; __u64 diff_size; if (ext4_emergency_state(sb) || sb_rdonly(sb) || !(sb->s_flags & SB_ACTIVE) || !journal || journal->j_flags & JBD2_UNMOUNT) return; now = ktime_get_real_seconds(); last_update = ext4_get_tstamp(es, s_wtime); if (likely(now - last_update < sbi->s_sb_update_sec)) return; lifetime_write_kbytes = sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); /* Get the number of kilobytes not written to disk to account * for statistics and compare with a multiple of 16 MB. This * is used to determine when the next superblock commit should * occur (i.e. not more often than once per 16MB if there was * less written in an hour). */ diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); if (diff_size > sbi->s_sb_update_kb) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; BUG_ON(txn->t_state == T_FINISHED); ext4_process_freed_data(sb, txn->t_tid); ext4_maybe_update_superblock(sb); } /* * This writepage callback for write_cache_pages() * takes care of a few cases after page cleaning. * * write_cache_pages() already checks for dirty pages * and calls clear_page_dirty_for_io(), which we want, * to write protect the pages. * * However, we may have to redirty a page (see below.) */ static int ext4_journalled_writepage_callback(struct folio *folio, struct writeback_control *wbc, void *data) { transaction_t *transaction = (transaction_t *) data; struct buffer_head *bh, *head; struct journal_head *jh; bh = head = folio_buffers(folio); do { /* * We have to redirty a page in these cases: * 1) If buffer is dirty, it means the page was dirty because it * contains a buffer that needs checkpointing. So the dirty bit * needs to be preserved so that checkpointing writes the buffer * properly. * 2) If buffer is not part of the committing transaction * (we may have just accidentally come across this buffer because * inode range tracking is not exact) or if the currently running * transaction already contains this buffer as well, dirty bit * needs to be preserved so that the buffer gets writeprotected * properly on running transaction's commit. */ jh = bh2jh(bh); if (buffer_dirty(bh) || (jh && (jh->b_transaction != transaction || jh->b_next_transaction))) { folio_redirty_for_writepage(wbc, folio); goto out; } } while ((bh = bh->b_this_page) != head); out: return AOP_WRITEPAGE_ACTIVATE; } static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode) { struct address_space *mapping = jinode->i_vfs_inode->i_mapping; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = jinode->i_dirty_start, .range_end = jinode->i_dirty_end, }; return write_cache_pages(mapping, &wbc, ext4_journalled_writepage_callback, jinode->i_transaction); } static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) { int ret; if (ext4_should_journal_data(jinode->i_vfs_inode)) ret = ext4_journalled_submit_inode_data_buffers(jinode); else ret = ext4_normal_submit_inode_data_buffers(jinode); return ret; } static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode) { int ret = 0; if (!ext4_should_journal_data(jinode->i_vfs_inode)) ret = jbd2_journal_finish_inode_data_buffers(jinode); return ret; } static bool system_going_down(void) { return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART; } struct ext4_err_translation { int code; int errno; }; #define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } static struct ext4_err_translation err_translation[] = { EXT4_ERR_TRANSLATE(EIO), EXT4_ERR_TRANSLATE(ENOMEM), EXT4_ERR_TRANSLATE(EFSBADCRC), EXT4_ERR_TRANSLATE(EFSCORRUPTED), EXT4_ERR_TRANSLATE(ENOSPC), EXT4_ERR_TRANSLATE(ENOKEY), EXT4_ERR_TRANSLATE(EROFS), EXT4_ERR_TRANSLATE(EFBIG), EXT4_ERR_TRANSLATE(EEXIST), EXT4_ERR_TRANSLATE(ERANGE), EXT4_ERR_TRANSLATE(EOVERFLOW), EXT4_ERR_TRANSLATE(EBUSY), EXT4_ERR_TRANSLATE(ENOTDIR), EXT4_ERR_TRANSLATE(ENOTEMPTY), EXT4_ERR_TRANSLATE(ESHUTDOWN), EXT4_ERR_TRANSLATE(EFAULT), }; static int ext4_errno_to_code(int errno) { int i; for (i = 0; i < ARRAY_SIZE(err_translation); i++) if (err_translation[i].errno == errno) return err_translation[i].code; return EXT4_ERR_UNKNOWN; } static void save_error_info(struct super_block *sb, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; spin_lock(&sbi->s_error_lock); sbi->s_add_error_count++; sbi->s_last_error_code = error; sbi->s_last_error_line = line; sbi->s_last_error_ino = ino; sbi->s_last_error_block = block; sbi->s_last_error_func = func; sbi->s_last_error_time = ktime_get_real_seconds(); if (!sbi->s_first_error_time) { sbi->s_first_error_code = error; sbi->s_first_error_line = line; sbi->s_first_error_ino = ino; sbi->s_first_error_block = block; sbi->s_first_error_func = func; sbi->s_first_error_time = sbi->s_last_error_time; } spin_unlock(&sbi->s_error_lock); } /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * * On ext2, we can store the error state of the filesystem in the * superblock. That is not possible on ext4, because we may have other * write ordering constraints on the superblock which prevent us from * writing it out straight away; and given that the journal is about to * be aborted, we can't rely on the current, or future, transactions to * write out the superblock safely. * * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. * * If force_ro is set, we unconditionally force the filesystem into an * ABORT|READONLY state, unless the error response on the fs has been set to * panic in which case we take the easy way out and panic immediately. This is * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); if (!continue_fs && !ext4_emergency_ro(sb) && journal) jbd2_journal_abort(journal, -EIO); if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, error, ino, block, func, line); /* * In case the fs should keep running, we need to writeout * superblock through the journal. Due to lock ordering * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. We just need to be * careful when the journal is already shutting down. If we get * here in that case, just update the sb directly as the last * transaction won't commit anyway. */ if (continue_fs && journal && !ext4_test_mount_flag(sb, EXT4_MF_JOURNAL_DESTROY)) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); } /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already * disabled. */ if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } if (ext4_emergency_ro(sb) || continue_fs) return; ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * We don't set SB_RDONLY because that requires sb->s_umount * semaphore and setting it without proper remount procedure is * confusing code such as freeze_super() leading to deadlocks * and other problems. */ set_bit(EXT4_FLAGS_EMERGENCY_RO, &EXT4_SB(sb)->s_ext4_flags); } static void update_super_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_sb_upd_work); journal_t *journal = sbi->s_journal; handle_t *handle; /* * If the journal is still running, we have to write out superblock * through the journal to avoid collisions of other journalled sb * updates. * * We use directly jbd2 functions here to avoid recursing back into * ext4 error handling code during handling of previous errors. */ if (!ext4_emergency_state(sbi->s_sb) && !sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; bool call_notify_err = false; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; if (jbd2_journal_get_write_access(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } if (sbi->s_add_error_count > 0) call_notify_err = true; ext4_update_super(sbi->s_sb); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } if (jbd2_journal_dirty_metadata(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } jbd2_journal_stop(handle); if (call_notify_err) ext4_notify_error_sysfs(sbi); return; } write_directly: /* * Write through journal failed. Write sb directly to get error info * out and hope for the best. */ ext4_commit_super(sbi->s_sb); ext4_notify_error_sysfs(sbi); } #define ext4_error_ratelimit(sb) \ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \ "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, unsigned int line, bool force_ro, int error, __u64 block, const char *fmt, ...) { struct va_format vaf; va_list args; if (unlikely(ext4_emergency_state(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n", sb->s_id, function, line, current->comm, &vaf); va_end(args); } fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED); ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, unsigned int line, ext4_fsblk_t block, int error, const char *fmt, ...) { va_list args; struct va_format vaf; if (unlikely(ext4_emergency_state(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: block %llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED); ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, function, line); } void __ext4_error_file(struct file *file, const char *function, unsigned int line, ext4_fsblk_t block, const char *fmt, ...) { va_list args; struct va_format vaf; struct inode *inode = file_inode(file); char pathname[80], *path; if (unlikely(ext4_emergency_state(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { path = file_path(file, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "block %llu: comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, path, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: " "comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, path, &vaf); va_end(args); } fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED); ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]) { char *errstr = NULL; switch (errno) { case -EFSCORRUPTED: errstr = "Corrupt filesystem"; break; case -EFSBADCRC: errstr = "Filesystem failed CRC"; break; case -EIO: errstr = "IO failure"; break; case -ENOMEM: errstr = "Out of memory"; break; case -EROFS: if (!sb || (EXT4_SB(sb)->s_journal && EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; break; default: /* If the caller passed in an extra buffer for unknown * errors, textualise them now. Else we just return * NULL. */ if (nbuf) { /* Check for truncated error codes... */ if (snprintf(nbuf, 16, "error %d", -errno) >= 0) errstr = nbuf; } break; } return errstr; } /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ void __ext4_std_error(struct super_block *sb, const char *function, unsigned int line, int errno) { char nbuf[16]; const char *errstr; if (unlikely(ext4_emergency_state(sb))) return; /* Special case: if the error is EROFS, and we're not already * inside a transaction, then there's really no point in logging * an error. */ if (errno == -EROFS && journal_current_handle() == NULL && sb_rdonly(sb)) return; if (ext4_error_ratelimit(sb)) { errstr = ext4_decode_error(sb, errno, nbuf); printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); } fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED); ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; if (sb) { atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (sb) printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); else printk("%sEXT4-fs: %pV\n", prefix, &vaf); va_end(args); } static int ext4_warning_ratelimit(struct super_block *sb) { atomic_inc(&EXT4_SB(sb)->s_warning_count); return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), "EXT4-fs warning"); } void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n", sb->s_id, function, line, &vaf); va_end(args); } void __ext4_warning_inode(const struct inode *inode, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(inode->i_sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: " "inode #%lu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } void __ext4_grp_locked_error(const char *function, unsigned int line, struct super_block *sb, ext4_group_t grp, unsigned long ino, ext4_fsblk_t block, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { struct va_format vaf; va_list args; if (unlikely(ext4_emergency_state(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ", sb->s_id, function, line, grp); if (ino) printk(KERN_CONT "inode %lu: ", ino); if (block) printk(KERN_CONT "block %llu:", (unsigned long long) block); printk(KERN_CONT "%pV\n", &vaf); va_end(args); } if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, EFSCORRUPTED, ino, block, function, line); schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } return; } ext4_unlock_group(sb, grp); ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the * filesystem will have already been marked read/only and the * journal has been aborted. We return 1 as a hint to callers * who might what to use the return value from * ext4_grp_locked_error() to distinguish between the * ERRORS_CONT and ERRORS_RO case, and perhaps return more * aggressively from the ext4 function in question, with a * more appropriate error code. */ ext4_lock_group(sb, grp); return; } void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t group, unsigned int flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; if (!grp || !gdp) return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret) percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free); } if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret && gdp) { int count; count = ext4_free_inodes_count(sb, gdp); percpu_counter_sub(&sbi->s_freeinodes_counter, count); } } } void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) return; ext4_warning(sb, "updating to rev %d because of new feature flag, " "running e2fsck is recommended", EXT4_DYNAMIC_REV); es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO); es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE); es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV); /* leave es->s_feature_*compat flags alone */ /* es->s_uuid will be set by e2fsck if empty */ /* * The rest of the superblock fields should be zero, and if not it * means they are likely already in use, so leave them alone. We * can leave it up to e2fsck to clean up any inconsistencies there. */ } static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; } static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; ext4_msg(sb, KERN_ERR, "sb orphan head is %d", le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); printk(KERN_ERR " " "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); } } #ifdef CONFIG_QUOTA static int ext4_quota_off(struct super_block *sb, int type); static inline void ext4_quotas_off(struct super_block *sb, int type) { BUG_ON(type > EXT4_MAXQUOTAS); /* Use our quota_off function to clear inode flags etc. */ for (type--; type >= 0; type--) ext4_quota_off(sb, type); } /* * This is a helper function which is used in the mount/remount * codepaths (which holds s_umount) to fetch the quota file name. */ static inline char *get_qf_name(struct super_block *sb, struct ext4_sb_info *sbi, int type) { return rcu_dereference_protected(sbi->s_qf_names[type], lockdep_is_held(&sb->s_umount)); } #else static inline void ext4_quotas_off(struct super_block *sb, int type) { } #endif static int ext4_percpu_param_init(struct ext4_sb_info *sbi) { ext4_fsblk_t block; int err; block = ext4_count_free_clusters(sbi->s_sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sbi->s_sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } if (!err) err = percpu_counter_init(&sbi->s_dirs_counter, ext4_count_dirs(sbi->s_sb), GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0, GFP_KERNEL); if (!err) err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) ext4_msg(sbi->s_sb, KERN_ERR, "insufficient memory"); return err; } static void ext4_percpu_param_destroy(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); } static void ext4_group_desc_free(struct ext4_sb_info *sbi) { struct buffer_head **group_desc; int i; rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) brelse(group_desc[i]); kvfree(group_desc); rcu_read_unlock(); } static void ext4_flex_groups_free(struct ext4_sb_info *sbi) { struct flex_groups **flex_groups; int i; rcu_read_lock(); flex_groups = rcu_dereference(sbi->s_flex_groups); if (flex_groups) { for (i = 0; i < sbi->s_flex_groups_allocated; i++) kvfree(flex_groups[i]); kvfree(flex_groups); } rcu_read_unlock(); } static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int aborted = 0; int err; /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL * Unregister sysfs before flush sbi->s_sb_upd_work. * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If * read metadata verify failed then will queue error work. * update_super_work will call start_this_handle may trigger * BUG_ON. */ ext4_unregister_sysfs(sb); if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount")) ext4_msg(sb, KERN_INFO, "unmounting filesystem %pU.", &sb->s_uuid); ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = ext4_journal_destroy(sbi, sbi->s_journal); if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } } else flush_work(&sbi->s_sb_upd_work); ext4_es_unregister_shrinker(sbi); timer_shutdown_sync(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); if (!ext4_emergency_state(sb) && !sb_rdonly(sb)) { if (!aborted) { ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } ext4_commit_super(sb); } ext4_group_desc_free(sbi); ext4_flex_groups_free(sbi); WARN_ON_ONCE(!(sbi->s_mount_state & EXT4_ERROR_FS) && percpu_counter_sum(&sbi->s_dirtyclusters_counter)); ext4_percpu_param_destroy(sbi); #ifdef CONFIG_QUOTA for (int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list * isn't empty. The on-disk one can be non-empty if we've * detected an error and taken the fs readonly, but the * in-memory list had better be clean by this point. */ if (!list_empty(&sbi->s_orphan)) dump_orphan_list(sb, sbi); ASSERT(list_empty(&sbi->s_orphan)); sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->s_journal_bdev_file) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ sync_blockdev(file_bdev(sbi->s_journal_bdev_file)); invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; ext4_stop_mmpd(sbi); brelse(sbi->s_sbh); sb->s_fs_info = NULL; /* * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); } static struct kmem_cache *ext4_inode_cachep; /* * Called inside transaction, so use GFP_NOFS */ static struct inode *ext4_alloc_inode(struct super_block *sb) { struct ext4_inode_info *ei; ei = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; inode_set_iversion(&ei->vfs_inode, 1); ei->i_flags = 0; spin_lock_init(&ei->i_raw_lock); ei->i_prealloc_node = RB_ROOT; atomic_set(&ei->i_prealloc_active, 0); rwlock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); INIT_LIST_HEAD(&ei->i_es_list); ei->i_es_all_nr = 0; ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; ei->i_reserved_data_blocks = 0; spin_lock_init(&(ei->i_block_reservation_lock)); ext4_init_pending_tree(&ei->i_pending_tree); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); ext4_fc_init_inode(&ei->vfs_inode); mutex_init(&ei->i_fc_lock); return &ei->vfs_inode; } static int ext4_drop_inode(struct inode *inode) { int drop = generic_drop_inode(inode); if (!drop) drop = fscrypt_drop_inode(inode); trace_ext4_drop_inode(inode, drop); return drop; } static void ext4_free_in_core_inode(struct inode *inode) { fscrypt_free_inode(inode); if (!list_empty(&(EXT4_I(inode)->i_fc_list))) { pr_warn("%s: inode %ld still in fc list", __func__, inode->i_ino); } kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } static void ext4_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); dump_stack(); } if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) && WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks)) ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", inode->i_ino, EXT4_I(inode), EXT4_I(inode)->i_reserved_data_blocks); } static void ext4_shutdown(struct super_block *sb) { ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH); } static void init_once(void *foo) { struct ext4_inode_info *ei = foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); ext4_fc_init_inode(&ei->vfs_inode); } static int __init init_inodecache(void) { ext4_inode_cachep = kmem_cache_create_usercopy("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, offsetof(struct ext4_inode_info, i_data), sizeof_field(struct ext4_inode_info, i_data), init_once); if (ext4_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } void ext4_clear_inode(struct inode *inode) { ext4_fc_del(inode); invalidate_inode_buffers(inode); clear_inode(inode); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); jbd2_free_inode(EXT4_I(inode)->jinode); EXT4_I(inode)->jinode = NULL; } fscrypt_put_encryption_info(inode); fsverity_cleanup_inode(inode); } static struct inode *ext4_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct inode *inode; /* * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ inode = ext4_iget(sb, ino, EXT4_IGET_HANDLE); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { iput(inode); return ERR_PTR(-ESTALE); } return inode; } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static int ext4_nfs_commit_metadata(struct inode *inode) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL }; trace_ext4_nfs_commit_metadata(inode); return ext4_write_inode(inode, &wbc); } #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) static int ext4_write_dquot(struct dquot *dquot); static int ext4_acquire_dquot(struct dquot *dquot); static int ext4_release_dquot(struct dquot *dquot); static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, .write_dquot = ext4_write_dquot, .acquire_dquot = ext4_acquire_dquot, .release_dquot = ext4_release_dquot, .mark_dirty = ext4_mark_dquot_dirty, .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = ext4_get_projid, .get_inode_usage = ext4_get_inode_usage, .get_next_id = dquot_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = ext4_quota_off, .quota_sync = dquot_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk, .get_nextdqblk = dquot_get_next_dqblk, }; #endif static const struct super_operations ext4_sops = { .alloc_inode = ext4_alloc_inode, .free_inode = ext4_free_in_core_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .show_options = ext4_show_options, .shutdown = ext4_shutdown, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, .get_dquots = ext4_get_dquots, #endif }; static const struct export_operations ext4_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, .commit_metadata = ext4_nfs_commit_metadata, }; enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid, Opt_sb, Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_acl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force #endif }; static const struct constant_table ext4_param_errors[] = { {"continue", EXT4_MOUNT_ERRORS_CONT}, {"panic", EXT4_MOUNT_ERRORS_PANIC}, {"remount-ro", EXT4_MOUNT_ERRORS_RO}, {} }; static const struct constant_table ext4_param_data[] = { {"journal", EXT4_MOUNT_JOURNAL_DATA}, {"ordered", EXT4_MOUNT_ORDERED_DATA}, {"writeback", EXT4_MOUNT_WRITEBACK_DATA}, {} }; static const struct constant_table ext4_param_data_err[] = { {"abort", Opt_data_err_abort}, {"ignore", Opt_data_err_ignore}, {} }; static const struct constant_table ext4_param_jqfmt[] = { {"vfsold", QFMT_VFS_OLD}, {"vfsv0", QFMT_VFS_V0}, {"vfsv1", QFMT_VFS_V1}, {} }; static const struct constant_table ext4_param_dax[] = { {"always", Opt_dax_always}, {"inode", Opt_dax_inode}, {"never", Opt_dax_never}, {} }; /* * Mount option specification * We don't use fsparam_flag_no because of the way we set the * options and the way we show them in _ext4_show_options(). To * keep the changes to a minimum, let's keep the negative options * separate for now. */ static const struct fs_parameter_spec ext4_param_specs[] = { fsparam_flag ("bsddf", Opt_bsd_df), fsparam_flag ("minixdf", Opt_minix_df), fsparam_flag ("grpid", Opt_grpid), fsparam_flag ("bsdgroups", Opt_grpid), fsparam_flag ("nogrpid", Opt_nogrpid), fsparam_flag ("sysvgroups", Opt_nogrpid), fsparam_gid ("resgid", Opt_resgid), fsparam_uid ("resuid", Opt_resuid), fsparam_u32 ("sb", Opt_sb), fsparam_enum ("errors", Opt_errors, ext4_param_errors), fsparam_flag ("nouid32", Opt_nouid32), fsparam_flag ("debug", Opt_debug), fsparam_flag ("oldalloc", Opt_removed), fsparam_flag ("orlov", Opt_removed), fsparam_flag ("user_xattr", Opt_user_xattr), fsparam_flag ("acl", Opt_acl), fsparam_flag ("norecovery", Opt_noload), fsparam_flag ("noload", Opt_noload), fsparam_flag ("bh", Opt_removed), fsparam_flag ("nobh", Opt_removed), fsparam_u32 ("commit", Opt_commit), fsparam_u32 ("min_batch_time", Opt_min_batch_time), fsparam_u32 ("max_batch_time", Opt_max_batch_time), fsparam_u32 ("journal_dev", Opt_journal_dev), fsparam_bdev ("journal_path", Opt_journal_path), fsparam_flag ("journal_checksum", Opt_journal_checksum), fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum), fsparam_flag ("journal_async_commit",Opt_journal_async_commit), fsparam_flag ("abort", Opt_abort), fsparam_enum ("data", Opt_data, ext4_param_data), fsparam_enum ("data_err", Opt_data_err, ext4_param_data_err), fsparam_string_empty ("usrjquota", Opt_usrjquota), fsparam_string_empty ("grpjquota", Opt_grpjquota), fsparam_enum ("jqfmt", Opt_jqfmt, ext4_param_jqfmt), fsparam_flag ("grpquota", Opt_grpquota), fsparam_flag ("quota", Opt_quota), fsparam_flag ("noquota", Opt_noquota), fsparam_flag ("usrquota", Opt_usrquota), fsparam_flag ("prjquota", Opt_prjquota), fsparam_flag ("barrier", Opt_barrier), fsparam_u32 ("barrier", Opt_barrier), fsparam_flag ("nobarrier", Opt_nobarrier), fsparam_flag ("i_version", Opt_removed), fsparam_flag ("dax", Opt_dax), fsparam_enum ("dax", Opt_dax_type, ext4_param_dax), fsparam_u32 ("stripe", Opt_stripe), fsparam_flag ("delalloc", Opt_delalloc), fsparam_flag ("nodelalloc", Opt_nodelalloc), fsparam_flag ("warn_on_error", Opt_warn_on_error), fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error), fsparam_u32 ("debug_want_extra_isize", Opt_debug_want_extra_isize), fsparam_flag ("mblk_io_submit", Opt_removed), fsparam_flag ("nomblk_io_submit", Opt_removed), fsparam_flag ("block_validity", Opt_block_validity), fsparam_flag ("noblock_validity", Opt_noblock_validity), fsparam_u32 ("inode_readahead_blks", Opt_inode_readahead_blks), fsparam_u32 ("journal_ioprio", Opt_journal_ioprio), fsparam_u32 ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("noauto_da_alloc", Opt_noauto_da_alloc), fsparam_flag ("dioread_nolock", Opt_dioread_nolock), fsparam_flag ("nodioread_nolock", Opt_dioread_lock), fsparam_flag ("dioread_lock", Opt_dioread_lock), fsparam_flag ("discard", Opt_discard), fsparam_flag ("nodiscard", Opt_nodiscard), fsparam_u32 ("init_itable", Opt_init_itable), fsparam_flag ("init_itable", Opt_init_itable), fsparam_flag ("noinit_itable", Opt_noinit_itable), #ifdef CONFIG_EXT4_DEBUG fsparam_flag ("fc_debug_force", Opt_fc_debug_force), fsparam_u32 ("fc_debug_max_replay", Opt_fc_debug_max_replay), #endif fsparam_u32 ("max_dir_size_kb", Opt_max_dir_size_kb), fsparam_flag ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_string ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_flag ("inlinecrypt", Opt_inlinecrypt), fsparam_flag ("nombcache", Opt_nombcache), fsparam_flag ("no_mbcache", Opt_nombcache), /* for backward compatibility */ fsparam_flag ("prefetch_block_bitmaps", Opt_removed), fsparam_flag ("no_prefetch_block_bitmaps", Opt_no_prefetch_block_bitmaps), fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan), fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("noreservation", Opt_removed), /* mount option from ext2/3 */ fsparam_u32 ("journal", Opt_removed), /* mount option from ext2/3 */ {} }; #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 #define MOPT_NOSUPPORT 0x0004 #define MOPT_EXPLICIT 0x0008 #ifdef CONFIG_QUOTA #define MOPT_Q 0 #define MOPT_QFMT 0x0010 #else #define MOPT_Q MOPT_NOSUPPORT #define MOPT_QFMT MOPT_NOSUPPORT #endif #define MOPT_NO_EXT2 0x0020 #define MOPT_NO_EXT3 0x0040 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) #define MOPT_SKIP 0x0080 #define MOPT_2 0x0100 static const struct mount_opts { int token; int mount_opt; int flags; } ext4_mount_opts[] = { {Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET}, {Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR}, {Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET}, {Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR}, {Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET}, {Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR}, {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET}, {Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR}, {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, {Opt_data_err, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2}, {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET}, {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR}, {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, {Opt_dax_type, 0, MOPT_EXT4_ONLY}, {Opt_journal_dev, 0, MOPT_NO_EXT2}, {Opt_journal_path, 0, MOPT_NO_EXT2}, {Opt_journal_ioprio, 0, MOPT_NO_EXT2}, {Opt_data, 0, MOPT_NO_EXT2}, {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, #else {Opt_acl, 0, MOPT_NOSUPPORT}, #endif {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET}, {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET}, {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA, MOPT_SET | MOPT_Q}, {Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA, MOPT_SET | MOPT_Q}, {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, {Opt_usrjquota, 0, MOPT_Q}, {Opt_grpjquota, 0, MOPT_Q}, {Opt_jqfmt, 0, MOPT_QFMT}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, #ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, #endif {Opt_abort, EXT4_MOUNT2_ABORT, MOPT_SET | MOPT_2}, {Opt_err, 0, 0} }; #if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; unsigned int version; } ext4_sb_encoding_map[] = { {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct ext4_sb_encodings * ext4_sb_read_encoding(const struct ext4_super_block *es) { __u16 magic = le16_to_cpu(es->s_encoding); int i; for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++) if (magic == ext4_sb_encoding_map[i].magic) return &ext4_sb_encoding_map[i]; return NULL; } #endif #define EXT4_SPEC_JQUOTA (1 << 0) #define EXT4_SPEC_JQFMT (1 << 1) #define EXT4_SPEC_DATAJ (1 << 2) #define EXT4_SPEC_SB_BLOCK (1 << 3) #define EXT4_SPEC_JOURNAL_DEV (1 << 4) #define EXT4_SPEC_JOURNAL_IOPRIO (1 << 5) #define EXT4_SPEC_s_want_extra_isize (1 << 7) #define EXT4_SPEC_s_max_batch_time (1 << 8) #define EXT4_SPEC_s_min_batch_time (1 << 9) #define EXT4_SPEC_s_inode_readahead_blks (1 << 10) #define EXT4_SPEC_s_li_wait_mult (1 << 11) #define EXT4_SPEC_s_max_dir_size_kb (1 << 12) #define EXT4_SPEC_s_stripe (1 << 13) #define EXT4_SPEC_s_resuid (1 << 14) #define EXT4_SPEC_s_resgid (1 << 15) #define EXT4_SPEC_s_commit_interval (1 << 16) #define EXT4_SPEC_s_fc_debug_max_replay (1 << 17) #define EXT4_SPEC_s_sb_block (1 << 18) #define EXT4_SPEC_mb_optimize_scan (1 << 19) struct ext4_fs_context { char *s_qf_names[EXT4_MAXQUOTAS]; struct fscrypt_dummy_policy dummy_enc_policy; int s_jquota_fmt; /* Format of quota to use */ #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif unsigned short qname_spec; unsigned long vals_s_flags; /* Bits to set in s_flags */ unsigned long mask_s_flags; /* Bits changed in s_flags */ unsigned long journal_devnum; unsigned long s_commit_interval; unsigned long s_stripe; unsigned int s_inode_readahead_blks; unsigned int s_want_extra_isize; unsigned int s_li_wait_mult; unsigned int s_max_dir_size_kb; unsigned int journal_ioprio; unsigned int vals_s_mount_opt; unsigned int mask_s_mount_opt; unsigned int vals_s_mount_opt2; unsigned int mask_s_mount_opt2; unsigned int opt_flags; /* MOPT flags */ unsigned int spec; u32 s_max_batch_time; u32 s_min_batch_time; kuid_t s_resuid; kgid_t s_resgid; ext4_fsblk_t s_sb_block; }; static void ext4_fc_free(struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; int i; if (!ctx) return; for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(ctx->s_qf_names[i]); fscrypt_free_dummy_policy(&ctx->dummy_enc_policy); kfree(ctx); } int ext4_init_fs_context(struct fs_context *fc) { struct ext4_fs_context *ctx; ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; fc->fs_private = ctx; fc->ops = &ext4_context_ops; return 0; } #ifdef CONFIG_QUOTA /* * Note the name of the specified quota file. */ static int note_qf_name(struct fs_context *fc, int qtype, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; char *qname; if (param->size < 1) { ext4_msg(NULL, KERN_ERR, "Missing quota name"); return -EINVAL; } if (strchr(param->string, '/')) { ext4_msg(NULL, KERN_ERR, "quotafile must be on filesystem root"); return -EINVAL; } if (ctx->s_qf_names[qtype]) { if (strcmp(ctx->s_qf_names[qtype], param->string) != 0) { ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(qtype)); return -EINVAL; } return 0; } qname = kmemdup_nul(param->string, param->size, GFP_KERNEL); if (!qname) { ext4_msg(NULL, KERN_ERR, "Not enough memory for storing quotafile name"); return -ENOMEM; } ctx->s_qf_names[qtype] = qname; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } /* * Clear the name of the specified quota file. */ static int unnote_qf_name(struct fs_context *fc, int qtype) { struct ext4_fs_context *ctx = fc->fs_private; kfree(ctx->s_qf_names[qtype]); ctx->s_qf_names[qtype] = NULL; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } #endif static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param, struct ext4_fs_context *ctx) { int err; if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption option not supported"); return -EINVAL; } err = fscrypt_parse_test_dummy_encryption(param, &ctx->dummy_enc_policy); if (err == -EINVAL) { ext4_msg(NULL, KERN_WARNING, "Value of option \"%s\" is unrecognized", param->key); } else if (err == -EEXIST) { ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return err; } #define EXT4_SET_CTX(name) \ static inline __maybe_unused \ void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name |= flag; \ } #define EXT4_CLEAR_CTX(name) \ static inline __maybe_unused \ void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name &= ~flag; \ } #define EXT4_TEST_CTX(name) \ static inline unsigned long \ ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ return (ctx->vals_s_##name & flag); \ } EXT4_SET_CTX(flags); /* set only */ EXT4_SET_CTX(mount_opt); EXT4_CLEAR_CTX(mount_opt); EXT4_TEST_CTX(mount_opt); EXT4_SET_CTX(mount_opt2); EXT4_CLEAR_CTX(mount_opt2); EXT4_TEST_CTX(mount_opt2); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; struct fs_parse_result result; const struct mount_opts *m; int is_remount; int token; token = fs_parse(fc, ext4_param_specs, param, &result); if (token < 0) return token; is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; for (m = ext4_mount_opts; m->token != Opt_err; m++) if (token == m->token) break; ctx->opt_flags |= m->flags; if (m->flags & MOPT_EXPLICIT) { if (m->mount_opt & EXT4_MOUNT_DELALLOC) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_DELALLOC); } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM); } else return -EINVAL; } if (m->flags & MOPT_NOSUPPORT) { ext4_msg(NULL, KERN_ERR, "%s option not supported", param->key); return 0; } switch (token) { #ifdef CONFIG_QUOTA case Opt_usrjquota: if (!*param->string) return unnote_qf_name(fc, USRQUOTA); else return note_qf_name(fc, USRQUOTA, param); case Opt_grpjquota: if (!*param->string) return unnote_qf_name(fc, GRPQUOTA); else return note_qf_name(fc, GRPQUOTA, param); #endif case Opt_sb: if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { ext4_msg(NULL, KERN_WARNING, "Ignoring %s option on remount", param->key); } else { ctx->s_sb_block = result.uint_32; ctx->spec |= EXT4_SPEC_s_sb_block; } return 0; case Opt_removed: ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", param->key); return 0; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_flags(ctx, SB_INLINECRYPT); #else ext4_msg(NULL, KERN_ERR, "inline encryption not supported"); #endif return 0; case Opt_errors: ctx_clear_mount_opt(ctx, EXT4_MOUNT_ERRORS_MASK); ctx_set_mount_opt(ctx, result.uint_32); return 0; #ifdef CONFIG_QUOTA case Opt_jqfmt: ctx->s_jquota_fmt = result.uint_32; ctx->spec |= EXT4_SPEC_JQFMT; return 0; #endif case Opt_data: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); ctx_set_mount_opt(ctx, result.uint_32); ctx->spec |= EXT4_SPEC_DATAJ; return 0; case Opt_commit: if (result.uint_32 == 0) result.uint_32 = JBD2_DEFAULT_MAX_COMMIT_AGE; else if (result.uint_32 > INT_MAX / HZ) { ext4_msg(NULL, KERN_ERR, "Invalid commit interval %d, " "must be smaller than %d", result.uint_32, INT_MAX / HZ); return -EINVAL; } ctx->s_commit_interval = HZ * result.uint_32; ctx->spec |= EXT4_SPEC_s_commit_interval; return 0; case Opt_debug_want_extra_isize: if ((result.uint_32 & 1) || (result.uint_32 < 4)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", result.uint_32); return -EINVAL; } ctx->s_want_extra_isize = result.uint_32; ctx->spec |= EXT4_SPEC_s_want_extra_isize; return 0; case Opt_max_batch_time: ctx->s_max_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_batch_time; return 0; case Opt_min_batch_time: ctx->s_min_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_min_batch_time; return 0; case Opt_inode_readahead_blks: if (result.uint_32 && (result.uint_32 > (1 << 30) || !is_power_of_2(result.uint_32))) { ext4_msg(NULL, KERN_ERR, "EXT4-fs: inode_readahead_blks must be " "0 or a power of 2 smaller than 2^31"); return -EINVAL; } ctx->s_inode_readahead_blks = result.uint_32; ctx->spec |= EXT4_SPEC_s_inode_readahead_blks; return 0; case Opt_init_itable: ctx_set_mount_opt(ctx, EXT4_MOUNT_INIT_INODE_TABLE); ctx->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; if (param->type == fs_value_is_string) ctx->s_li_wait_mult = result.uint_32; ctx->spec |= EXT4_SPEC_s_li_wait_mult; return 0; case Opt_max_dir_size_kb: ctx->s_max_dir_size_kb = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_dir_size_kb; return 0; #ifdef CONFIG_EXT4_DEBUG case Opt_fc_debug_max_replay: ctx->s_fc_debug_max_replay = result.uint_32; ctx->spec |= EXT4_SPEC_s_fc_debug_max_replay; return 0; #endif case Opt_stripe: ctx->s_stripe = result.uint_32; ctx->spec |= EXT4_SPEC_s_stripe; return 0; case Opt_resuid: ctx->s_resuid = result.uid; ctx->spec |= EXT4_SPEC_s_resuid; return 0; case Opt_resgid: ctx->s_resgid = result.gid; ctx->spec |= EXT4_SPEC_s_resgid; return 0; case Opt_journal_dev: if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } ctx->journal_devnum = result.uint_32; ctx->spec |= EXT4_SPEC_JOURNAL_DEV; return 0; case Opt_journal_path: { struct inode *journal_inode; struct path path; int error; if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } error = fs_lookup_param(fc, param, 1, LOOKUP_FOLLOW, &path); if (error) { ext4_msg(NULL, KERN_ERR, "error: could not find " "journal device path"); return -EINVAL; } journal_inode = d_inode(path.dentry); ctx->journal_devnum = new_encode_dev(journal_inode->i_rdev); ctx->spec |= EXT4_SPEC_JOURNAL_DEV; path_put(&path); return 0; } case Opt_journal_ioprio: if (result.uint_32 > 7) { ext4_msg(NULL, KERN_ERR, "Invalid journal IO priority" " (must be 0-7)"); return -EINVAL; } ctx->journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, result.uint_32); ctx->spec |= EXT4_SPEC_JOURNAL_IOPRIO; return 0; case Opt_test_dummy_encryption: return ext4_parse_test_dummy_encryption(param, ctx); case Opt_dax: case Opt_dax_type: #ifdef CONFIG_FS_DAX { int type = (token == Opt_dax) ? Opt_dax : result.uint_32; switch (type) { case Opt_dax: case Opt_dax_always: ctx_set_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); break; case Opt_dax_never: ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); break; case Opt_dax_inode: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); /* Strictly for printing options */ ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE); break; } return 0; } #else ext4_msg(NULL, KERN_INFO, "dax option not supported"); return -EINVAL; #endif case Opt_data_err: if (result.uint_32 == Opt_data_err_abort) ctx_set_mount_opt(ctx, m->mount_opt); else if (result.uint_32 == Opt_data_err_ignore) ctx_clear_mount_opt(ctx, m->mount_opt); return 0; case Opt_mb_optimize_scan: if (result.int_32 == 1) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else if (result.int_32 == 0) { ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else { ext4_msg(NULL, KERN_WARNING, "mb_optimize_scan should be set to 0 or 1."); return -EINVAL; } return 0; } /* * At this point we should only be getting options requiring MOPT_SET, * or MOPT_CLEAR. Anything else is a bug */ if (m->token == Opt_err) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } else { unsigned int set = 0; if ((param->type == fs_value_is_flag) || result.uint_32 > 0) set = 1; if (m->flags & MOPT_CLEAR) set = !set; else if (unlikely(!(m->flags & MOPT_SET))) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } if (m->flags & MOPT_2) { if (set != 0) ctx_set_mount_opt2(ctx, m->mount_opt); else ctx_clear_mount_opt2(ctx, m->mount_opt); } else { if (set != 0) ctx_set_mount_opt(ctx, m->mount_opt); else ctx_clear_mount_opt(ctx, m->mount_opt); } } return 0; } static int parse_options(struct fs_context *fc, char *options) { struct fs_parameter param; int ret; char *key; if (!options) return 0; while ((key = strsep(&options, ",")) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); param.type = fs_value_is_flag; param.string = NULL; if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); param.string = kmemdup_nul(value, v_len, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } param.key = key; param.size = v_len; ret = ext4_parse_param(fc, ¶m); kfree(param.string); if (ret < 0) return ret; } } ret = ext4_validate_options(fc); if (ret < 0) return ret; return 0; } static int parse_apply_sb_mount_options(struct super_block *sb, struct ext4_fs_context *m_ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); char *s_mount_opts = NULL; struct ext4_fs_context *s_ctx = NULL; struct fs_context *fc = NULL; int ret = -ENOMEM; if (!sbi->s_es->s_mount_opts[0]) return 0; s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, sizeof(sbi->s_es->s_mount_opts), GFP_KERNEL); if (!s_mount_opts) return ret; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); if (!fc) goto out_free; s_ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); if (!s_ctx) goto out_free; fc->fs_private = s_ctx; fc->s_fs_info = sbi; ret = parse_options(fc, s_mount_opts); if (ret < 0) goto parse_failed; ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) { parse_failed: ext4_msg(sb, KERN_WARNING, "failed to parse options in superblock: %s", s_mount_opts); ret = 0; goto out_free; } if (s_ctx->spec & EXT4_SPEC_JOURNAL_DEV) m_ctx->journal_devnum = s_ctx->journal_devnum; if (s_ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO) m_ctx->journal_ioprio = s_ctx->journal_ioprio; ext4_apply_options(fc, sb); ret = 0; out_free: if (fc) { ext4_fc_free(fc); kfree(fc); } kfree(s_mount_opts); return ret; } static void ext4_apply_quota_options(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA bool quota_feature = ext4_has_feature_quota(sb); struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); char *qname; int i; if (quota_feature) return; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; qname = ctx->s_qf_names[i]; /* May be NULL */ if (qname) set_opt(sb, QUOTA); ctx->s_qf_names[i] = NULL; qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) kfree_rcu_mightsleep(qname); } } if (ctx->spec & EXT4_SPEC_JQFMT) sbi->s_jquota_fmt = ctx->s_jquota_fmt; #endif } /* * Check quota settings consistency. */ static int ext4_check_quota_consistency(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); bool quota_feature = ext4_has_feature_quota(sb); bool quota_loaded = sb_any_quota_loaded(sb); bool usr_qf_name, grp_qf_name, usrquota, grpquota; int quota_flags, i; /* * We do the test below only for project quotas. 'usrquota' and * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ if (ctx_test_mount_opt(ctx, EXT4_MOUNT_PRJQUOTA) && !ext4_has_feature_project(sb)) { ext4_msg(NULL, KERN_ERR, "Project quota feature not enabled. " "Cannot enable project quota enforcement."); return -EINVAL; } quota_flags = EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA; if (quota_loaded && ctx->mask_s_mount_opt & quota_flags && !ctx_test_mount_opt(ctx, quota_flags)) goto err_quota_change; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; if (quota_loaded && !!sbi->s_qf_names[i] != !!ctx->s_qf_names[i]) goto err_jquota_change; if (sbi->s_qf_names[i] && ctx->s_qf_names[i] && strcmp(get_qf_name(sb, sbi, i), ctx->s_qf_names[i]) != 0) goto err_jquota_specified; } if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Journaled quota options ignored when " "QUOTA feature is enabled"); return 0; } } if (ctx->spec & EXT4_SPEC_JQFMT) { if (sbi->s_jquota_fmt != ctx->s_jquota_fmt && quota_loaded) goto err_jquota_change; if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Quota format mount options " "ignored when QUOTA feature is enabled"); return 0; } } /* Make sure we don't mix old and new quota format */ usr_qf_name = (get_qf_name(sb, sbi, USRQUOTA) || ctx->s_qf_names[USRQUOTA]); grp_qf_name = (get_qf_name(sb, sbi, GRPQUOTA) || ctx->s_qf_names[GRPQUOTA]); usrquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || test_opt(sb, USRQUOTA)); grpquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) || test_opt(sb, GRPQUOTA)); if (usr_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); usrquota = false; } if (grp_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); grpquota = false; } if (usr_qf_name || grp_qf_name) { if (usrquota || grpquota) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } if (!(ctx->spec & EXT4_SPEC_JQFMT || sbi->s_jquota_fmt)) { ext4_msg(NULL, KERN_ERR, "journaled quota format " "not specified"); return -EINVAL; } } return 0; err_quota_change: ext4_msg(NULL, KERN_ERR, "Cannot change quota options when quota turned on"); return -EINVAL; err_jquota_change: ext4_msg(NULL, KERN_ERR, "Cannot change journaled quota " "options when quota turned on"); return -EINVAL; err_jquota_specified: ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(i)); return -EINVAL; #else return 0; #endif } static int ext4_check_test_dummy_encryption(const struct fs_context *fc, struct super_block *sb) { const struct ext4_fs_context *ctx = fc->fs_private; const struct ext4_sb_info *sbi = EXT4_SB(sb); if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy)) return 0; if (!ext4_has_feature_encrypt(sb)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption requires encrypt feature"); return -EINVAL; } /* * This mount option is just for testing, and it's not worthwhile to * implement the extra complexity (e.g. RCU protection) that would be * needed to allow it to be set or changed during remount. We do allow * it to be specified during remount, but only if there is no change. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Can't set or change test_dummy_encryption on remount"); return -EINVAL; } /* Also make sure s_mount_opts didn't contain a conflicting value. */ if (fscrypt_is_dummy_policy_set(&sbi->s_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return 0; } static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx, struct super_block *sb) { if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy) || /* if already set, it was already verified to be the same */ fscrypt_is_dummy_policy_set(&EXT4_SB(sb)->s_dummy_enc_policy)) return; EXT4_SB(sb)->s_dummy_enc_policy = ctx->dummy_enc_policy; memset(&ctx->dummy_enc_policy, 0, sizeof(ctx->dummy_enc_policy)); ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); } static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; int err; if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext2"); return -EINVAL; } if ((ctx->opt_flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext3"); return -EINVAL; } if (ctx->s_want_extra_isize > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", ctx->s_want_extra_isize); return -EINVAL; } err = ext4_check_test_dummy_encryption(fc, sb); if (err) return err; if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) { if (!sbi->s_journal) { ext4_msg(NULL, KERN_WARNING, "Remounting file system with no journal " "so ignoring journalled data option"); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); } else if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS) != test_opt(sb, DATA_FLAGS)) { ext4_msg(NULL, KERN_ERR, "Cannot change data mode " "on remount"); return -EINVAL; } } if (is_remount) { if (!sbi->s_journal && ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT)) { ext4_msg(NULL, KERN_WARNING, "Remounting fs w/o journal so ignoring data_err option"); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT); } if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { fail_dax_change_remount: ext4_msg(NULL, KERN_ERR, "can't change " "dax mount option while remounting"); return -EINVAL; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER) && (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) { goto fail_dax_change_remount; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE) && ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) { goto fail_dax_change_remount; } } return ext4_check_quota_consistency(fc, sb); } static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; sbi->s_mount_opt &= ~ctx->mask_s_mount_opt; sbi->s_mount_opt |= ctx->vals_s_mount_opt; sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; sb->s_flags &= ~ctx->mask_s_flags; sb->s_flags |= ctx->vals_s_flags; #define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; }) APPLY(s_commit_interval); APPLY(s_stripe); APPLY(s_max_batch_time); APPLY(s_min_batch_time); APPLY(s_want_extra_isize); APPLY(s_inode_readahead_blks); APPLY(s_max_dir_size_kb); APPLY(s_li_wait_mult); APPLY(s_resgid); APPLY(s_resuid); #ifdef CONFIG_EXT4_DEBUG APPLY(s_fc_debug_max_replay); #endif ext4_apply_quota_options(fc, sb); ext4_apply_test_dummy_encryption(ctx, sb); } static int ext4_validate_options(struct fs_context *fc) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; char *usr_qf_name, *grp_qf_name; usr_qf_name = ctx->s_qf_names[USRQUOTA]; grp_qf_name = ctx->s_qf_names[GRPQUOTA]; if (usr_qf_name || grp_qf_name) { if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) && usr_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) && grp_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA)) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } } #endif return 1; } static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; switch (sbi->s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; case QFMT_VFS_V0: fmtname = "vfsv0"; break; case QFMT_VFS_V1: fmtname = "vfsv1"; break; } seq_printf(seq, ",jqfmt=%s", fmtname); } rcu_read_lock(); usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); if (usr_qf_name) seq_show_option(seq, "usrjquota", usr_qf_name); if (grp_qf_name) seq_show_option(seq, "grpjquota", grp_qf_name); rcu_read_unlock(); #endif } static const char *token2str(int token) { const struct fs_parameter_spec *spec; for (spec = ext4_param_specs; spec->name != NULL; spec++) if (spec->opt == token && !spec->type) break; return spec->name; } /* * Show an option if * - it's set to a non-default value OR * - if the per-sb default is different from the global default */ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, int nodefs) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int def_errors; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; #define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep) #define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg) if (sbi->s_sb_block != 1) SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block); for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; int opt_2 = m->flags & MOPT_2; unsigned int mount_opt, def_mount_opt; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || m->flags & MOPT_SKIP) continue; if (opt_2) { mount_opt = sbi->s_mount_opt2; def_mount_opt = sbi->s_def_mount_opt2; } else { mount_opt = sbi->s_mount_opt; def_mount_opt = sbi->s_def_mount_opt; } /* skip if same as the default */ if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt))) continue; /* select Opt_noFoo vs Opt_Foo */ if ((want_set && (mount_opt & m->mount_opt) != m->mount_opt) || (!want_set && (mount_opt & m->mount_opt))) continue; SEQ_OPTS_PRINT("%s", token2str(m->token)); } if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) SEQ_OPTS_PRINT("resuid=%u", from_kuid_munged(&init_user_ns, sbi->s_resuid)); if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) SEQ_OPTS_PRINT("resgid=%u", from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE) SEQ_OPTS_PUTS("errors=continue"); if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC) SEQ_OPTS_PUTS("errors=panic"); if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ); if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) SEQ_OPTS_PUTS("data=ordered"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) SEQ_OPTS_PUTS("data=writeback"); } if (nodefs || sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS) SEQ_OPTS_PRINT("inode_readahead_blks=%u", sbi->s_inode_readahead_blks); if (test_opt(sb, INIT_INODE_TABLE) && (nodefs || (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); if (nodefs || sbi->s_max_dir_size_kb) SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); fscrypt_show_test_dummy_encryption(seq, sep, sb); if (sb->s_flags & SB_INLINECRYPT) SEQ_OPTS_PUTS("inlinecrypt"); if (test_opt(sb, DAX_ALWAYS)) { if (IS_EXT2_SB(sb)) SEQ_OPTS_PUTS("dax"); else SEQ_OPTS_PUTS("dax=always"); } else if (test_opt2(sb, DAX_NEVER)) { SEQ_OPTS_PUTS("dax=never"); } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD && !test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=0"); } else if (sbi->s_groups_count < MB_DEFAULT_LINEAR_SCAN_THRESHOLD && test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=1"); } if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) SEQ_OPTS_PUTS("prefetch_block_bitmaps"); if (ext4_emergency_ro(sb)) SEQ_OPTS_PUTS("emergency_ro"); if (ext4_forced_shutdown(sb)) SEQ_OPTS_PUTS("shutdown"); ext4_show_quota_options(seq, sb); return 0; } static int ext4_show_options(struct seq_file *seq, struct dentry *root) { return _ext4_show_options(seq, root->d_sb, 0); } int ext4_seq_options_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; int rc; seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); seq_putc(seq, '\n'); return rc; } static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; goto done; } if (read_only) goto done; if (!(sbi->s_mount_state & EXT4_VALID_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " "running e2fsck is recommended"); else if (sbi->s_mount_state & EXT4_ERROR_FS) ext4_msg(sb, KERN_WARNING, "warning: mounting fs with errors, " "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) ext4_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (ext4_get_tstamp(es, s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds())) ext4_msg(sb, KERN_WARNING, "warning: checktime reached, " "running e2fsck is recommended"); if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); ext4_update_tstamp(es, s_mtime); if (sbi->s_journal) { ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n", sb->s_blocksize, sbi->s_groups_count, EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); return err; } int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups **old_groups, **new_groups; int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; size = ext4_flex_group(sbi, ngroup - 1) + 1; if (size <= sbi->s_flex_groups_allocated) return 0; new_groups = kvzalloc(roundup_pow_of_two(size * sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { ext4_msg(sb, KERN_ERR, "not enough memory for %d flex group pointers", size); return -ENOMEM; } for (i = sbi->s_flex_groups_allocated; i < size; i++) { new_groups[i] = kvzalloc(roundup_pow_of_two( sizeof(struct flex_groups)), GFP_KERNEL); if (!new_groups[i]) { for (j = sbi->s_flex_groups_allocated; j < i; j++) kvfree(new_groups[j]); kvfree(new_groups); ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size); return -ENOMEM; } } rcu_read_lock(); old_groups = rcu_dereference(sbi->s_flex_groups); if (old_groups) memcpy(new_groups, old_groups, (sbi->s_flex_groups_allocated * sizeof(struct flex_groups *))); rcu_read_unlock(); rcu_assign_pointer(sbi->s_flex_groups, new_groups); sbi->s_flex_groups_allocated = size; if (old_groups) ext4_kvfree_array_rcu(old_groups); return 0; } static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; struct flex_groups *fg; ext4_group_t flex_group; int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { sbi->s_log_groups_per_flex = 0; return 1; } err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); if (err) goto failed; for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), &fg->free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; failed: return 0; } static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { int offset = offsetof(struct ext4_group_desc, bg_checksum); __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_feature_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __u32 csum32; __u16 dummy_csum = 0; csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset); csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); if (offset < sbi->s_desc_size) csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset, sbi->s_desc_size - offset); crc = csum32 & 0xFFFF; goto out; } /* old crc16 code */ if (!ext4_has_feature_gdt_csum(sb)) return 0; crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, sbi->s_desc_size - offset); out: return cpu_to_le16(crc); } int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (ext4_has_group_desc_csum(sb) && (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp))) return 0; return 1; } void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (!ext4_has_group_desc_csum(sb)) return; gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp); } /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; ext4_group_t i, grp = sbi->s_groups_count; if (ext4_has_feature_flex_bg(sb)) flexbg_flag = 1; ext4_debug("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); if ((grp == sbi->s_groups_count) && !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap >= sb_block + 1 && block_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap >= sb_block + 1 && inode_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_table >= sb_block + 1 && inode_table <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " "(block %llu)!", i, inode_table); return 0; } ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sb, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!sb_rdonly(sb)) { ext4_unlock_group(sb, i); return 0; } } ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } if (NULL != first_not_zeroed) *first_not_zeroed = grp; return 1; } /* * Maximal extent format file size. * Resulting logical blkno at s_maxbytes must fit in our on-disk * extent format containers, within a sector_t, and within i_blocks * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, * so that won't be a limiting factor. * * However there is other limiting factor. We do store extents in the form * of starting block and length, hence the resulting length of the extent * covering maximum file size must fit into on-disk format containers as * well. Given that length is always by 1 unit bigger than max unit (because * we count 0 as well) we have to lower the s_maxbytes by one fs block. * * Note, this does *not* consider any metadata overhead for vfs i_blocks. */ static loff_t ext4_max_size(int blkbits, int has_huge_files) { loff_t res; loff_t upper_limit = MAX_LFS_FILESIZE; BUILD_BUG_ON(sizeof(blkcnt_t) < sizeof(u64)); if (!has_huge_files) { upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (blkbits - 9); upper_limit <<= blkbits; } /* * 32-bit extent-start container, ee_block. We lower the maxbytes * by one fs block, so ee_len can cover the extent of maximum file * size */ res = (1LL << 32) - 1; res <<= blkbits; /* Sanity check against vm- & vfs- imposed limits */ if (res > upper_limit) res = upper_limit; return res; } /* * Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks. * We need to be 1 filesystem block less than the 2^48 sector limit. */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { loff_t upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; unsigned int ppb = 1 << (bits - 2); /* * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field * represents total file blocks in 2^32 512-byte sectors == * size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (bits - 9); } else { /* * We use 48 bit ext4_inode i_blocks * With EXT4_HUGE_FILE_FL set the i_blocks * represent total number of blocks in * file system block size */ upper_limit = (1LL << 48) - 1; } /* Compute how many blocks we can address by block tree */ res += ppb; res += ppb * ppb; res += ((loff_t)ppb) * ppb * ppb; /* Compute how many metadata blocks are needed */ meta_blocks = 1; meta_blocks += 1 + ppb; meta_blocks += 1 + ppb + ppb * ppb; /* Does block tree limit file size? */ if (res + meta_blocks <= upper_limit) goto check_lfs; res = upper_limit; /* How many metadata blocks are needed for addressing upper_limit? */ upper_limit -= EXT4_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; upper_limit -= ppb; /* double indirect blocks */ if (upper_limit < ppb * ppb) { meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb); res -= meta_blocks; goto check_lfs; } meta_blocks += 1 + ppb; upper_limit -= ppb * ppb; /* tripple indirect blocks for the rest */ meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) + DIV_ROUND_UP_ULL(upper_limit, ppb*ppb); res -= meta_blocks; check_lfs: res <<= bits; if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; return res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t bg, first_meta_bg; int has_super = 0; first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg) return logical_sb_block + nr + 1; bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) has_super = 1; /* * If we have a meta_bg fs with 1k blocks, group 0's GDT is at * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled * on modern mke2fs or blksize > 1k on older mke2fs) then we must * compensate. */ if (sb->s_blocksize == 1024 && nr == 0 && le32_to_cpu(sbi->s_es->s_first_data_block) == 0) has_super++; return (has_super + ext4_group_first_block_no(sb, bg)); } /** * ext4_get_stripe_size: Get the stripe size. * @sbi: In memory super block info * * If we have specified it via mount option, then * use the mount option value. If the value specified at mount time is * greater than the blocks per group use the super block value. * If the super block value is greater than blocks per group return 0. * Allocator needs it be less than blocks per group. * */ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) { unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride); unsigned long stripe_width = le32_to_cpu(sbi->s_es->s_raid_stripe_width); int ret; if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) ret = sbi->s_stripe; else if (stripe_width && stripe_width <= sbi->s_blocks_per_group) ret = stripe_width; else if (stride && stride <= sbi->s_blocks_per_group) ret = stride; else ret = 0; /* * If the stripe width is 1, this makes no sense and * we set it to 0 to turn off stripe handling code. */ if (ret <= 1) ret = 0; return ret; } /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. * Returns 1 if this filesystem can be mounted as requested, * 0 if it cannot be. */ int ext4_feature_set_ok(struct super_block *sb, int readonly) { if (ext4_has_unknown_ext4_incompat_features(sb)) { ext4_msg(sb, KERN_ERR, "Couldn't mount because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & ~EXT4_FEATURE_INCOMPAT_SUPP)); return 0; } if (!IS_ENABLED(CONFIG_UNICODE) && ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " "mounted without CONFIG_UNICODE"); return 0; } if (readonly) return 1; if (ext4_has_feature_readonly(sb)) { ext4_msg(sb, KERN_INFO, "filesystem is read-only"); sb->s_flags |= SB_RDONLY; return 1; } /* Check that feature set is OK for a read-write mount */ if (ext4_has_unknown_ext4_ro_compat_features(sb)) { ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); return 0; } if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " "extents feature\n"); return 0; } #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ return 1; } /* * This function is called once a day if we have errors logged * on the file system */ static void print_daily_error_info(struct timer_list *t) { struct ext4_sb_info *sbi = from_timer(sbi, t, s_err_report); struct super_block *sb = sbi->s_sb; struct ext4_super_block *es = sbi->s_es; if (es->s_error_count) /* fsck newer than v1.41.13 is needed to clean this condition. */ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, le32_to_cpu(es->s_first_error_line)); if (es->s_first_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_first_error_ino)); if (es->s_first_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_first_error_block)); printk(KERN_CONT "\n"); } if (es->s_last_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, le32_to_cpu(es->s_last_error_line)); if (es->s_last_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_last_error_ino)); if (es->s_last_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_last_error_block)); printk(KERN_CONT "\n"); } mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */ } /* Find next suitable group and run ext4_init_inode_table */ static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; struct super_block *sb = elr->lr_super; ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; ext4_group_t group = elr->lr_next_group; unsigned int prefetch_ios = 0; int ret = 0; int nr = EXT4_SB(sb)->s_mb_prefetch; u64 start_time; if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { elr->lr_next_group = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); ext4_mb_prefetch_fini(sb, elr->lr_next_group, nr); trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, nr); if (group >= elr->lr_next_group) { ret = 1; if (elr->lr_first_not_zeroed != ngroups && !ext4_emergency_state(sb) && !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { elr->lr_next_group = elr->lr_first_not_zeroed; elr->lr_mode = EXT4_LI_MODE_ITABLE; ret = 0; } } return ret; } for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; break; } if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } if (group >= ngroups) ret = 1; if (!ret) { start_time = ktime_get_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) * EXT4_SB(elr->lr_super)->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } return ret; } /* * Remove lr_request from the list_request and free the * request structure. Should be called with li_list_mtx held */ static void ext4_remove_li_request(struct ext4_li_request *elr) { if (!elr) return; list_del(&elr->lr_request); EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } static void ext4_unregister_li_request(struct super_block *sb) { mutex_lock(&ext4_li_mtx); if (!ext4_li_info) { mutex_unlock(&ext4_li_mtx); return; } mutex_lock(&ext4_li_info->li_list_mtx); ext4_remove_li_request(EXT4_SB(sb)->s_li_request); mutex_unlock(&ext4_li_info->li_list_mtx); mutex_unlock(&ext4_li_mtx); } static struct task_struct *ext4_lazyinit_task; /* * This is the function where ext4lazyinit thread lives. It walks * through the request list searching for next scheduled filesystem. * When such a fs is found, run the lazy initialization request * (ext4_rn_li_request) and keep track of the time spend in this * function. Based on that time we compute next schedule time of * the request. When walking through the list is complete, compute * next waking time and put itself into sleep. */ static int ext4_lazyinit_thread(void *arg) { struct ext4_lazy_init *eli = arg; struct list_head *pos, *n; struct ext4_li_request *elr; unsigned long next_wakeup, cur; BUG_ON(NULL == eli); set_freezable(); cont_thread: while (true) { bool next_wakeup_initialized = false; next_wakeup = 0; mutex_lock(&eli->li_list_mtx); if (list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); goto exit_thread; } list_for_each_safe(pos, n, &eli->li_request_list) { int err = 0; int progress = 0; elr = list_entry(pos, struct ext4_li_request, lr_request); if (time_before(jiffies, elr->lr_next_sched)) { if (!next_wakeup_initialized || time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; next_wakeup_initialized = true; } continue; } if (down_read_trylock(&elr->lr_super->s_umount)) { if (sb_start_write_trylock(elr->lr_super)) { progress = 1; /* * We hold sb->s_umount, sb can not * be removed from the list, it is * now safe to drop li_list_mtx */ mutex_unlock(&eli->li_list_mtx); err = ext4_run_li_request(elr); sb_end_write(elr->lr_super); mutex_lock(&eli->li_list_mtx); n = pos->next; } up_read((&elr->lr_super->s_umount)); } /* error, remove the lazy_init job */ if (err) { ext4_remove_li_request(elr); continue; } if (!progress) { elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); } if (!next_wakeup_initialized || time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; next_wakeup_initialized = true; } } mutex_unlock(&eli->li_list_mtx); try_to_freeze(); cur = jiffies; if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) { cond_resched(); continue; } schedule_timeout_interruptible(next_wakeup - cur); if (kthread_should_stop()) { ext4_clear_request_list(); goto exit_thread; } } exit_thread: /* * It looks like the request list is empty, but we need * to check it under the li_list_mtx lock, to prevent any * additions into it, and of course we should lock ext4_li_mtx * to atomically free the list and ext4_li_info, because at * this point another ext4 filesystem could be registering * new one. */ mutex_lock(&ext4_li_mtx); mutex_lock(&eli->li_list_mtx); if (!list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); mutex_unlock(&ext4_li_mtx); goto cont_thread; } mutex_unlock(&eli->li_list_mtx); kfree(ext4_li_info); ext4_li_info = NULL; mutex_unlock(&ext4_li_mtx); return 0; } static void ext4_clear_request_list(void) { struct list_head *pos, *n; struct ext4_li_request *elr; mutex_lock(&ext4_li_info->li_list_mtx); list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { elr = list_entry(pos, struct ext4_li_request, lr_request); ext4_remove_li_request(elr); } mutex_unlock(&ext4_li_info->li_list_mtx); } static int ext4_run_lazyinit_thread(void) { ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); if (IS_ERR(ext4_lazyinit_task)) { int err = PTR_ERR(ext4_lazyinit_task); ext4_clear_request_list(); kfree(ext4_li_info); ext4_li_info = NULL; printk(KERN_CRIT "EXT4-fs: error %d creating inode table " "initialization thread\n", err); return err; } ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING; return 0; } /* * Check whether it make sense to run itable init. thread or not. * If there is at least one uninitialized inode table, return * corresponding group number, else the loop goes through all * groups and return total number of groups. */ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) { ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; struct ext4_group_desc *gdp = NULL; if (!ext4_has_group_desc_csum(sb)) return ngroups; for (group = 0; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) continue; if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } return group; } static int ext4_li_info_new(void) { struct ext4_lazy_init *eli = NULL; eli = kzalloc(sizeof(*eli), GFP_KERNEL); if (!eli) return -ENOMEM; INIT_LIST_HEAD(&eli->li_request_list); mutex_init(&eli->li_list_mtx); eli->li_state |= EXT4_LAZYINIT_QUIT; ext4_li_info = eli; return 0; } static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { struct ext4_li_request *elr; elr = kzalloc(sizeof(*elr), GFP_KERNEL); if (!elr) return NULL; elr->lr_super = sb; elr->lr_first_not_zeroed = start; if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) { elr->lr_mode = EXT4_LI_MODE_ITABLE; elr->lr_next_group = start; } else { elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; } /* * Randomize first schedule time of the request to * spread the inode table initialization requests * better. */ elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); return elr; } int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr = NULL; ext4_group_t ngroups = sbi->s_groups_count; int ret = 0; mutex_lock(&ext4_li_mtx); if (sbi->s_li_request != NULL) { /* * Reset timeout so it can be computed again, because * s_li_wait_mult might have changed. */ sbi->s_li_request->lr_timeout = 0; goto out; } if (ext4_emergency_state(sb) || sb_rdonly(sb) || (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && (first_not_zeroed == ngroups || !test_opt(sb, INIT_INODE_TABLE)))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); if (!elr) { ret = -ENOMEM; goto out; } if (NULL == ext4_li_info) { ret = ext4_li_info_new(); if (ret) goto out; } mutex_lock(&ext4_li_info->li_list_mtx); list_add(&elr->lr_request, &ext4_li_info->li_request_list); mutex_unlock(&ext4_li_info->li_list_mtx); sbi->s_li_request = elr; /* * set elr to NULL here since it has been inserted to * the request_list and the removal and free of it is * handled by ext4_clear_request_list from now on. */ elr = NULL; if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { ret = ext4_run_lazyinit_thread(); if (ret) goto out; } out: mutex_unlock(&ext4_li_mtx); if (ret) kfree(elr); return ret; } /* * We do not need to lock anything since this is called on * module unload. */ static void ext4_destroy_lazyinit_thread(void) { /* * If thread exited earlier * there's nothing to be done. */ if (!ext4_li_info || !ext4_lazyinit_task) return; kthread_stop(ext4_lazyinit_task); } static int set_journal_csum_feature_set(struct super_block *sb) { int ret = 1; int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_feature_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; incompat = 0; } jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | incompat); } else if (test_opt(sb, JOURNAL_CHECKSUM)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, incompat); jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } else { jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } return ret; } /* * Note: calculating the overhead so we can be compatible with * historical BSD practice is quite difficult in the face of * clusters/bigalloc. This is because multiple metadata blocks from * different block group can end up in the same allocation cluster. * Calculating the exact overhead in the face of clustered allocation * requires either O(all block bitmaps) in memory or O(number of block * groups**2) in time. We will still calculate the superblock for * older file systems --- and if we come across with a bigalloc file * system with zero in s_overhead_clusters the estimate will be close to * correct especially for very large cluster sizes --- but for newer * file systems, it's better to calculate this figure once at mkfs * time, and store it in the superblock. If the superblock value is * present (even for non-bigalloc file systems), we will use it. */ static int count_overhead(struct super_block *sb, ext4_group_t grp, char *buf) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp; ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) return (has_super + ext4_bg_num_gdb(sb, grp) + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + (grp * EXT4_BLOCKS_PER_GROUP(sb)); last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); b = ext4_block_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_table(sb, gdp); if (b >= first_block && b + sbi->s_itb_per_group <= last_block) for (j = 0; j < sbi->s_itb_per_group; j++, b++) { int c = EXT4_B2C(sbi, b - first_block); ext4_set_bit(c, buf); count++; } if (i != grp) continue; s = 0; if (ext4_bg_has_super(sb, grp)) { ext4_set_bit(s++, buf); count++; } j = ext4_bg_num_gdb(sb, grp); if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) { ext4_error(sb, "Invalid number of block group " "descriptor blocks: %d", j); j = EXT4_BLOCKS_PER_GROUP(sb) - s; } count += j; for (; j > 0; j--) ext4_set_bit(EXT4_B2C(sbi, s++), buf); } if (!count) return 0; return EXT4_CLUSTERS_PER_GROUP(sb) - ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); } /* * Compute the overhead and stash it in sbi->s_overhead */ int ext4_calculate_overhead(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct inode *j_inode; unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum); ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; char *buf = (char *) get_zeroed_page(GFP_NOFS); if (!buf) return -ENOMEM; /* * Compute the overhead (FS structures). This is constant * for a given filesystem unless the number of block groups * changes so we cache the previous value until it does. */ /* * All of the blocks before first_data_block are overhead */ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); /* * Add the overhead found in each block group */ for (i = 0; i < ngroups; i++) { int blks; blks = count_overhead(sb, i, buf); overhead += blks; if (blks) memset(buf, 0, PAGE_SIZE); cond_resched(); } /* * Add the internal journal blocks whether the journal has been * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev_file) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); if (!IS_ERR(j_inode)) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; overhead += EXT4_NUM_B2C(sbi, j_blocks); iput(j_inode); } else { ext4_msg(sb, KERN_ERR, "can't get journal size"); } } sbi->s_overhead = overhead; smp_wmb(); free_page((unsigned long) buf); return 0; } static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * There's no need to reserve anything when we aren't using extents. * The space estimates are exact, there are no unwritten extents, * hole punching doesn't need new metadata... This is needed especially * to keep ext2/3 backward compatibility. */ if (!ext4_has_feature_extents(sb)) return; /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run * out of space like for example punch hole, or converting * unwritten extents in delalloc path. In most cases such * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ resv_clusters = (ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits); do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); atomic64_set(&sbi->s_resv_clusters, resv_clusters); } static const char *ext4_quota_mode(struct super_block *sb) { #ifdef CONFIG_QUOTA if (!ext4_quota_capable(sb)) return "none"; if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb)) return "journalled"; else return "writeback"; #else return "disabled"; #endif } static void ext4_setup_csum_trigger(struct super_block *sb, enum ext4_journal_trigger_type type, void (*trigger)( struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size)) { struct ext4_sb_info *sbi = EXT4_SB(sb); sbi->s_journal_triggers[type].sb = sb; sbi->s_journal_triggers[type].tr_triggers.t_frozen = trigger; } static void ext4_free_sbi(struct ext4_sb_info *sbi) { if (!sbi) return; kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) { struct ext4_sb_info *sbi; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return NULL; sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, NULL, NULL); sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) goto err_out; sb->s_fs_info = sbi; sbi->s_sb = sb; return sbi; err_out: fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); return NULL; } static void ext4_set_def_opts(struct super_block *sb, struct ext4_super_block *es) { unsigned long def_mount_opts; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); set_opt(sb, INIT_INODE_TABLE); if (def_mount_opts & EXT4_DEFM_DEBUG) set_opt(sb, DEBUG); if (def_mount_opts & EXT4_DEFM_BSDGROUPS) set_opt(sb, GRPID); if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ set_opt(sb, XATTR_USER); #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif if (ext4_has_feature_fast_commit(sb)) set_opt2(sb, JOURNAL_FAST_COMMIT); /* don't forget to enable journal_csum when metadata_csum is enabled. */ if (ext4_has_feature_metadata_csum(sb)) set_opt(sb, JOURNAL_CHECKSUM); if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) set_opt(sb, ORDERED_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK) set_opt(sb, WRITEBACK_DATA); if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_PANIC) set_opt(sb, ERRORS_PANIC); else if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_CONTINUE) set_opt(sb, ERRORS_CONT); else set_opt(sb, ERRORS_RO); /* block_validity enabled by default; disable with noblock_validity */ set_opt(sb, BLOCK_VALIDITY); if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0) set_opt(sb, BARRIER); /* * enable delayed allocation by default * Use -o nodelalloc to turn it off */ if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) && ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); if (sb->s_blocksize <= PAGE_SIZE) set_opt(sb, DIOREAD_NOLOCK); } static int ext4_handle_clustersize(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int clustersize; /* Handle clustersize */ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); if (ext4_has_feature_bigalloc(sb)) { if (clustersize < sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "cluster size (%d) smaller than " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); } else { if (clustersize != sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "fragment/cluster size (%d) != " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#blocks per group too big: %lu", sbi->s_blocks_per_group); return -EINVAL; } sbi->s_cluster_bits = 0; } sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group); if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu", sbi->s_clusters_per_group); return -EINVAL; } if (sbi->s_blocks_per_group != (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and clusters per group (%lu) inconsistent", sbi->s_blocks_per_group, sbi->s_clusters_per_group); return -EINVAL; } sbi->s_cluster_ratio = clustersize / sb->s_blocksize; /* Do we have standard group size of clustersize * 8 blocks ? */ if (sbi->s_blocks_per_group == clustersize << 3) set_opt2(sb, STD_GROUP_SIZE); return 0; } /* * ext4_atomic_write_init: Initializes filesystem min & max atomic write units. * @sb: super block * TODO: Later add support for bigalloc */ static void ext4_atomic_write_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct block_device *bdev = sb->s_bdev; if (!bdev_can_atomic_write(bdev)) return; if (!ext4_has_feature_extents(sb)) return; sbi->s_awu_min = max(sb->s_blocksize, bdev_atomic_write_unit_min_bytes(bdev)); sbi->s_awu_max = min(sb->s_blocksize, bdev_atomic_write_unit_max_bytes(bdev)); if (sbi->s_awu_min && sbi->s_awu_max && sbi->s_awu_min <= sbi->s_awu_max) { ext4_msg(sb, KERN_NOTICE, "Supports (experimental) DIO atomic writes awu_min: %u, awu_max: %u", sbi->s_awu_min, sbi->s_awu_max); } else { sbi->s_awu_min = 0; sbi->s_awu_max = 0; } } static void ext4_fast_commit_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Initialize fast commit stuff */ atomic_set(&sbi->s_fc_subtid, 0); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); sbi->s_fc_ineligible_tid = 0; spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; sbi->s_fc_replay_state.fc_regions_size = 0; sbi->s_fc_replay_state.fc_regions_used = 0; sbi->s_fc_replay_state.fc_regions_valid = 0; sbi->s_fc_replay_state.fc_modified_inodes = NULL; sbi->s_fc_replay_state.fc_modified_inodes_size = 0; sbi->s_fc_replay_state.fc_modified_inodes_used = 0; } static int ext4_inode_info_init(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; } else { sbi->s_inode_size = le16_to_cpu(es->s_inode_size); sbi->s_first_ino = le32_to_cpu(es->s_first_ino); if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { ext4_msg(sb, KERN_ERR, "invalid first ino: %u", sbi->s_first_ino); return -EINVAL; } if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > sb->s_blocksize)) { ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); ext4_msg(sb, KERN_ERR, "blocksize: %lu", sb->s_blocksize); return -EINVAL; } /* * i_atime_extra is the last extra field available for * [acm]times in struct ext4_inode. Checking for that * field should suffice to ensure we have extra space * for all three. */ if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { sb->s_time_gran = 1; sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; } else { sb->s_time_gran = NSEC_PER_SEC; sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; } sb->s_time_min = EXT4_TIMESTAMP_MIN; } if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; if (ext4_has_feature_extra_isize(sb)) { unsigned v, max = (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE); v = le16_to_cpu(es->s_want_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_want_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; v = le16_to_cpu(es->s_min_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_min_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; } } return 0; } #if IS_ENABLED(CONFIG_UNICODE) static int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; __u16 encoding_flags = le16_to_cpu(es->s_encoding_flags); if (!ext4_has_feature_casefold(sb) || sb->s_encoding) return 0; encoding_info = ext4_sb_read_encoding(es); if (!encoding_info) { ext4_msg(sb, KERN_ERR, "Encoding requested by superblock is unknown"); return -EINVAL; } encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { ext4_msg(sb, KERN_ERR, "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); return -EINVAL; } ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); sb->s_encoding = encoding; sb->s_encoding_flags = encoding_flags; return 0; } #else static inline int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { return 0; } #endif static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Warn if metadata_csum and gdt_csum are both set. */ if (ext4_has_feature_metadata_csum(sb) && ext4_has_feature_gdt_csum(sb)) ext4_warning(sb, "metadata_csum and uninit_bg are " "redundant flags; please run fsck."); /* Check for a known checksum algorithm */ if (!ext4_verify_csum_type(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "unknown checksum algorithm."); return -EINVAL; } ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "invalid superblock checksum. Run e2fsck?"); return -EFSBADCRC; } /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); else if (ext4_has_feature_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); return 0; } static int ext4_check_feature_compatibility(struct super_block *sb, struct ext4_super_block *es, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && (ext4_has_compat_features(sb) || ext4_has_ro_compat_features(sb) || ext4_has_incompat_features(sb))) ext4_msg(sb, KERN_WARNING, "feature flags set on rev 0 fs, " "running e2fsck is recommended"); if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) { set_opt2(sb, HURD_COMPAT); if (ext4_has_feature_64bit(sb)) { ext4_msg(sb, KERN_ERR, "The Hurd can't support 64-bit file systems"); return -EINVAL; } /* * ea_inode feature uses l_i_version field which is not * available in HURD_COMPAT mode. */ if (ext4_has_feature_ea_inode(sb)) { ext4_msg(sb, KERN_ERR, "ea_inode feature is not supported for Hurd"); return -EINVAL; } } if (IS_EXT2_SB(sb)) { if (ext2_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext2 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext[34] filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due " "to feature incompatibilities"); return -EINVAL; } } if (IS_EXT3_SB(sb)) { if (ext3_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext3 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext4 filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due " "to feature incompatibilities"); return -EINVAL; } } /* * Check feature flags regardless of the revision level, since we * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) return -EINVAL; if (sbi->s_daxdev) { if (sb->s_blocksize == PAGE_SIZE) set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); else ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem" " that may contain inline data"); return -EINVAL; } if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "DAX unsupported by block device."); return -EINVAL; } } if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) { ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", es->s_encryption_level); return -EINVAL; } return 0; } static int ext4_check_geometry(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); __u64 blocks_count; int err; if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) { ext4_msg(sb, KERN_ERR, "Number of reserved GDT blocks insanely large: %d", le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); return -EINVAL; } /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); return err; } /* check blocks count against device size */ blocks_count = sb_bdev_nr_blocks(sb); if (blocks_count && ext4_blocks_count(es) > blocks_count) { ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " "exceeds size of device (%llu blocks)", ext4_blocks_count(es), blocks_count); return -EINVAL; } /* * It makes no sense for the first data block to be beyond the end * of the filesystem. */ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block %u is beyond end of filesystem (%llu)", le32_to_cpu(es->s_first_data_block), ext4_blocks_count(es)); return -EINVAL; } if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && (sbi->s_cluster_ratio == 1)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block is 0 with a 1k block and cluster size"); return -EINVAL; } blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " "(block count %llu, first data block %u, " "blocks per group %lu)", blocks_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); return -EINVAL; } sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != le32_to_cpu(es->s_inodes_count)) { ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", le32_to_cpu(es->s_inodes_count), ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); return -EINVAL; } return 0; } static int ext4_group_desc_init(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t logical_sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int db_count; ext4_fsblk_t block; int i; db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { if (le32_to_cpu(es->s_first_meta_bg) > db_count) { ext4_msg(sb, KERN_WARNING, "first meta block group too large: %u " "(group descriptor block count %u)", le32_to_cpu(es->s_first_meta_bg), db_count); return -EINVAL; } } rcu_assign_pointer(sbi->s_group_desc, kvmalloc_array(db_count, sizeof(struct buffer_head *), GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); return -ENOMEM; } bgl_lock_init(sbi->s_blockgroup_lock); /* Pre-read the descriptors into the buffer cache */ for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logical_sb_block, i); ext4_sb_breadahead_unmovable(sb, block); } for (i = 0; i < db_count; i++) { struct buffer_head *bh; block = descriptor_loc(sb, logical_sb_block, i); bh = ext4_sb_bread_unmovable(sb, block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); sbi->s_gdb_count = i; return PTR_ERR(bh); } rcu_read_lock(); rcu_dereference(sbi->s_group_desc)[i] = bh; rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); return -EFSCORRUPTED; } return 0; } static int ext4_load_and_init_journal(struct super_block *sb, struct ext4_super_block *es, struct ext4_fs_context *ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err; err = ext4_load_journal(sb, es, ctx->journal_devnum); if (err) return err; if (ext4_has_feature_64bit(sb) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto out; } if (!set_journal_csum_feature_set(sb)) { ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " "feature set"); goto out; } if (test_opt2(sb, JOURNAL_FAST_COMMIT) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { ext4_msg(sb, KERN_ERR, "Failed to set fast commit journal feature"); goto out; } /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { case 0: /* No mode set, assume a default based on the journal * capabilities: ORDERED_DATA if the journal can * cope, else JOURNAL_DATA */ if (jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { set_opt(sb, ORDERED_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_ORDERED_DATA; } else { set_opt(sb, JOURNAL_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; } break; case EXT4_MOUNT_ORDERED_DATA: case EXT4_MOUNT_WRITEBACK_DATA: if (!jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { ext4_msg(sb, KERN_ERR, "Journal does not support " "requested data journaling mode"); goto out; } break; default: break; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA && test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); goto out; } set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); sbi->s_journal->j_submit_inode_data_buffers = ext4_journal_submit_inode_data_buffers; sbi->s_journal->j_finish_inode_data_buffers = ext4_journal_finish_inode_data_buffers; return 0; out: ext4_journal_destroy(sbi, sbi->s_journal); return -EINVAL; } static int ext4_check_journal_data_mode(struct super_block *sb) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with " "data=journal disables delayed allocation, " "dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); return -EINVAL; } if (test_opt(sb, DAX_ALWAYS)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ext4_has_feature_encrypt(sb)) { ext4_msg(sb, KERN_WARNING, "encrypted files will use data=ordered " "instead of data journaling mode"); } if (test_opt(sb, DELALLOC)) clear_opt(sb, DELALLOC); } else { sb->s_iflags |= SB_I_CGROUPWB; } return 0; } static const char *ext4_has_journal_option(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) return "journal_async_commit"; if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) return "journal_checksum"; if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) return "commit="; if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) return "data="; if (test_opt(sb, DATA_ERR_ABORT)) return "data_err=abort"; return NULL; } static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es; ext4_fsblk_t logical_sb_block; unsigned long offset = 0; struct buffer_head *bh; int ret = -EINVAL; int blocksize; blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { ext4_msg(sb, KERN_ERR, "unable to set blocksize"); return -EINVAL; } /* * The ext4 superblock will not be buffer aligned for other than 1kB * block sizes. We need to calculate the offset from buffer start. */ if (blocksize != EXT4_MIN_BLOCK_SIZE) { logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); } else { logical_sb_block = sbi->s_sb_block; } bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "unable to read superblock"); return PTR_ERR(bh); } /* * Note: s_es must be initialized as soon as possible because * some ext4 macro-instructions depend on its value */ es = (struct ext4_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT4_SUPER_MAGIC) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto out; } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log block size: %u", le32_to_cpu(es->s_log_block_size)); goto out; } if (le32_to_cpu(es->s_log_cluster_size) > (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log cluster size: %u", le32_to_cpu(es->s_log_cluster_size)); goto out; } blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); /* * If the default block size is not the same as the real block size, * we need to reload it. */ if (sb->s_blocksize == blocksize) { *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; } /* * bh must be released before kill_bdev(), otherwise * it won't be freed and its page also. kill_bdev() * is called by sb_set_blocksize(). */ brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); bh = NULL; goto out; } logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "Can't read superblock on 2nd try"); ret = PTR_ERR(bh); bh = NULL; goto out; } es = (struct ext4_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!"); goto out; } *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; out: brelse(bh); return ret; } static int ext4_hash_info_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; unsigned int i; sbi->s_def_hash_version = es->s_def_hash_version; if (sbi->s_def_hash_version > DX_HASH_LAST) { ext4_msg(sb, KERN_ERR, "Invalid default hash set in the superblock"); return -EINVAL; } else if (sbi->s_def_hash_version == DX_HASH_SIPHASH) { ext4_msg(sb, KERN_ERR, "SIPHASH is not a valid default hash value"); return -EINVAL; } for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); if (ext4_has_feature_dir_index(sb)) { i = le32_to_cpu(es->s_flags); if (i & EXT2_FLAGS_UNSIGNED_HASH) sbi->s_hash_unsigned = 3; else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); sbi->s_hash_unsigned = 3; #else if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif } } return 0; } static int ext4_block_group_meta_init(struct super_block *sb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int has_huge_files; has_huge_files = ext4_has_feature_huge_file(sb); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { ext4_msg(sb, KERN_ERR, "unsupported descriptor size %lu", sbi->s_desc_size); return -EINVAL; } } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); return -EINVAL; } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", sbi->s_inodes_per_group); return -EINVAL; } sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb); sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY; sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); return 0; } /* * It's hard to get stripe aligned blocks if stripe is not aligned with * cluster, just disable stripe and alert user to simplify code and avoid * stripe aligned allocation which will rarely succeed. */ static bool ext4_is_stripe_incompatible(struct super_block *sb, unsigned long stripe) { struct ext4_sb_info *sbi = EXT4_SB(sb); return (stripe > 0 && sbi->s_cluster_ratio > 1 && stripe % sbi->s_cluster_ratio != 0); } static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) { struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t logical_sb_block; struct inode *root; int needs_recovery; int err; ext4_group_t first_not_zeroed; struct ext4_fs_context *ctx = fc->fs_private; int silent = fc->sb_flags & SB_SILENT; /* Set defaults for the variables that will be set during parsing */ if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sectors_written_start = part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); err = ext4_load_super(sb, &logical_sb_block, silent); if (err) goto out_fail; es = sbi->s_es; sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); err = ext4_init_metadata_csum(sb, es); if (err) goto failed_mount; ext4_set_def_opts(sb, es); sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; sbi->s_sb_update_kb = EXT4_DEF_SB_UPDATE_INTERVAL_KB; sbi->s_sb_update_sec = EXT4_DEF_SB_UPDATE_INTERVAL_SEC; /* * set default s_li_wait_mult for lazyinit, for the case there is * no mount option specified. */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; err = ext4_inode_info_init(sb, es); if (err) goto failed_mount; err = parse_apply_sb_mount_options(sb, ctx); if (err < 0) goto failed_mount; sbi->s_def_mount_opt = sbi->s_mount_opt; sbi->s_def_mount_opt2 = sbi->s_mount_opt2; err = ext4_check_opt_consistency(fc, sb); if (err < 0) goto failed_mount; ext4_apply_options(fc, sb); err = ext4_encoding_init(sb, es); if (err) goto failed_mount; err = ext4_check_journal_data_mode(sb); if (err) goto failed_mount; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; /* HSM events are allowed by default. */ sb->s_iflags |= SB_I_ALLOW_HSM; err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; err = ext4_block_group_meta_init(sb, silent); if (err) goto failed_mount; err = ext4_hash_info_init(sb); if (err) goto failed_mount; err = ext4_handle_clustersize(sb); if (err) goto failed_mount; err = ext4_check_geometry(sb, es); if (err) goto failed_mount; timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); if (err) goto failed_mount3; err = ext4_es_register_shrinker(sbi); if (err) goto failed_mount3; sbi->s_stripe = ext4_get_stripe_size(sbi); if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", sbi->s_stripe, sbi->s_cluster_ratio); sbi->s_stripe = 0; } sbi->s_extent_max_zeroout_kb = 32; /* * set up enough so that it can read an inode */ sb->s_op = &ext4_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; #endif #ifdef CONFIG_FS_VERITY sb->s_vop = &ext4_verityops; #endif #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (ext4_has_feature_quota(sb)) sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid)); super_set_sysfs_name_bdev(sb); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); spin_lock_init(&sbi->s_bdev_wb_lock); ext4_atomic_write_init(sb); ext4_fast_commit_init(sb); sb->s_root = NULL; needs_recovery = (es->s_last_orphan != 0 || ext4_has_feature_orphan_present(sb) || ext4_has_feature_journal_needs_recovery(sb)); if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto failed_mount3a; } err = -EINVAL; /* * The first inode we look at is the journal inode. Don't try * root first: it may be modified in the journal! */ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); goto failed_mount3a; } else { const char *journal_option; /* Nojournal mode, all journal mount options are illegal */ journal_option = ext4_has_journal_option(sb); if (journal_option != NULL) { ext4_msg(sb, KERN_ERR, "can't mount with %s, fs mounted w/o journal", journal_option); goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); clear_opt2(sb, JOURNAL_FAST_COMMIT); sbi->s_journal = NULL; needs_recovery = 0; } if (!test_opt(sb, NO_MBCACHE)) { sbi->s_ea_block_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_block_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); err = -EINVAL; goto failed_mount_wq; } if (ext4_has_feature_ea_inode(sb)) { sbi->s_ea_inode_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_inode_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_inode_cache"); err = -EINVAL; goto failed_mount_wq; } } } /* * Get the # of file system overhead blocks from the * superblock if present. */ sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); /* ignore the precalculated value if it is ridiculous */ if (sbi->s_overhead > ext4_blocks_count(es)) sbi->s_overhead = 0; /* * If the bigalloc feature is not enabled recalculating the * overhead doesn't take long, so we might as well just redo * it to make sure we are using the correct value. */ if (!ext4_has_feature_bigalloc(sb)) sbi->s_overhead = 0; if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; } /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ EXT4_SB(sb)->rsv_conversion_wq = alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->rsv_conversion_wq) { printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); err = -ENOMEM; goto failed_mount4; } /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. */ root = ext4_iget(sb, EXT4_ROOT_INO, EXT4_IGET_SPECIAL); if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); err = PTR_ERR(root); root = NULL; goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); iput(root); err = -EFSCORRUPTED; goto failed_mount4; } generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); err = -ENOMEM; goto failed_mount4; } err = ext4_setup_super(sb, es, sb_rdonly(sb)); if (err == -EROFS) { sb->s_flags |= SB_RDONLY; } else if (err) goto failed_mount4a; ext4_set_resv_clusters(sb); if (test_opt(sb, BLOCK_VALIDITY)) { err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " "zone (%d)", err); goto failed_mount4a; } } ext4_fc_replay_cleanup(sb); ext4_ext_init(sb); /* * Enable optimize_scan if number of groups is > threshold. This can be * turned off by passing "mb_optimize_scan=0". This can also be * turned on forcefully by passing "mb_optimize_scan=1". */ if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) { if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD) set_opt2(sb, MB_OPTIMIZE_SCAN); else clear_opt2(sb, MB_OPTIMIZE_SCAN); } err = ext4_mb_init(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", err); goto failed_mount5; } /* * We can only set up the journal commit callback once * mballoc is initialized */ if (sbi->s_journal) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; err = ext4_percpu_param_init(sbi); if (err) goto failed_mount6; if (ext4_has_feature_flex_bg(sb)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); err = -ENOMEM; goto failed_mount6; } err = ext4_register_li_request(sb, first_not_zeroed); if (err) goto failed_mount6; err = ext4_init_orphan_info(sb); if (err) goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) goto failed_mount8; } #endif /* CONFIG_QUOTA */ /* * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; /* * Update the checksum after updating free space/inode counters and * ext4_orphan_cleanup. Otherwise the superblock can have an incorrect * checksum in the buffer cache until it is written out and * e2fsprogs programs trying to open a file system immediately * after it is mounted can fail. */ ext4_superblock_csum_set(sb); if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) goto failed_mount9; } if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) { ext4_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); clear_opt(sb, DISCARD); } if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); /* Register sysfs after all initializations are complete. */ err = ext4_register_sysfs(sb); if (err) goto failed_mount9; return 0; failed_mount9: ext4_quotas_off(sb, EXT4_MAXQUOTAS); failed_mount8: __maybe_unused ext4_release_orphan_info(sb); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); ext4_flex_groups_free(sbi); ext4_percpu_param_destroy(sbi); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); failed_mount4a: dput(sb->s_root); sb->s_root = NULL; failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { ext4_journal_destroy(sbi, sbi->s_journal); } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: /* flush s_sb_upd_work before sbi destroy */ flush_work(&sbi->s_sb_upd_work); ext4_stop_mmpd(sbi); timer_delete_sync(&sbi->s_err_report); ext4_group_desc_free(sbi); failed_mount: #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif #ifdef CONFIG_QUOTA for (unsigned int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); if (sbi->s_journal_bdev_file) { invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; return err; } static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi; const char *descr; int ret; sbi = ext4_alloc_sbi(sb); if (!sbi) return -ENOMEM; fc->s_fs_info = sbi; /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); sbi->s_sb_block = 1; /* Default super block location */ if (ctx->spec & EXT4_SPEC_s_sb_block) sbi->s_sb_block = ctx->s_sb_block; ret = __ext4_fill_super(fc, sb); if (ret < 0) goto free_sbi; if (sbi->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) descr = " journalled data mode"; else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) descr = " ordered data mode"; else descr = " writeback data mode"; } else descr = "out journal"; if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. " "Quota mode: %s.", &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ ext4_update_overhead(sb, false); return 0; free_sbi: ext4_free_sbi(sbi); fc->s_fs_info = NULL; return ret; } static int ext4_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, ext4_fill_super); } /* * Setup any per-fs journal parameters now. We'll do this both on * initial mount, once the journal has been initialised but before we've * done any recovery; and again on any subsequent remount. */ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) { struct ext4_sb_info *sbi = EXT4_SB(sb); journal->j_commit_interval = sbi->s_commit_interval; journal->j_min_batch_time = sbi->s_min_batch_time; journal->j_max_batch_time = sbi->s_max_batch_time; ext4_fc_init(sb, journal); write_lock(&journal->j_state_lock); if (test_opt(sb, BARRIER)) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; /* * Always enable journal cycle record option, letting the journal * records log transactions continuously between each mount. */ journal->j_flags |= JBD2_CYCLE_RECORD; write_unlock(&journal->j_state_lock); } static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; /* * Test for the existence of a valid inode on disk. Bad things * happen if we iget() an unused inode, as the subsequent iput() * will try to delete it. */ journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); return ERR_CAST(journal_inode); } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); ext4_msg(sb, KERN_ERR, "journal inode is deleted"); return ERR_PTR(-EFSCORRUPTED); } if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return ERR_PTR(-EFSCORRUPTED); } ext4_debug("Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); return journal_inode; } static int ext4_journal_bmap(journal_t *journal, sector_t *block) { struct ext4_map_blocks map; int ret; if (journal->j_inode == NULL) return 0; map.m_lblk = *block; map.m_len = 1; ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); if (ret <= 0) { ext4_msg(journal->j_inode->i_sb, KERN_CRIT, "journal bmap failed: block %llu ret %d\n", *block, ret); jbd2_journal_abort(journal, ret ? ret : -EIO); return ret; } *block = map.m_pblk; return 0; } static journal_t *ext4_open_inode_journal(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (IS_ERR(journal_inode)) return ERR_CAST(journal_inode); journal = jbd2_journal_init_inode(journal_inode); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); return ERR_CAST(journal); } journal->j_private = sb; journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } static struct file *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; struct file *bdev_file; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; struct ext4_super_block *es; int errno; bdev_file = bdev_file_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, sb, &fs_holder_ops); if (IS_ERR(bdev_file)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file)); return bdev_file; } bdev = file_bdev(bdev_file); blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { ext4_msg(sb, KERN_ERR, "blocksize too small for journal device"); errno = -EINVAL; goto out_bdev; } sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev_file, blocksize); bh = __bread(bdev, sb_block, blocksize); if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " "external journal"); errno = -EINVAL; goto out_bdev; } es = (struct ext4_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { ext4_msg(sb, KERN_ERR, "external journal has bad superblock"); errno = -EFSCORRUPTED; goto out_bh; } if ((le32_to_cpu(es->s_feature_ro_compat) & EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "external journal has corrupt superblock"); errno = -EFSCORRUPTED; goto out_bh; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { ext4_msg(sb, KERN_ERR, "journal UUID does not match"); errno = -EFSCORRUPTED; goto out_bh; } *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); return bdev_file; out_bh: brelse(bh); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static journal_t *ext4_open_dev_journal(struct super_block *sb, dev_t j_dev) { journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; struct file *bdev_file; int errno = 0; bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); if (IS_ERR(bdev_file)) return ERR_CAST(bdev_file); journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); errno = PTR_ERR(journal); goto out_bdev; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { ext4_msg(sb, KERN_ERR, "External journal has more than one " "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); errno = -EINVAL; goto out_journal; } journal->j_private = sb; EXT4_SB(sb)->s_journal_bdev_file = bdev_file; ext4_init_journal_params(sb, journal); return journal; out_journal: ext4_journal_destroy(EXT4_SB(sb), journal); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static int ext4_load_journal(struct super_block *sb, struct ext4_super_block *es, unsigned long journal_devnum) { journal_t *journal; unsigned int journal_inum = le32_to_cpu(es->s_journal_inum); dev_t journal_dev; int err = 0; int really_read_only; int journal_dev_ro; if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { ext4_msg(sb, KERN_INFO, "external journal device major/minor " "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); if (journal_inum && journal_dev) { ext4_msg(sb, KERN_ERR, "filesystem has both journal inode and journal device!"); return -EINVAL; } if (journal_inum) { journal = ext4_open_inode_journal(sb, journal_inum); if (IS_ERR(journal)) return PTR_ERR(journal); } else { journal = ext4_open_dev_journal(sb, journal_dev); if (IS_ERR(journal)) return PTR_ERR(journal); } journal_dev_ro = bdev_read_only(journal->j_dev); really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; if (journal_dev_ro && !sb_rdonly(sb)) { ext4_msg(sb, KERN_ERR, "journal device read-only, try mounting with '-o ro'"); err = -EROFS; goto err_out; } /* * Are we loading a blank journal or performing recovery after a * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ if (ext4_has_feature_journal_needs_recovery(sb)) { if (sb_rdonly(sb)) { ext4_msg(sb, KERN_INFO, "INFO: recovery " "required on readonly filesystem"); if (really_read_only) { ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); err = -EROFS; goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!ext4_has_feature_journal_needs_recovery(sb)) err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); __le16 orig_state; bool changed = false; if (save) memcpy(save, ((char *) es) + EXT4_S_ERR_START, EXT4_S_ERR_LEN); err = jbd2_journal_load(journal); if (save && memcmp(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN)) { memcpy(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN); changed = true; } kfree(save); orig_state = es->s_state; es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS); if (orig_state != es->s_state) changed = true; /* Write out restored error information to the superblock */ if (changed && !really_read_only) { int err2; err2 = ext4_commit_super(sb); err = err ? : err2; } } if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); goto err_out; } EXT4_SB(sb)->s_journal = journal; err = ext4_clear_journal_err(sb, es); if (err) { ext4_journal_destroy(EXT4_SB(sb), journal); return err; } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); ext4_commit_super(sb); } if (!really_read_only && journal_inum && journal_inum != le32_to_cpu(es->s_journal_inum)) { es->s_journal_inum = cpu_to_le32(journal_inum); ext4_commit_super(sb); } return 0; err_out: ext4_journal_destroy(EXT4_SB(sb), journal); return err; } /* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct buffer_head *sbh = sbi->s_sbh; lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system * read/only but we need to replay the journal; at that point, * for people who are east of GMT and who make their clock * tick in localtime for Windows bug-for-bug compatibility, * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ if (!sb_rdonly(sb)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(sbi, percpu_counter_sum_positive( &sbi->s_freeclusters_counter))); if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { es->s_state |= cpu_to_le16(EXT4_ERROR_FS); if (!es->s_first_error_time && !es->s_first_error_time_hi) { __ext4_update_tstamp(&es->s_first_error_time, &es->s_first_error_time_hi, sbi->s_first_error_time); strtomem_pad(es->s_first_error_func, sbi->s_first_error_func, 0); es->s_first_error_line = cpu_to_le32(sbi->s_first_error_line); es->s_first_error_ino = cpu_to_le32(sbi->s_first_error_ino); es->s_first_error_block = cpu_to_le64(sbi->s_first_error_block); es->s_first_error_errcode = ext4_errno_to_code(sbi->s_first_error_code); } __ext4_update_tstamp(&es->s_last_error_time, &es->s_last_error_time_hi, sbi->s_last_error_time); strtomem_pad(es->s_last_error_func, sbi->s_last_error_func, 0); es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line); es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino); es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block); es->s_last_error_errcode = ext4_errno_to_code(sbi->s_last_error_code); /* * Start the daily error reporting function if it hasn't been * started already */ if (!es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); le32_add_cpu(&es->s_error_count, sbi->s_add_error_count); sbi->s_add_error_count = 0; } spin_unlock(&sbi->s_error_lock); ext4_superblock_csum_set(sb); unlock_buffer(sbh); } static int ext4_commit_super(struct super_block *sb) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; if (!sbh) return -EINVAL; ext4_update_super(sb); lock_buffer(sbh); /* Buffer got discarded which means block device got invalidated */ if (!buffer_mapped(sbh)) { unlock_buffer(sbh); return -EIO; } if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the * USB device was yanked out. Or it could happen to * be a transient write error and maybe the block will * be remapped. Nothing we can do but to retry the * write and hope for the best. */ ext4_msg(sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } get_bh(sbh); /* Clear potential dirty bit if it was journalled update */ clear_buffer_dirty(sbh); sbh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh); wait_on_buffer(sbh); if (buffer_write_io_error(sbh)) { ext4_msg(sb, KERN_ERR, "I/O error while writing " "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); return -EIO; } return 0; } /* * Have we just finished recovery? If so, and if we are mounting (or * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es) { int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { if (journal != NULL) { ext4_error(sb, "Journal got removed while the fs was " "mounted!"); return -EFSCORRUPTED; } return 0; } jbd2_journal_lock_updates(journal); err = jbd2_journal_flush(journal, 0); if (err < 0) goto out; if (sb_rdonly(sb) && (ext4_has_feature_journal_needs_recovery(sb) || ext4_has_feature_orphan_present(sb))) { if (!ext4_orphan_file_empty(sb)) { ext4_error(sb, "Orphan file not empty on read-only fs."); err = -EFSCORRUPTED; goto out; } ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); return err; } /* * If we are mounting (or read-write remounting) a filesystem whose journal * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; if (!ext4_has_feature_journal(sb)) { ext4_error(sb, "Journal got removed while the fs was mounted!"); return -EFSCORRUPTED; } journal = EXT4_SB(sb)->s_journal; /* * Now check for any error status which may have been recorded in the * journal by a prior ext4_error() or ext4_abort() */ j_errno = jbd2_journal_errno(journal); if (j_errno) { char nbuf[16]; errstr = ext4_decode_error(sb, j_errno, nbuf); ext4_warning(sb, "Filesystem error recorded " "from previous mount: %s", errstr); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); j_errno = ext4_commit_super(sb); if (j_errno) return j_errno; ext4_warning(sb, "Marked fs in need of filesystem check."); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } return 0; } /* * Force the running and committing transactions to commit, * and wait on the commit. */ int ext4_force_commit(struct super_block *sb) { return ext4_journal_force_commit(EXT4_SB(sb)->s_journal); } static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); ret = ext4_emergency_state(sb); if (unlikely(ret)) return ret; trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots */ dquot_writeback_dquots(sb, -1); /* * Data writeback is possible w/o journal transaction, so barrier must * being sent at the end of the function. But we can skip it if * transaction_commit will do it for us. */ if (sbi->s_journal) { target = jbd2_get_latest_transaction(sbi->s_journal); if (wait && sbi->s_journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(sbi->s_journal, target)) needs_barrier = true; if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) ret = jbd2_log_wait_commit(sbi->s_journal, target); } } else if (wait && test_opt(sb, BARRIER)) needs_barrier = true; if (needs_barrier) { int err; err = blkdev_issue_flush(sb->s_bdev); if (!ret) ret = err; } return ret; } /* * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean * state independently. It relies on upper layer to stop all data & metadata * modifications. */ static int ext4_freeze(struct super_block *sb) { int error = 0; journal_t *journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ jbd2_journal_lock_updates(journal); /* * Don't clear the needs_recovery flag if we failed to * flush the journal. */ error = jbd2_journal_flush(journal, 0); if (error < 0) goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ ext4_clear_feature_journal_needs_recovery(sb); if (ext4_orphan_file_empty(sb)) ext4_clear_feature_orphan_present(sb); } error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(journal); return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ static int ext4_unfreeze(struct super_block *sb) { if (ext4_emergency_state(sb)) return 0; if (EXT4_SB(sb)->s_journal) { /* Reset the needs_recovery flag before the fs is unlocked. */ ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } ext4_commit_super(sb); return 0; } /* * Structure to save mount options for ext4_remount's benefit */ struct ext4_mount_options { unsigned long s_mount_opt; unsigned long s_mount_opt2; kuid_t s_resuid; kgid_t s_resgid; unsigned long s_commit_interval; u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA int s_jquota_fmt; char *s_qf_names[EXT4_MAXQUOTAS]; #endif }; static int __ext4_remount(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long old_sb_flags; struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif /* Store the original options */ old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_mount_opt2 = sbi->s_mount_opt2; old_opts.s_resuid = sbi->s_resuid; old_opts.s_resgid = sbi->s_resgid; old_opts.s_commit_interval = sbi->s_commit_interval; old_opts.s_min_batch_time = sbi->s_min_batch_time; old_opts.s_max_batch_time = sbi->s_max_batch_time; #ifdef CONFIG_QUOTA old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { char *qf_name = get_qf_name(sb, sbi, i); old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); return -ENOMEM; } } else old_opts.s_qf_names[i] = NULL; #endif if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) { if (sbi->s_journal && sbi->s_journal->j_task->io_context) ctx->journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; else ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; } if ((ctx->spec & EXT4_SPEC_s_stripe) && ext4_is_stripe_incompatible(sb, ctx->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", ctx->s_stripe, sbi->s_cluster_ratio); ctx->s_stripe = 0; } /* * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause * two calls to ext4_should_dioread_nolock() to return inconsistent * values, triggering WARN_ON in ext4_add_complete_io(). we grab * here s_writepages_rwsem to avoid race between writepages ops and * remount. */ alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " "during remount not supported; ignoring"); sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); err = -EINVAL; goto restore_opts; } if (test_opt(sb, DIOREAD_NOLOCK)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dioread_nolock"); err = -EINVAL; goto restore_opts; } } else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) { if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); err = -EINVAL; goto restore_opts; } } if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) { ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount"); err = -EINVAL; goto restore_opts; } if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) && !test_opt(sb, DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount"); err = -EINVAL; goto restore_opts; } sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); es = sbi->s_es; if (sbi->s_journal) { ext4_init_journal_params(sb, sbi->s_journal); set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); } /* Flush outstanding errors before changing fs state */ flush_work(&sbi->s_sb_upd_work); if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { if (ext4_emergency_state(sb)) { err = -EROFS; goto restore_opts; } if (fc->sb_flags & SB_RDONLY) { err = sync_filesystem(sb); if (err < 0) goto restore_opts; err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; /* * First of all, the unconditional stuff we have to do * to disable replay of the journal when we next remount */ sb->s_flags |= SB_RDONLY; /* * OK, test if we are remounting a valid rw partition * readonly, and if so set the rdonly flag and then * mark the partition as valid again. */ if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) && (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); if (sbi->s_journal) { /* * We let remount-ro finish even if marking fs * as clean failed... */ ext4_mark_recovery_complete(sb, es); } } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || !ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } /* * Make sure the group descriptor checksums * are sane. If they aren't, refuse to remount r/w. */ for (g = 0; g < sbi->s_groups_count; g++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, g, NULL); if (!ext4_group_desc_csum_verify(sb, g, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)), le16_to_cpu(gdp->bg_checksum)); err = -EFSBADCRC; goto restore_opts; } } /* * If we have an unprocessed orphan list hanging * around from a previously readonly bdev mount, * require a full umount/remount for now. */ if (es->s_last_orphan || !ext4_orphan_file_empty(sb)) { ext4_msg(sb, KERN_WARNING, "Couldn't " "remount RDWR because of unprocessed " "orphan inode list. Please " "umount/remount instead"); err = -EINVAL; goto restore_opts; } /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ if (sbi->s_journal) { err = ext4_clear_journal_err(sb, es); if (err) goto restore_opts; } sbi->s_mount_state = (le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY); err = ext4_setup_super(sb, es, 0); if (err) goto restore_opts; sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA enable_quota = 1; #endif } } /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. */ if (test_opt(sb, BLOCK_VALIDITY) && !sbi->s_system_blks) { err = ext4_setup_system_zone(sb); if (err) goto restore_opts; } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); else if (ext4_has_feature_quota(sb)) { err = ext4_enable_quotas(sb); if (err) goto restore_opts; } } /* Release old quota file names */ for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); /* * Reinitialize lazy itable initialization thread based on * current settings */ if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) ext4_unregister_li_request(sb); else { ext4_group_t first_not_zeroed; first_not_zeroed = ext4_has_uninit_itable(sb); ext4_register_li_request(sb, first_not_zeroed); } if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); /* * Handle aborting the filesystem as the last thing during remount to * avoid obsure errors during remount when some option changes fail to * apply due to shutdown filesystem. */ if (test_opt2(sb, ABORT)) ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); return 0; restore_opts: /* * If there was a failing r/w to ro transition, we may need to * re-enable quota */ if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; sbi->s_resuid = old_opts.s_resuid; sbi->s_resgid = old_opts.s_resgid; sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { to_free[i] = get_qf_name(sb, sbi, i); rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } synchronize_rcu(); for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(to_free[i]); #endif if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); return err; } static int ext4_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int ret; bool old_ro = sb_rdonly(sb); fc->s_fs_info = EXT4_SB(sb); ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) return ret; ret = __ext4_remount(fc, sb); if (ret < 0) return ret; ext4_msg(sb, KERN_INFO, "re-mounted %pU%s.", &sb->s_uuid, (old_ro != sb_rdonly(sb)) ? (sb_rdonly(sb) ? " ro" : " r/w") : ""); return 0; } #ifdef CONFIG_QUOTA static int ext4_statfs_project(struct super_block *sb, kprojid_t projid, struct kstatfs *buf) { struct kqid qid; struct dquot *dquot; u64 limit; u64 curblock; qid = make_kqid_projid(projid); dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; if (limit) { uint64_t remaining = 0; curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; if (limit > curblock) remaining = limit - curblock; buf->f_blocks = min(buf->f_blocks, limit); buf->f_bfree = min(buf->f_bfree, remaining); buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); if (limit) { uint64_t remaining = 0; if (limit > dquot->dq_dqb.dqb_curinodes) remaining = limit - dquot->dq_dqb.dqb_curinodes; buf->f_files = min(buf->f_files, limit); buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } #endif static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_fsblk_t overhead = 0, resv_blocks; s64 bfree; resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters)); if (!test_opt(sb, MINIX_DF)) overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); buf->f_bavail = buf->f_bfree - (ext4_r_blocks_count(es) + resv_blocks); if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); buf->f_namelen = EXT4_NAME_LEN; buf->f_fsid = uuid_to_fsid(es->s_uuid); #ifdef CONFIG_QUOTA if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf); #endif return 0; } #ifdef CONFIG_QUOTA /* * Helper functions so that transaction is started before we acquire dqio_sem * to keep correct lock ordering of transaction > dqio_sem */ static inline struct inode *dquot_to_inode(struct dquot *dquot) { return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; } static int ext4_write_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; struct inode *inode; inode = dquot_to_inode(dquot); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to commit dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_acquire_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to acquire dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_release_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; bool freeze_protected = false; /* * Trying to sb_start_intwrite() in a running transaction * can result in a deadlock. Further, running transactions * are already protected from freezing. */ if (!ext4_journal_current_handle()) { sb_start_intwrite(dquot->dq_sb); freeze_protected = true; } handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); if (freeze_protected) sb_end_intwrite(dquot->dq_sb); return PTR_ERR(handle); } ret = dquot_release(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to release dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; if (freeze_protected) sb_end_intwrite(dquot->dq_sb); return ret; } static int ext4_mark_dquot_dirty(struct dquot *dquot) { struct super_block *sb = dquot->dq_sb; if (ext4_is_quota_journalled(sb)) { dquot_mark_dquot_dirty(dquot); return ext4_write_dquot(dquot); } else { return dquot_mark_dquot_dirty(dquot); } } static int ext4_write_info(struct super_block *sb, int type) { int ret, err; handle_t *handle; /* Data block + inode block */ handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static void lockdep_set_quota_inode(struct inode *inode, int subclass) { struct ext4_inode_info *ei = EXT4_I(inode); /* The first argument of lockdep_set_subclass has to be * *exactly* the same as the argument to init_rwsem() --- in * this case, in init_once() --- or lockdep gets unhappy * because the name of the lock is set using the * stringification of the argument to init_rwsem(). */ (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, subclass); } /* * Standard function to be called on quota_on */ static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { int err; if (!test_opt(sb, QUOTA)) return -EINVAL; /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) return -EXDEV; /* Quota already enabled for this file? */ if (IS_NOQUOTA(d_inode(path->dentry))) return -EBUSY; /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ if (path->dentry->d_parent != sb->s_root) ext4_msg(sb, KERN_WARNING, "Quota file not on filesystem root. " "Journaled quota will not work"); sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY; } else { /* * Clear the flag just in case mount options changed since * last time. */ sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY; } lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); err = dquot_quota_on(sb, type, format_id, path); if (!err) { struct inode *inode = d_inode(path->dentry); handle_t *handle; /* * Set inode flags to prevent userspace from messing with quota * files. If this fails, we return success anyway since quotas * are already enabled and this is not a hard failure. */ inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) goto unlock_inode; EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL; inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, S_NOATIME | S_IMMUTABLE); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); if (err) dquot_quota_off(sb, type); } if (err) lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_NORMAL); return err; } static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) { switch (type) { case USRQUOTA: return qf_inum == EXT4_USR_QUOTA_INO; case GRPQUOTA: return qf_inum == EXT4_GRP_QUOTA_INO; case PRJQUOTA: return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; default: BUG(); } } static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { int err; struct inode *qf_inode; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; BUG_ON(!ext4_has_feature_quota(sb)); if (!qf_inums[type]) return -EPERM; if (!ext4_check_quota_inum(type, qf_inums[type])) { ext4_error(sb, "Bad quota inum: %lu, type: %d", qf_inums[type], type); return -EUCLEAN; } qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { ext4_error(sb, "Bad quota inode: %lu, type: %d", qf_inums[type], type); return PTR_ERR(qf_inode); } /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_load_quota_inode(qf_inode, type, format_id, flags); if (err) lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); iput(qf_inode); return err; } /* Enable usage tracking for all quota types. */ int ext4_enable_quotas(struct super_block *sb) { int type, err = 0; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; bool quota_mopt[EXT4_MAXQUOTAS] = { test_opt(sb, USRQUOTA), test_opt(sb, GRPQUOTA), test_opt(sb, PRJQUOTA), }; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; for (type = 0; type < EXT4_MAXQUOTAS; type++) { if (qf_inums[type]) { err = ext4_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d, ino=%lu). " "Please run e2fsck to fix.", type, err, qf_inums[type]); ext4_quotas_off(sb, type); return err; } } } return 0; } static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; handle_t *handle; int err; /* Force all delayed allocation blocks to be allocated. * Caller already holds s_umount sem */ if (test_opt(sb, DELALLOC)) sync_filesystem(sb); if (!inode || !igrab(inode)) goto out; err = dquot_quota_off(sb, type); if (err || ext4_has_feature_quota(sb)) goto out_put; /* * When the filesystem was remounted read-only first, we cannot cleanup * inode flags here. Bad luck but people should be using QUOTA feature * these days anyway. */ if (sb_rdonly(sb)) goto out_put; inode_lock(inode); /* * Update modification times of quota files when userspace can * start looking at them. If we fail, we return success anyway since * this is not a hard failure and quotas are already disabled. */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out_unlock; } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: inode_unlock(inode); out_put: lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL); iput(inode); return err; out: return dquot_quota_off(sb, type); } /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) * we don't have to be afraid of races */ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int offset = off & (sb->s_blocksize - 1); int tocopy; size_t toread; struct buffer_head *bh; loff_t i_size = i_size_read(inode); if (off > i_size) return 0; if (off+len > i_size) len = i_size-off; toread = len; while (toread > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); bh = ext4_bread(NULL, inode, blk, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) /* A hole? */ memset(data, 0, tocopy); else memcpy(data, bh->b_data+offset, tocopy); brelse(bh); offset = 0; toread -= tocopy; data += tocopy; blk++; } return len; } /* Write to quotafile (we know the transaction is already started and has * enough credits) */ static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int err = 0, err2 = 0, offset = off & (sb->s_blocksize - 1); int retries = 0; struct buffer_head *bh; handle_t *handle = journal_current_handle(); if (!handle) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); return -EIO; } /* * Since we account only one data block in transaction credits, * then it is impossible to cross a block boundary. */ if (sb->s_blocksize - offset < len) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because not block aligned", (unsigned long long)off, (unsigned long long)len); return -EIO; } do { bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) goto out; BUFFER_TRACE(bh, "get write access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) { brelse(bh); return err; } lock_buffer(bh); memcpy(bh->b_data+offset, data, len); flush_dcache_folio(bh->b_folio); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; } return err ? err : len; } #endif #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static inline void register_as_ext2(void) { int err = register_filesystem(&ext2_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext2 (%d)\n", err); } static inline void unregister_as_ext2(void) { unregister_filesystem(&ext2_fs_type); } static inline int ext2_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext2_incompat_features(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext2_ro_compat_features(sb)) return 0; return 1; } #else static inline void register_as_ext2(void) { } static inline void unregister_as_ext2(void) { } static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; } #endif static inline void register_as_ext3(void) { int err = register_filesystem(&ext3_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext3 (%d)\n", err); } static inline void unregister_as_ext3(void) { unregister_filesystem(&ext3_fs_type); } static inline int ext3_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext3_incompat_features(sb)) return 0; if (!ext4_has_feature_journal(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext3_ro_compat_features(sb)) return 0; return 1; } static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL; kill_block_super(sb); if (bdev_file) bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { .owner = THIS_MODULE, .name = "ext4", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, }; MODULE_ALIAS_FS("ext4"); static int __init ext4_init_fs(void) { int err; ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; /* Build-time check for flags consistency */ ext4_check_flag_values(); err = ext4_init_es(); if (err) return err; err = ext4_init_pending(); if (err) goto out7; err = ext4_init_post_read_processing(); if (err) goto out6; err = ext4_init_pageio(); if (err) goto out5; err = ext4_init_system_zone(); if (err) goto out4; err = ext4_init_sysfs(); if (err) goto out3; err = ext4_init_mballoc(); if (err) goto out2; err = init_inodecache(); if (err) goto out1; err = ext4_fc_init_dentry_cache(); if (err) goto out05; register_as_ext3(); register_as_ext2(); err = register_filesystem(&ext4_fs_type); if (err) goto out; return 0; out: unregister_as_ext2(); unregister_as_ext3(); ext4_fc_destroy_dentry_cache(); out05: destroy_inodecache(); out1: ext4_exit_mballoc(); out2: ext4_exit_sysfs(); out3: ext4_exit_system_zone(); out4: ext4_exit_pageio(); out5: ext4_exit_post_read_processing(); out6: ext4_exit_pending(); out7: ext4_exit_es(); return err; } static void __exit ext4_exit_fs(void) { ext4_destroy_lazyinit_thread(); unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); ext4_fc_destroy_dentry_cache(); destroy_inodecache(); ext4_exit_mballoc(); ext4_exit_sysfs(); ext4_exit_system_zone(); ext4_exit_pageio(); ext4_exit_post_read_processing(); ext4_exit_es(); ext4_exit_pending(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) |
| 251 252 1294 1058 252 1002 1080 127 78 78 78 78 14 3 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/namespace.c * Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc. */ #include <linux/ipc.h> #include <linux/msg.h> #include <linux/ipc_namespace.h> #include <linux/rcupdate.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/sched/task.h> #include "util.h" /* * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount. */ static void free_ipc(struct work_struct *unused); static DECLARE_WORK(free_ipc_work, free_ipc); static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES); } static void dec_ipc_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES); } static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, struct ipc_namespace *old_ns) { struct ipc_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; again: ucounts = inc_ipc_namespaces(user_ns); if (!ucounts) { /* * IPC namespaces are freed asynchronously, by free_ipc_work. * If frees were pending, flush_work will wait, and * return true. Fail the allocation if no frees are pending. */ if (flush_work(&free_ipc_work)) goto again; goto fail; } err = -ENOMEM; ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT); if (ns == NULL) goto fail_dec; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free; ns->ns.ops = &ipcns_operations; refcount_set(&ns->ns.count, 1); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; err = mq_init_ns(ns); if (err) goto fail_put; err = -ENOMEM; if (!setup_mq_sysctls(ns)) goto fail_put; if (!setup_ipc_sysctls(ns)) goto fail_mq; err = msg_init_ns(ns); if (err) goto fail_ipc; sem_init_ns(ns); shm_init_ns(ns); return ns; fail_ipc: retire_ipc_sysctls(ns); fail_mq: retire_mq_sysctls(ns); fail_put: put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); fail_free: kfree(ns); fail_dec: dec_ipc_namespaces(ucounts); fail: return ERR_PTR(err); } struct ipc_namespace *copy_ipcs(unsigned long flags, struct user_namespace *user_ns, struct ipc_namespace *ns) { if (!(flags & CLONE_NEWIPC)) return get_ipc_ns(ns); return create_ipc_ns(user_ns, ns); } /* * free_ipcs - free all ipcs of one type * @ns: the namespace to remove the ipcs from * @ids: the table of ipcs to free * @free: the function called to free each individual ipc * * Called for each kind of ipc when an ipc_namespace exits. */ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)) { struct kern_ipc_perm *perm; int next_id; int total, in_use; down_write(&ids->rwsem); in_use = ids->in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { perm = idr_find(&ids->ipcs_idr, next_id); if (perm == NULL) continue; rcu_read_lock(); ipc_lock_object(perm); free(ns, perm); total++; } up_write(&ids->rwsem); } static void free_ipc_ns(struct ipc_namespace *ns) { /* * Caller needs to wait for an RCU grace period to have passed * after making the mount point inaccessible to new accesses. */ mntput(ns->mq_mnt); sem_exit_ns(ns); msg_exit_ns(ns); shm_exit_ns(ns); retire_mq_sysctls(ns); retire_ipc_sysctls(ns); dec_ipc_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); } static LLIST_HEAD(free_ipc_list); static void free_ipc(struct work_struct *unused) { struct llist_node *node = llist_del_all(&free_ipc_list); struct ipc_namespace *n, *t; llist_for_each_entry_safe(n, t, node, mnt_llist) mnt_make_shortterm(n->mq_mnt); /* Wait for any last users to have gone away. */ synchronize_rcu(); llist_for_each_entry_safe(n, t, node, mnt_llist) free_ipc_ns(n); } /* * put_ipc_ns - drop a reference to an ipc namespace. * @ns: the namespace to put * * If this is the last task in the namespace exiting, and * it is dropping the refcount to 0, then it can race with * a task in another ipc namespace but in a mounts namespace * which has this ipcns's mqueuefs mounted, doing some action * with one of the mqueuefs files. That can raise the refcount. * So dropping the refcount, and raising the refcount when * accessing it through the VFS, are protected with mq_lock. * * (Clearly, a task raising the refcount on its own ipc_ns * needn't take mq_lock since it can't race with the last task * in the ipcns exiting). */ void put_ipc_ns(struct ipc_namespace *ns) { if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) { mq_clear_sbinfo(ns); spin_unlock(&mq_lock); if (llist_add(&ns->mnt_llist, &free_ipc_list)) schedule_work(&free_ipc_work); } } static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) { return container_of(ns, struct ipc_namespace, ns); } static struct ns_common *ipcns_get(struct task_struct *task) { struct ipc_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) ns = get_ipc_ns(nsproxy->ipc_ns); task_unlock(task); return ns ? &ns->ns : NULL; } static void ipcns_put(struct ns_common *ns) { return put_ipc_ns(to_ipc_ns(ns)); } static int ipcns_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct ipc_namespace *ns = to_ipc_ns(new); if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; put_ipc_ns(nsproxy->ipc_ns); nsproxy->ipc_ns = get_ipc_ns(ns); return 0; } static struct user_namespace *ipcns_owner(struct ns_common *ns) { return to_ipc_ns(ns)->user_ns; } const struct proc_ns_operations ipcns_operations = { .name = "ipc", .type = CLONE_NEWIPC, .get = ipcns_get, .put = ipcns_put, .install = ipcns_install, .owner = ipcns_owner, }; |
| 23 1 105 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle firewalling core * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> * Bart De Schuymer <bdschuym@pandora.be> * * Lennert dedicates this file to Kerstin Wurdinger. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/in_route.h> #include <linux/inetdevice.h> #include <net/route.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { } static void fake_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { } static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) { return NULL; } static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { return NULL; } static unsigned int fake_mtu(const struct dst_entry *dst) { return dst->dev->mtu; } static struct dst_ops fake_dst_ops = { .family = AF_INET, .update_pmtu = fake_update_pmtu, .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, .mtu = fake_mtu, }; /* * Initialize bogus route table used to keep netfilter happy. * Currently, we fill in the PMTU entry because netfilter * refragmentation needs it, and the rt_flags entry because * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ static const u32 br_dst_default_metrics[RTAX_MAX] = { [RTAX_MTU - 1] = 1500, }; void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } int __init br_nf_core_init(void) { return dst_entries_init(&fake_dst_ops); } void br_nf_core_fini(void) { dst_entries_destroy(&fake_dst_ops); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /** * file phonet.h * * Phonet sockets kernel interface * * Copyright (C) 2008 Nokia Corporation. All rights reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * version 2 as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA * 02110-1301 USA */ #ifndef _UAPILINUX_PHONET_H #define _UAPILINUX_PHONET_H #include <linux/types.h> #include <linux/socket.h> /* Automatic protocol selection */ #define PN_PROTO_TRANSPORT 0 /* Phonet datagram socket */ #define PN_PROTO_PHONET 1 /* Phonet pipe */ #define PN_PROTO_PIPE 2 #define PHONET_NPROTO 3 /* Socket options for SOL_PNPIPE level */ #define PNPIPE_ENCAP 1 #define PNPIPE_IFINDEX 2 #define PNPIPE_HANDLE 3 #define PNPIPE_INITSTATE 4 #define PNADDR_ANY 0 #define PNADDR_BROADCAST 0xFC #define PNPORT_RESOURCE_ROUTING 0 /* Values for PNPIPE_ENCAP option */ #define PNPIPE_ENCAP_NONE 0 #define PNPIPE_ENCAP_IP 1 /* ioctls */ #define SIOCPNGETOBJECT (SIOCPROTOPRIVATE + 0) #define SIOCPNENABLEPIPE (SIOCPROTOPRIVATE + 13) #define SIOCPNADDRESOURCE (SIOCPROTOPRIVATE + 14) #define SIOCPNDELRESOURCE (SIOCPROTOPRIVATE + 15) /* Phonet protocol header */ struct phonethdr { __u8 pn_rdev; __u8 pn_sdev; __u8 pn_res; __be16 pn_length; __u8 pn_robj; __u8 pn_sobj; } __attribute__((packed)); /* Common Phonet payload header */ struct phonetmsg { __u8 pn_trans_id; /* transaction ID */ __u8 pn_msg_id; /* message type */ union { struct { __u8 pn_submsg_id; /* message subtype */ __u8 pn_data[5]; } base; struct { __u16 pn_e_res_id; /* extended resource ID */ __u8 pn_e_submsg_id; /* message subtype */ __u8 pn_e_data[3]; } ext; } pn_msg_u; }; #define PN_COMMON_MESSAGE 0xF0 #define PN_COMMGR 0x10 #define PN_PREFIX 0xE0 /* resource for extended messages */ #define pn_submsg_id pn_msg_u.base.pn_submsg_id #define pn_e_submsg_id pn_msg_u.ext.pn_e_submsg_id #define pn_e_res_id pn_msg_u.ext.pn_e_res_id #define pn_data pn_msg_u.base.pn_data #define pn_e_data pn_msg_u.ext.pn_e_data /* data for unreachable errors */ #define PN_COMM_SERVICE_NOT_IDENTIFIED_RESP 0x01 #define PN_COMM_ISA_ENTITY_NOT_REACHABLE_RESP 0x14 #define pn_orig_msg_id pn_data[0] #define pn_status pn_data[1] #define pn_e_orig_msg_id pn_e_data[0] #define pn_e_status pn_e_data[1] /* Phonet socket address structure */ struct sockaddr_pn { __kernel_sa_family_t spn_family; __u8 spn_obj; __u8 spn_dev; __u8 spn_resource; __u8 spn_zero[sizeof(struct sockaddr) - sizeof(__kernel_sa_family_t) - 3]; } __attribute__((packed)); /* Well known address */ #define PN_DEV_PC 0x10 static inline __u16 pn_object(__u8 addr, __u16 port) { return (addr << 8) | (port & 0x3ff); } static inline __u8 pn_obj(__u16 handle) { return handle & 0xff; } static inline __u8 pn_dev(__u16 handle) { return handle >> 8; } static inline __u16 pn_port(__u16 handle) { return handle & 0x3ff; } static inline __u8 pn_addr(__u16 handle) { return (handle >> 8) & 0xfc; } static inline void pn_sockaddr_set_addr(struct sockaddr_pn *spn, __u8 addr) { spn->spn_dev &= 0x03; spn->spn_dev |= addr & 0xfc; } static inline void pn_sockaddr_set_port(struct sockaddr_pn *spn, __u16 port) { spn->spn_dev &= 0xfc; spn->spn_dev |= (port >> 8) & 0x03; spn->spn_obj = port & 0xff; } static inline void pn_sockaddr_set_object(struct sockaddr_pn *spn, __u16 handle) { spn->spn_dev = pn_dev(handle); spn->spn_obj = pn_obj(handle); } static inline void pn_sockaddr_set_resource(struct sockaddr_pn *spn, __u8 resource) { spn->spn_resource = resource; } static inline __u8 pn_sockaddr_get_addr(const struct sockaddr_pn *spn) { return spn->spn_dev & 0xfc; } static inline __u16 pn_sockaddr_get_port(const struct sockaddr_pn *spn) { return ((spn->spn_dev & 0x03) << 8) | spn->spn_obj; } static inline __u16 pn_sockaddr_get_object(const struct sockaddr_pn *spn) { return pn_object(spn->spn_dev, spn->spn_obj); } static inline __u8 pn_sockaddr_get_resource(const struct sockaddr_pn *spn) { return spn->spn_resource; } /* Phonet device ioctl requests */ #endif /* _UAPILINUX_PHONET_H */ |
| 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 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 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file holds USB constants and structures that are needed for * USB device APIs. These are used by the USB device model, which is * defined in chapter 9 of the USB 2.0 specification and in the * Wireless USB 1.0 spec (now defunct). Linux has several APIs in C that * need these: * * - the master/host side Linux-USB kernel driver API; * - the "usbfs" user space API; and * - the Linux "gadget" slave/device/peripheral side driver API. * * USB 2.0 adds an additional "On The Go" (OTG) mode, which lets systems * act either as a USB master/host or as a USB slave/device. That means * the master and slave side APIs benefit from working well together. * * Note all descriptors are declared '__attribute__((packed))' so that: * * [a] they never get padded, either internally (USB spec writers * probably handled that) or externally; * * [b] so that accessing bigger-than-a-bytes fields will never * generate bus errors on any platform, even when the location of * its descriptor inside a bundle isn't "naturally aligned", and * * [c] for consistency, removing all doubt even when it appears to * someone that the two other points are non-issues for that * particular descriptor type. */ #ifndef _UAPI__LINUX_USB_CH9_H #define _UAPI__LINUX_USB_CH9_H #include <linux/types.h> /* __u8 etc */ #include <asm/byteorder.h> /* le16_to_cpu */ /*-------------------------------------------------------------------------*/ /* CONTROL REQUEST SUPPORT */ /* * USB directions * * This bit flag is used in endpoint descriptors' bEndpointAddress field. * It's also one of three fields in control requests bRequestType. */ #define USB_DIR_OUT 0 /* to device */ #define USB_DIR_IN 0x80 /* to host */ /* * USB types, the second of three bRequestType fields */ #define USB_TYPE_MASK (0x03 << 5) #define USB_TYPE_STANDARD (0x00 << 5) #define USB_TYPE_CLASS (0x01 << 5) #define USB_TYPE_VENDOR (0x02 << 5) #define USB_TYPE_RESERVED (0x03 << 5) /* * USB recipients, the third of three bRequestType fields */ #define USB_RECIP_MASK 0x1f #define USB_RECIP_DEVICE 0x00 #define USB_RECIP_INTERFACE 0x01 #define USB_RECIP_ENDPOINT 0x02 #define USB_RECIP_OTHER 0x03 /* From Wireless USB 1.0 */ #define USB_RECIP_PORT 0x04 #define USB_RECIP_RPIPE 0x05 /* * Standard requests, for the bRequest field of a SETUP packet. * * These are qualified by the bRequestType field, so that for example * TYPE_CLASS or TYPE_VENDOR specific feature flags could be retrieved * by a GET_STATUS request. */ #define USB_REQ_GET_STATUS 0x00 #define USB_REQ_CLEAR_FEATURE 0x01 #define USB_REQ_SET_FEATURE 0x03 #define USB_REQ_SET_ADDRESS 0x05 #define USB_REQ_GET_DESCRIPTOR 0x06 #define USB_REQ_SET_DESCRIPTOR 0x07 #define USB_REQ_GET_CONFIGURATION 0x08 #define USB_REQ_SET_CONFIGURATION 0x09 #define USB_REQ_GET_INTERFACE 0x0A #define USB_REQ_SET_INTERFACE 0x0B #define USB_REQ_SYNCH_FRAME 0x0C #define USB_REQ_SET_SEL 0x30 #define USB_REQ_SET_ISOCH_DELAY 0x31 #define USB_REQ_SET_ENCRYPTION 0x0D /* Wireless USB */ #define USB_REQ_GET_ENCRYPTION 0x0E #define USB_REQ_RPIPE_ABORT 0x0E #define USB_REQ_SET_HANDSHAKE 0x0F #define USB_REQ_RPIPE_RESET 0x0F #define USB_REQ_GET_HANDSHAKE 0x10 #define USB_REQ_SET_CONNECTION 0x11 #define USB_REQ_SET_SECURITY_DATA 0x12 #define USB_REQ_GET_SECURITY_DATA 0x13 #define USB_REQ_SET_WUSB_DATA 0x14 #define USB_REQ_LOOPBACK_DATA_WRITE 0x15 #define USB_REQ_LOOPBACK_DATA_READ 0x16 #define USB_REQ_SET_INTERFACE_DS 0x17 /* specific requests for USB Power Delivery */ #define USB_REQ_GET_PARTNER_PDO 20 #define USB_REQ_GET_BATTERY_STATUS 21 #define USB_REQ_SET_PDO 22 #define USB_REQ_GET_VDM 23 #define USB_REQ_SEND_VDM 24 /* The Link Power Management (LPM) ECN defines USB_REQ_TEST_AND_SET command, * used by hubs to put ports into a new L1 suspend state, except that it * forgot to define its number ... */ /* * USB feature flags are written using USB_REQ_{CLEAR,SET}_FEATURE, and * are read as a bit array returned by USB_REQ_GET_STATUS. (So there * are at most sixteen features of each type.) Hubs may also support a * new USB_REQ_TEST_AND_SET_FEATURE to put ports into L1 suspend. */ #define USB_DEVICE_SELF_POWERED 0 /* (read only) */ #define USB_DEVICE_REMOTE_WAKEUP 1 /* dev may initiate wakeup */ #define USB_DEVICE_TEST_MODE 2 /* (wired high speed only) */ #define USB_DEVICE_BATTERY 2 /* (wireless) */ #define USB_DEVICE_B_HNP_ENABLE 3 /* (otg) dev may initiate HNP */ #define USB_DEVICE_WUSB_DEVICE 3 /* (wireless)*/ #define USB_DEVICE_A_HNP_SUPPORT 4 /* (otg) RH port supports HNP */ #define USB_DEVICE_A_ALT_HNP_SUPPORT 5 /* (otg) other RH port does */ #define USB_DEVICE_DEBUG_MODE 6 /* (special devices only) */ /* * Test Mode Selectors * See USB 2.0 spec Table 9-7 */ #define USB_TEST_J 1 #define USB_TEST_K 2 #define USB_TEST_SE0_NAK 3 #define USB_TEST_PACKET 4 #define USB_TEST_FORCE_ENABLE 5 /* Status Type */ #define USB_STATUS_TYPE_STANDARD 0 #define USB_STATUS_TYPE_PTM 1 /* * New Feature Selectors as added by USB 3.0 * See USB 3.0 spec Table 9-7 */ #define USB_DEVICE_U1_ENABLE 48 /* dev may initiate U1 transition */ #define USB_DEVICE_U2_ENABLE 49 /* dev may initiate U2 transition */ #define USB_DEVICE_LTM_ENABLE 50 /* dev may send LTM */ #define USB_INTRF_FUNC_SUSPEND 0 /* function suspend */ #define USB_INTR_FUNC_SUSPEND_OPT_MASK 0xFF00 /* * Suspend Options, Table 9-8 USB 3.0 spec */ #define USB_INTRF_FUNC_SUSPEND_LP (1 << (8 + 0)) #define USB_INTRF_FUNC_SUSPEND_RW (1 << (8 + 1)) /* * Interface status, Figure 9-5 USB 3.0 spec */ #define USB_INTRF_STAT_FUNC_RW_CAP 1 #define USB_INTRF_STAT_FUNC_RW 2 #define USB_ENDPOINT_HALT 0 /* IN/OUT will STALL */ /* Bit array elements as returned by the USB_REQ_GET_STATUS request. */ #define USB_DEV_STAT_U1_ENABLED 2 /* transition into U1 state */ #define USB_DEV_STAT_U2_ENABLED 3 /* transition into U2 state */ #define USB_DEV_STAT_LTM_ENABLED 4 /* Latency tolerance messages */ /* * Feature selectors from Table 9-8 USB Power Delivery spec */ #define USB_DEVICE_BATTERY_WAKE_MASK 40 #define USB_DEVICE_OS_IS_PD_AWARE 41 #define USB_DEVICE_POLICY_MODE 42 #define USB_PORT_PR_SWAP 43 #define USB_PORT_GOTO_MIN 44 #define USB_PORT_RETURN_POWER 45 #define USB_PORT_ACCEPT_PD_REQUEST 46 #define USB_PORT_REJECT_PD_REQUEST 47 #define USB_PORT_PORT_PD_RESET 48 #define USB_PORT_C_PORT_PD_CHANGE 49 #define USB_PORT_CABLE_PD_RESET 50 #define USB_DEVICE_CHARGING_POLICY 54 /** * struct usb_ctrlrequest - SETUP data for a USB device control request * @bRequestType: matches the USB bmRequestType field * @bRequest: matches the USB bRequest field * @wValue: matches the USB wValue field (le16 byte order) * @wIndex: matches the USB wIndex field (le16 byte order) * @wLength: matches the USB wLength field (le16 byte order) * * This structure is used to send control requests to a USB device. It matches * the different fields of the USB 2.0 Spec section 9.3, table 9-2. See the * USB spec for a fuller description of the different fields, and what they are * used for. * * Note that the driver for any interface can issue control requests. * For most devices, interfaces don't coordinate with each other, so * such requests may be made at any time. */ struct usb_ctrlrequest { __u8 bRequestType; __u8 bRequest; __le16 wValue; __le16 wIndex; __le16 wLength; } __attribute__ ((packed)); /*-------------------------------------------------------------------------*/ /* * STANDARD DESCRIPTORS ... as returned by GET_DESCRIPTOR, or * (rarely) accepted by SET_DESCRIPTOR. * * Note that all multi-byte values here are encoded in little endian * byte order "on the wire". Within the kernel and when exposed * through the Linux-USB APIs, they are not converted to cpu byte * order; it is the responsibility of the client code to do this. * The single exception is when device and configuration descriptors (but * not other descriptors) are read from character devices * (i.e. /dev/bus/usb/BBB/DDD); * in this case the fields are converted to host endianness by the kernel. */ /* * Descriptor types ... USB 2.0 spec table 9.5 */ #define USB_DT_DEVICE 0x01 #define USB_DT_CONFIG 0x02 #define USB_DT_STRING 0x03 #define USB_DT_INTERFACE 0x04 #define USB_DT_ENDPOINT 0x05 #define USB_DT_DEVICE_QUALIFIER 0x06 #define USB_DT_OTHER_SPEED_CONFIG 0x07 #define USB_DT_INTERFACE_POWER 0x08 /* these are from a minor usb 2.0 revision (ECN) */ #define USB_DT_OTG 0x09 #define USB_DT_DEBUG 0x0a #define USB_DT_INTERFACE_ASSOCIATION 0x0b /* these are from the Wireless USB spec */ #define USB_DT_SECURITY 0x0c #define USB_DT_KEY 0x0d #define USB_DT_ENCRYPTION_TYPE 0x0e #define USB_DT_BOS 0x0f #define USB_DT_DEVICE_CAPABILITY 0x10 #define USB_DT_WIRELESS_ENDPOINT_COMP 0x11 /* From the eUSB2 spec */ #define USB_DT_EUSB2_ISOC_ENDPOINT_COMP 0x12 /* From Wireless USB spec */ #define USB_DT_WIRE_ADAPTER 0x21 /* From USB Device Firmware Upgrade Specification, Revision 1.1 */ #define USB_DT_DFU_FUNCTIONAL 0x21 /* these are from the Wireless USB spec */ #define USB_DT_RPIPE 0x22 #define USB_DT_CS_RADIO_CONTROL 0x23 /* From the T10 UAS specification */ #define USB_DT_PIPE_USAGE 0x24 /* From the USB 3.0 spec */ #define USB_DT_SS_ENDPOINT_COMP 0x30 /* From the USB 3.1 spec */ #define USB_DT_SSP_ISOC_ENDPOINT_COMP 0x31 /* Conventional codes for class-specific descriptors. The convention is * defined in the USB "Common Class" Spec (3.11). Individual class specs * are authoritative for their usage, not the "common class" writeup. */ #define USB_DT_CS_DEVICE (USB_TYPE_CLASS | USB_DT_DEVICE) #define USB_DT_CS_CONFIG (USB_TYPE_CLASS | USB_DT_CONFIG) #define USB_DT_CS_STRING (USB_TYPE_CLASS | USB_DT_STRING) #define USB_DT_CS_INTERFACE (USB_TYPE_CLASS | USB_DT_INTERFACE) #define USB_DT_CS_ENDPOINT (USB_TYPE_CLASS | USB_DT_ENDPOINT) /* All standard descriptors have these 2 fields at the beginning */ struct usb_descriptor_header { __u8 bLength; __u8 bDescriptorType; } __attribute__ ((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_DEVICE: Device descriptor */ struct usb_device_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 bcdUSB; __u8 bDeviceClass; __u8 bDeviceSubClass; __u8 bDeviceProtocol; __u8 bMaxPacketSize0; __le16 idVendor; __le16 idProduct; __le16 bcdDevice; __u8 iManufacturer; __u8 iProduct; __u8 iSerialNumber; __u8 bNumConfigurations; } __attribute__ ((packed)); #define USB_DT_DEVICE_SIZE 18 /* * Device and/or Interface Class codes * as found in bDeviceClass or bInterfaceClass * and defined by www.usb.org documents */ #define USB_CLASS_PER_INTERFACE 0 /* for DeviceClass */ #define USB_CLASS_AUDIO 1 #define USB_CLASS_COMM 2 #define USB_CLASS_HID 3 #define USB_CLASS_PHYSICAL 5 #define USB_CLASS_STILL_IMAGE 6 #define USB_CLASS_PRINTER 7 #define USB_CLASS_MASS_STORAGE 8 #define USB_CLASS_HUB 9 #define USB_CLASS_CDC_DATA 0x0a #define USB_CLASS_CSCID 0x0b /* chip+ smart card */ #define USB_CLASS_CONTENT_SEC 0x0d /* content security */ #define USB_CLASS_VIDEO 0x0e #define USB_CLASS_WIRELESS_CONTROLLER 0xe0 #define USB_CLASS_PERSONAL_HEALTHCARE 0x0f #define USB_CLASS_AUDIO_VIDEO 0x10 #define USB_CLASS_BILLBOARD 0x11 #define USB_CLASS_USB_TYPE_C_BRIDGE 0x12 #define USB_CLASS_MCTP 0x14 #define USB_CLASS_MISC 0xef #define USB_CLASS_APP_SPEC 0xfe #define USB_SUBCLASS_DFU 0x01 #define USB_CLASS_VENDOR_SPEC 0xff #define USB_SUBCLASS_VENDOR_SPEC 0xff /*-------------------------------------------------------------------------*/ /* USB_DT_CONFIG: Configuration descriptor information. * * USB_DT_OTHER_SPEED_CONFIG is the same descriptor, except that the * descriptor type is different. Highspeed-capable devices can look * different depending on what speed they're currently running. Only * devices with a USB_DT_DEVICE_QUALIFIER have any OTHER_SPEED_CONFIG * descriptors. */ struct usb_config_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wTotalLength; __u8 bNumInterfaces; __u8 bConfigurationValue; __u8 iConfiguration; __u8 bmAttributes; __u8 bMaxPower; } __attribute__ ((packed)); #define USB_DT_CONFIG_SIZE 9 /* from config descriptor bmAttributes */ #define USB_CONFIG_ATT_ONE (1 << 7) /* must be set */ #define USB_CONFIG_ATT_SELFPOWER (1 << 6) /* self powered */ #define USB_CONFIG_ATT_WAKEUP (1 << 5) /* can wakeup */ #define USB_CONFIG_ATT_BATTERY (1 << 4) /* battery powered */ /*-------------------------------------------------------------------------*/ /* USB String descriptors can contain at most 126 characters. */ #define USB_MAX_STRING_LEN 126 /* USB_DT_STRING: String descriptor */ struct usb_string_descriptor { __u8 bLength; __u8 bDescriptorType; union { __le16 legacy_padding; __DECLARE_FLEX_ARRAY(__le16, wData); /* UTF-16LE encoded */ }; } __attribute__ ((packed)); /* note that "string" zero is special, it holds language codes that * the device supports, not Unicode characters. */ /*-------------------------------------------------------------------------*/ /* USB_DT_INTERFACE: Interface descriptor */ struct usb_interface_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bInterfaceNumber; __u8 bAlternateSetting; __u8 bNumEndpoints; __u8 bInterfaceClass; __u8 bInterfaceSubClass; __u8 bInterfaceProtocol; __u8 iInterface; } __attribute__ ((packed)); #define USB_DT_INTERFACE_SIZE 9 /*-------------------------------------------------------------------------*/ /* USB_DT_ENDPOINT: Endpoint descriptor */ struct usb_endpoint_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bEndpointAddress; __u8 bmAttributes; __le16 wMaxPacketSize; __u8 bInterval; /* NOTE: these two are _only_ in audio endpoints. */ /* use USB_DT_ENDPOINT*_SIZE in bLength, not sizeof. */ __u8 bRefresh; __u8 bSynchAddress; } __attribute__ ((packed)); #define USB_DT_ENDPOINT_SIZE 7 #define USB_DT_ENDPOINT_AUDIO_SIZE 9 /* Audio extension */ /* * Endpoints */ #define USB_ENDPOINT_NUMBER_MASK 0x0f /* in bEndpointAddress */ #define USB_ENDPOINT_DIR_MASK 0x80 #define USB_ENDPOINT_XFERTYPE_MASK 0x03 /* in bmAttributes */ #define USB_ENDPOINT_XFER_CONTROL 0 #define USB_ENDPOINT_XFER_ISOC 1 #define USB_ENDPOINT_XFER_BULK 2 #define USB_ENDPOINT_XFER_INT 3 #define USB_ENDPOINT_MAX_ADJUSTABLE 0x80 #define USB_ENDPOINT_MAXP_MASK 0x07ff #define USB_EP_MAXP_MULT_SHIFT 11 #define USB_EP_MAXP_MULT_MASK (3 << USB_EP_MAXP_MULT_SHIFT) #define USB_EP_MAXP_MULT(m) \ (((m) & USB_EP_MAXP_MULT_MASK) >> USB_EP_MAXP_MULT_SHIFT) /* The USB 3.0 spec redefines bits 5:4 of bmAttributes as interrupt ep type. */ #define USB_ENDPOINT_INTRTYPE 0x30 #define USB_ENDPOINT_INTR_PERIODIC (0 << 4) #define USB_ENDPOINT_INTR_NOTIFICATION (1 << 4) #define USB_ENDPOINT_SYNCTYPE 0x0c #define USB_ENDPOINT_SYNC_NONE (0 << 2) #define USB_ENDPOINT_SYNC_ASYNC (1 << 2) #define USB_ENDPOINT_SYNC_ADAPTIVE (2 << 2) #define USB_ENDPOINT_SYNC_SYNC (3 << 2) #define USB_ENDPOINT_USAGE_MASK 0x30 #define USB_ENDPOINT_USAGE_DATA 0x00 #define USB_ENDPOINT_USAGE_FEEDBACK 0x10 #define USB_ENDPOINT_USAGE_IMPLICIT_FB 0x20 /* Implicit feedback Data endpoint */ /*-------------------------------------------------------------------------*/ /** * usb_endpoint_num - get the endpoint's number * @epd: endpoint to be checked * * Returns @epd's number: 0 to 15. */ static inline int usb_endpoint_num(const struct usb_endpoint_descriptor *epd) { return epd->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK; } /** * usb_endpoint_type - get the endpoint's transfer type * @epd: endpoint to be checked * * Returns one of USB_ENDPOINT_XFER_{CONTROL, ISOC, BULK, INT} according * to @epd's transfer type. */ static inline int usb_endpoint_type(const struct usb_endpoint_descriptor *epd) { return epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK; } /** * usb_endpoint_dir_in - check if the endpoint has IN direction * @epd: endpoint to be checked * * Returns true if the endpoint is of type IN, otherwise it returns false. */ static inline int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd) { return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN); } /** * usb_endpoint_dir_out - check if the endpoint has OUT direction * @epd: endpoint to be checked * * Returns true if the endpoint is of type OUT, otherwise it returns false. */ static inline int usb_endpoint_dir_out( const struct usb_endpoint_descriptor *epd) { return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT); } /** * usb_endpoint_xfer_bulk - check if the endpoint has bulk transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type bulk, otherwise it returns false. */ static inline int usb_endpoint_xfer_bulk( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_BULK); } /** * usb_endpoint_xfer_control - check if the endpoint has control transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type control, otherwise it returns false. */ static inline int usb_endpoint_xfer_control( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_CONTROL); } /** * usb_endpoint_xfer_int - check if the endpoint has interrupt transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type interrupt, otherwise it returns * false. */ static inline int usb_endpoint_xfer_int( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT); } /** * usb_endpoint_xfer_isoc - check if the endpoint has isochronous transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type isochronous, otherwise it returns * false. */ static inline int usb_endpoint_xfer_isoc( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_ISOC); } /** * usb_endpoint_is_bulk_in - check if the endpoint is bulk IN * @epd: endpoint to be checked * * Returns true if the endpoint has bulk transfer type and IN direction, * otherwise it returns false. */ static inline int usb_endpoint_is_bulk_in( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_in(epd); } /** * usb_endpoint_is_bulk_out - check if the endpoint is bulk OUT * @epd: endpoint to be checked * * Returns true if the endpoint has bulk transfer type and OUT direction, * otherwise it returns false. */ static inline int usb_endpoint_is_bulk_out( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_out(epd); } /** * usb_endpoint_is_int_in - check if the endpoint is interrupt IN * @epd: endpoint to be checked * * Returns true if the endpoint has interrupt transfer type and IN direction, * otherwise it returns false. */ static inline int usb_endpoint_is_int_in( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_int(epd) && usb_endpoint_dir_in(epd); } /** * usb_endpoint_is_int_out - check if the endpoint is interrupt OUT * @epd: endpoint to be checked * * Returns true if the endpoint has interrupt transfer type and OUT direction, * otherwise it returns false. */ static inline int usb_endpoint_is_int_out( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_int(epd) && usb_endpoint_dir_out(epd); } /** * usb_endpoint_is_isoc_in - check if the endpoint is isochronous IN * @epd: endpoint to be checked * * Returns true if the endpoint has isochronous transfer type and IN direction, * otherwise it returns false. */ static inline int usb_endpoint_is_isoc_in( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_in(epd); } /** * usb_endpoint_is_isoc_out - check if the endpoint is isochronous OUT * @epd: endpoint to be checked * * Returns true if the endpoint has isochronous transfer type and OUT direction, * otherwise it returns false. */ static inline int usb_endpoint_is_isoc_out( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_out(epd); } /** * usb_endpoint_maxp - get endpoint's max packet size * @epd: endpoint to be checked * * Returns @epd's max packet bits [10:0] */ static inline int usb_endpoint_maxp(const struct usb_endpoint_descriptor *epd) { return __le16_to_cpu(epd->wMaxPacketSize) & USB_ENDPOINT_MAXP_MASK; } /** * usb_endpoint_maxp_mult - get endpoint's transactional opportunities * @epd: endpoint to be checked * * Return @epd's wMaxPacketSize[12:11] + 1 */ static inline int usb_endpoint_maxp_mult(const struct usb_endpoint_descriptor *epd) { int maxp = __le16_to_cpu(epd->wMaxPacketSize); return USB_EP_MAXP_MULT(maxp) + 1; } static inline int usb_endpoint_interrupt_type( const struct usb_endpoint_descriptor *epd) { return epd->bmAttributes & USB_ENDPOINT_INTRTYPE; } /*-------------------------------------------------------------------------*/ /* USB_DT_EUSB2_ISOC_ENDPOINT_COMP: eUSB2 Isoch Endpoint Companion descriptor */ struct usb_eusb2_isoc_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wMaxPacketSize; __le32 dwBytesPerInterval; } __attribute__ ((packed)); #define USB_DT_EUSB2_ISOC_EP_COMP_SIZE 8 /*-------------------------------------------------------------------------*/ /* USB_DT_SSP_ISOC_ENDPOINT_COMP: SuperSpeedPlus Isochronous Endpoint Companion * descriptor */ struct usb_ssp_isoc_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wReseved; __le32 dwBytesPerInterval; } __attribute__ ((packed)); #define USB_DT_SSP_ISOC_EP_COMP_SIZE 8 /*-------------------------------------------------------------------------*/ /* USB_DT_SS_ENDPOINT_COMP: SuperSpeed Endpoint Companion descriptor */ struct usb_ss_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bMaxBurst; __u8 bmAttributes; __le16 wBytesPerInterval; } __attribute__ ((packed)); #define USB_DT_SS_EP_COMP_SIZE 6 /* Bits 4:0 of bmAttributes if this is a bulk endpoint */ static inline int usb_ss_max_streams(const struct usb_ss_ep_comp_descriptor *comp) { int max_streams; if (!comp) return 0; max_streams = comp->bmAttributes & 0x1f; if (!max_streams) return 0; max_streams = 1 << max_streams; return max_streams; } /* Bits 1:0 of bmAttributes if this is an isoc endpoint */ #define USB_SS_MULT(p) (1 + ((p) & 0x3)) /* Bit 7 of bmAttributes if a SSP isoc endpoint companion descriptor exists */ #define USB_SS_SSP_ISOC_COMP(p) ((p) & (1 << 7)) /*-------------------------------------------------------------------------*/ /* USB_DT_DEVICE_QUALIFIER: Device Qualifier descriptor */ struct usb_qualifier_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 bcdUSB; __u8 bDeviceClass; __u8 bDeviceSubClass; __u8 bDeviceProtocol; __u8 bMaxPacketSize0; __u8 bNumConfigurations; __u8 bRESERVED; } __attribute__ ((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_OTG (from OTG 1.0a supplement) */ struct usb_otg_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bmAttributes; /* support for HNP, SRP, etc */ } __attribute__ ((packed)); /* USB_DT_OTG (from OTG 2.0 supplement) */ struct usb_otg20_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bmAttributes; /* support for HNP, SRP and ADP, etc */ __le16 bcdOTG; /* OTG and EH supplement release number * in binary-coded decimal(i.e. 2.0 is 0200H) */ } __attribute__ ((packed)); /* from usb_otg_descriptor.bmAttributes */ #define USB_OTG_SRP (1 << 0) #define USB_OTG_HNP (1 << 1) /* swap host/device roles */ #define USB_OTG_ADP (1 << 2) /* support ADP */ /* OTG 3.0 */ #define USB_OTG_RSP (1 << 3) /* support RSP */ #define OTG_STS_SELECTOR 0xF000 /* OTG status selector */ /*-------------------------------------------------------------------------*/ /* USB_DT_DEBUG: for special highspeed devices, replacing serial console */ struct usb_debug_descriptor { __u8 bLength; __u8 bDescriptorType; /* bulk endpoints with 8 byte maxpacket */ __u8 bDebugInEndpoint; __u8 bDebugOutEndpoint; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_INTERFACE_ASSOCIATION: groups interfaces */ struct usb_interface_assoc_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bFirstInterface; __u8 bInterfaceCount; __u8 bFunctionClass; __u8 bFunctionSubClass; __u8 bFunctionProtocol; __u8 iFunction; } __attribute__ ((packed)); #define USB_DT_INTERFACE_ASSOCIATION_SIZE 8 /*-------------------------------------------------------------------------*/ /* USB_DT_SECURITY: group of wireless security descriptors, including * encryption types available for setting up a CC/association. */ struct usb_security_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wTotalLength; __u8 bNumEncryptionTypes; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_KEY: used with {GET,SET}_SECURITY_DATA; only public keys * may be retrieved. */ struct usb_key_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 tTKID[3]; __u8 bReserved; __u8 bKeyData[]; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_ENCRYPTION_TYPE: bundled in DT_SECURITY groups */ struct usb_encryption_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bEncryptionType; #define USB_ENC_TYPE_UNSECURE 0 #define USB_ENC_TYPE_WIRED 1 /* non-wireless mode */ #define USB_ENC_TYPE_CCM_1 2 /* aes128/cbc session */ #define USB_ENC_TYPE_RSA_1 3 /* rsa3072/sha1 auth */ __u8 bEncryptionValue; /* use in SET_ENCRYPTION */ __u8 bAuthKeyIndex; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_BOS: group of device-level capabilities */ struct usb_bos_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wTotalLength; __u8 bNumDeviceCaps; } __attribute__((packed)); #define USB_DT_BOS_SIZE 5 /*-------------------------------------------------------------------------*/ /* USB_DT_DEVICE_CAPABILITY: grouped with BOS */ struct usb_dev_cap_header { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; } __attribute__((packed)); #define USB_CAP_TYPE_WIRELESS_USB 1 struct usb_wireless_cap_descriptor { /* Ultra Wide Band */ __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bmAttributes; #define USB_WIRELESS_P2P_DRD (1 << 1) #define USB_WIRELESS_BEACON_MASK (3 << 2) #define USB_WIRELESS_BEACON_SELF (1 << 2) #define USB_WIRELESS_BEACON_DIRECTED (2 << 2) #define USB_WIRELESS_BEACON_NONE (3 << 2) __le16 wPHYRates; /* bit rates, Mbps */ #define USB_WIRELESS_PHY_53 (1 << 0) /* always set */ #define USB_WIRELESS_PHY_80 (1 << 1) #define USB_WIRELESS_PHY_107 (1 << 2) /* always set */ #define USB_WIRELESS_PHY_160 (1 << 3) #define USB_WIRELESS_PHY_200 (1 << 4) /* always set */ #define USB_WIRELESS_PHY_320 (1 << 5) #define USB_WIRELESS_PHY_400 (1 << 6) #define USB_WIRELESS_PHY_480 (1 << 7) __u8 bmTFITXPowerInfo; /* TFI power levels */ __u8 bmFFITXPowerInfo; /* FFI power levels */ __le16 bmBandGroup; __u8 bReserved; } __attribute__((packed)); #define USB_DT_USB_WIRELESS_CAP_SIZE 11 /* USB 2.0 Extension descriptor */ #define USB_CAP_TYPE_EXT 2 struct usb_ext_cap_descriptor { /* Link Power Management */ __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __le32 bmAttributes; #define USB_LPM_SUPPORT (1 << 1) /* supports LPM */ #define USB_BESL_SUPPORT (1 << 2) /* supports BESL */ #define USB_BESL_BASELINE_VALID (1 << 3) /* Baseline BESL valid*/ #define USB_BESL_DEEP_VALID (1 << 4) /* Deep BESL valid */ #define USB_SET_BESL_BASELINE(p) (((p) & 0xf) << 8) #define USB_SET_BESL_DEEP(p) (((p) & 0xf) << 12) #define USB_GET_BESL_BASELINE(p) (((p) & (0xf << 8)) >> 8) #define USB_GET_BESL_DEEP(p) (((p) & (0xf << 12)) >> 12) } __attribute__((packed)); #define USB_DT_USB_EXT_CAP_SIZE 7 /* * SuperSpeed USB Capability descriptor: Defines the set of SuperSpeed USB * specific device level capabilities */ #define USB_SS_CAP_TYPE 3 struct usb_ss_cap_descriptor { /* Link Power Management */ __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bmAttributes; #define USB_LTM_SUPPORT (1 << 1) /* supports LTM */ __le16 wSpeedSupported; #define USB_LOW_SPEED_OPERATION (1) /* Low speed operation */ #define USB_FULL_SPEED_OPERATION (1 << 1) /* Full speed operation */ #define USB_HIGH_SPEED_OPERATION (1 << 2) /* High speed operation */ #define USB_5GBPS_OPERATION (1 << 3) /* Operation at 5Gbps */ __u8 bFunctionalitySupport; __u8 bU1devExitLat; __le16 bU2DevExitLat; } __attribute__((packed)); #define USB_DT_USB_SS_CAP_SIZE 10 /* * Container ID Capability descriptor: Defines the instance unique ID used to * identify the instance across all operating modes */ #define CONTAINER_ID_TYPE 4 struct usb_ss_container_id_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __u8 ContainerID[16]; /* 128-bit number */ } __attribute__((packed)); #define USB_DT_USB_SS_CONTN_ID_SIZE 20 /* * Platform Device Capability descriptor: Defines platform specific device * capabilities */ #define USB_PLAT_DEV_CAP_TYPE 5 struct usb_plat_dev_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __u8 UUID[16]; __u8 CapabilityData[]; } __attribute__((packed)); #define USB_DT_USB_PLAT_DEV_CAP_SIZE(capability_data_size) (20 + capability_data_size) /* * SuperSpeed Plus USB Capability descriptor: Defines the set of * SuperSpeed Plus USB specific device level capabilities */ #define USB_SSP_CAP_TYPE 0xa struct usb_ssp_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __le32 bmAttributes; #define USB_SSP_SUBLINK_SPEED_ATTRIBS (0x1f << 0) /* sublink speed entries */ #define USB_SSP_SUBLINK_SPEED_IDS (0xf << 5) /* speed ID entries */ __le16 wFunctionalitySupport; #define USB_SSP_MIN_SUBLINK_SPEED_ATTRIBUTE_ID (0xf) #define USB_SSP_MIN_RX_LANE_COUNT (0xf << 8) #define USB_SSP_MIN_TX_LANE_COUNT (0xf << 12) __le16 wReserved; union { __le32 legacy_padding; /* list of sublink speed attrib entries */ __DECLARE_FLEX_ARRAY(__le32, bmSublinkSpeedAttr); }; #define USB_SSP_SUBLINK_SPEED_SSID (0xf) /* sublink speed ID */ #define USB_SSP_SUBLINK_SPEED_LSE (0x3 << 4) /* Lanespeed exponent */ #define USB_SSP_SUBLINK_SPEED_LSE_BPS 0 #define USB_SSP_SUBLINK_SPEED_LSE_KBPS 1 #define USB_SSP_SUBLINK_SPEED_LSE_MBPS 2 #define USB_SSP_SUBLINK_SPEED_LSE_GBPS 3 #define USB_SSP_SUBLINK_SPEED_ST (0x3 << 6) /* Sublink type */ #define USB_SSP_SUBLINK_SPEED_ST_SYM_RX 0 #define USB_SSP_SUBLINK_SPEED_ST_ASYM_RX 1 #define USB_SSP_SUBLINK_SPEED_ST_SYM_TX 2 #define USB_SSP_SUBLINK_SPEED_ST_ASYM_TX 3 #define USB_SSP_SUBLINK_SPEED_RSVD (0x3f << 8) /* Reserved */ #define USB_SSP_SUBLINK_SPEED_LP (0x3 << 14) /* Link protocol */ #define USB_SSP_SUBLINK_SPEED_LP_SS 0 #define USB_SSP_SUBLINK_SPEED_LP_SSP 1 #define USB_SSP_SUBLINK_SPEED_LSM (0xff << 16) /* Lanespeed mantissa */ } __attribute__((packed)); /* * USB Power Delivery Capability Descriptor: * Defines capabilities for PD */ /* Defines the various PD Capabilities of this device */ #define USB_PD_POWER_DELIVERY_CAPABILITY 0x06 /* Provides information on each battery supported by the device */ #define USB_PD_BATTERY_INFO_CAPABILITY 0x07 /* The Consumer characteristics of a Port on the device */ #define USB_PD_PD_CONSUMER_PORT_CAPABILITY 0x08 /* The provider characteristics of a Port on the device */ #define USB_PD_PD_PROVIDER_PORT_CAPABILITY 0x09 struct usb_pd_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; /* set to USB_PD_POWER_DELIVERY_CAPABILITY */ __u8 bReserved; __le32 bmAttributes; #define USB_PD_CAP_BATTERY_CHARGING (1 << 1) /* supports Battery Charging specification */ #define USB_PD_CAP_USB_PD (1 << 2) /* supports USB Power Delivery specification */ #define USB_PD_CAP_PROVIDER (1 << 3) /* can provide power */ #define USB_PD_CAP_CONSUMER (1 << 4) /* can consume power */ #define USB_PD_CAP_CHARGING_POLICY (1 << 5) /* supports CHARGING_POLICY feature */ #define USB_PD_CAP_TYPE_C_CURRENT (1 << 6) /* supports power capabilities defined in the USB Type-C Specification */ #define USB_PD_CAP_PWR_AC (1 << 8) #define USB_PD_CAP_PWR_BAT (1 << 9) #define USB_PD_CAP_PWR_USE_V_BUS (1 << 14) __le16 bmProviderPorts; /* Bit zero refers to the UFP of the device */ __le16 bmConsumerPorts; __le16 bcdBCVersion; __le16 bcdPDVersion; __le16 bcdUSBTypeCVersion; } __attribute__((packed)); struct usb_pd_cap_battery_info_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; /* Index of string descriptor shall contain the user friendly name for this battery */ __u8 iBattery; /* Index of string descriptor shall contain the Serial Number String for this battery */ __u8 iSerial; __u8 iManufacturer; __u8 bBatteryId; /* uniquely identifies this battery in status Messages */ __u8 bReserved; /* * Shall contain the Battery Charge value above which this * battery is considered to be fully charged but not necessarily * “topped off.” */ __le32 dwChargedThreshold; /* in mWh */ /* * Shall contain the minimum charge level of this battery such * that above this threshold, a device can be assured of being * able to power up successfully (see Battery Charging 1.2). */ __le32 dwWeakThreshold; /* in mWh */ __le32 dwBatteryDesignCapacity; /* in mWh */ __le32 dwBatteryLastFullchargeCapacity; /* in mWh */ } __attribute__((packed)); struct usb_pd_cap_consumer_port_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __u8 bmCapabilities; /* port will oerate under: */ #define USB_PD_CAP_CONSUMER_BC (1 << 0) /* BC */ #define USB_PD_CAP_CONSUMER_PD (1 << 1) /* PD */ #define USB_PD_CAP_CONSUMER_TYPE_C (1 << 2) /* USB Type-C Current */ __le16 wMinVoltage; /* in 50mV units */ __le16 wMaxVoltage; /* in 50mV units */ __u16 wReserved; __le32 dwMaxOperatingPower; /* in 10 mW - operating at steady state */ __le32 dwMaxPeakPower; /* in 10mW units - operating at peak power */ __le32 dwMaxPeakPowerTime; /* in 100ms units - duration of peak */ #define USB_PD_CAP_CONSUMER_UNKNOWN_PEAK_POWER_TIME 0xffff } __attribute__((packed)); struct usb_pd_cap_provider_port_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved1; __u8 bmCapabilities; /* port will oerate under: */ #define USB_PD_CAP_PROVIDER_BC (1 << 0) /* BC */ #define USB_PD_CAP_PROVIDER_PD (1 << 1) /* PD */ #define USB_PD_CAP_PROVIDER_TYPE_C (1 << 2) /* USB Type-C Current */ __u8 bNumOfPDObjects; __u8 bReserved2; __le32 wPowerDataObject[]; } __attribute__((packed)); /* * Precision time measurement capability descriptor: advertised by devices and * hubs that support PTM */ #define USB_PTM_CAP_TYPE 0xb struct usb_ptm_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; } __attribute__((packed)); #define USB_DT_USB_PTM_ID_SIZE 3 /* * The size of the descriptor for the Sublink Speed Attribute Count * (SSAC) specified in bmAttributes[4:0]. SSAC is zero-based */ #define USB_DT_USB_SSP_CAP_SIZE(ssac) (12 + (ssac + 1) * 4) /*-------------------------------------------------------------------------*/ /* USB_DT_WIRELESS_ENDPOINT_COMP: companion descriptor associated with * each endpoint descriptor for a wireless device */ struct usb_wireless_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bMaxBurst; __u8 bMaxSequence; __le16 wMaxStreamDelay; __le16 wOverTheAirPacketSize; __u8 bOverTheAirInterval; __u8 bmCompAttributes; #define USB_ENDPOINT_SWITCH_MASK 0x03 /* in bmCompAttributes */ #define USB_ENDPOINT_SWITCH_NO 0 #define USB_ENDPOINT_SWITCH_SWITCH 1 #define USB_ENDPOINT_SWITCH_SCALE 2 } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_REQ_SET_HANDSHAKE is a four-way handshake used between a wireless * host and a device for connection set up, mutual authentication, and * exchanging short lived session keys. The handshake depends on a CC. */ struct usb_handshake { __u8 bMessageNumber; __u8 bStatus; __u8 tTKID[3]; __u8 bReserved; __u8 CDID[16]; __u8 nonce[16]; __u8 MIC[8]; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_REQ_SET_CONNECTION modifies or revokes a connection context (CC). * A CC may also be set up using non-wireless secure channels (including * wired USB!), and some devices may support CCs with multiple hosts. */ struct usb_connection_context { __u8 CHID[16]; /* persistent host id */ __u8 CDID[16]; /* device id (unique w/in host context) */ __u8 CK[16]; /* connection key */ } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB 2.0 defines three speeds, here's how Linux identifies them */ enum usb_device_speed { USB_SPEED_UNKNOWN = 0, /* enumerating */ USB_SPEED_LOW, USB_SPEED_FULL, /* usb 1.1 */ USB_SPEED_HIGH, /* usb 2.0 */ USB_SPEED_WIRELESS, /* wireless (usb 2.5) */ USB_SPEED_SUPER, /* usb 3.0 */ USB_SPEED_SUPER_PLUS, /* usb 3.1 */ }; enum usb_device_state { /* NOTATTACHED isn't in the USB spec, and this state acts * the same as ATTACHED ... but it's clearer this way. */ USB_STATE_NOTATTACHED = 0, /* chapter 9 and authentication (wireless) device states */ USB_STATE_ATTACHED, USB_STATE_POWERED, /* wired */ USB_STATE_RECONNECTING, /* auth */ USB_STATE_UNAUTHENTICATED, /* auth */ USB_STATE_DEFAULT, /* limited function */ USB_STATE_ADDRESS, USB_STATE_CONFIGURED, /* most functions */ USB_STATE_SUSPENDED /* NOTE: there are actually four different SUSPENDED * states, returning to POWERED, DEFAULT, ADDRESS, or * CONFIGURED respectively when SOF tokens flow again. * At this level there's no difference between L1 and L2 * suspend states. (L2 being original USB 1.1 suspend.) */ }; enum usb3_link_state { USB3_LPM_U0 = 0, USB3_LPM_U1, USB3_LPM_U2, USB3_LPM_U3 }; /* * A U1 timeout of 0x0 means the parent hub will reject any transitions to U1. * 0xff means the parent hub will accept transitions to U1, but will not * initiate a transition. * * A U1 timeout of 0x1 to 0x7F also causes the hub to initiate a transition to * U1 after that many microseconds. Timeouts of 0x80 to 0xFE are reserved * values. * * A U2 timeout of 0x0 means the parent hub will reject any transitions to U2. * 0xff means the parent hub will accept transitions to U2, but will not * initiate a transition. * * A U2 timeout of 0x1 to 0xFE also causes the hub to initiate a transition to * U2 after N*256 microseconds. Therefore a U2 timeout value of 0x1 means a U2 * idle timer of 256 microseconds, 0x2 means 512 microseconds, 0xFE means * 65.024ms. */ #define USB3_LPM_DISABLED 0x0 #define USB3_LPM_U1_MAX_TIMEOUT 0x7F #define USB3_LPM_U2_MAX_TIMEOUT 0xFE #define USB3_LPM_DEVICE_INITIATED 0xFF struct usb_set_sel_req { __u8 u1_sel; __u8 u1_pel; __le16 u2_sel; __le16 u2_pel; } __attribute__ ((packed)); /* * The Set System Exit Latency control transfer provides one byte each for * U1 SEL and U1 PEL, so the max exit latency is 0xFF. U2 SEL and U2 PEL each * are two bytes long. */ #define USB3_LPM_MAX_U1_SEL_PEL 0xFF #define USB3_LPM_MAX_U2_SEL_PEL 0xFFFF /*-------------------------------------------------------------------------*/ /* * As per USB compliance update, a device that is actively drawing * more than 100mA from USB must report itself as bus-powered in * the GetStatus(DEVICE) call. * https://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34 */ #define USB_SELF_POWER_VBUS_MAX_DRAW 100 #endif /* _UAPI__LINUX_USB_CH9_H */ |
| 2815 2816 2816 2814 2079 782 2816 2818 1 2819 3 2813 2820 2817 1685 2017 391 51 2816 2820 9 2814 49 3630 2820 179 834 49 1004 1 1 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs * * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes * 2000-2002 x86-64 support by Andi Kleen */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> #include <linux/kstrtox.h> #include <linux/errno.h> #include <linux/wait.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> #include <linux/uaccess.h> #include <linux/user-return-notifier.h> #include <linux/uprobes.h> #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/syscalls.h> #include <linux/rseq.h> #include <asm/processor.h> #include <asm/ucontext.h> #include <asm/fpu/signal.h> #include <asm/fpu/xstate.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> #include <asm/vm86.h> #include <asm/syscall.h> #include <asm/sigframe.h> #include <asm/signal.h> #include <asm/shstk.h> static inline int is_ia32_compat_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_IA32_EMULATION) && ksig->ka.sa.sa_flags & SA_IA32_ABI; } static inline int is_ia32_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); } static inline int is_x32_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_X86_X32_ABI) && ksig->ka.sa.sa_flags & SA_X32_ABI; } /* * Enable all pkeys temporarily, so as to ensure that both the current * execution stack as well as the alternate signal stack are writeable. * The application can use any of the available pkeys to protect the * alternate signal stack, and we don't know which one it is, so enable * all. The PKRU register will be reset to init_pkru later in the flow, * in fpu__clear_user_states(), and it is the application's responsibility * to enable the appropriate pkey as the first step in the signal handler * so that the handler does not segfault. */ static inline u32 sig_prepare_pkru(void) { u32 orig_pkru = read_pkru(); write_pkru(0); return orig_pkru; } /* * Set up a signal frame. */ /* x86 ABI requires 16-byte alignment */ #define FRAME_ALIGNMENT 16UL #define MAX_FRAME_PADDING (FRAME_ALIGNMENT - 1) /* * Determine which stack to use.. */ void __user * get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { struct k_sigaction *ka = &ksig->ka; int ia32_frame = is_ia32_frame(ksig); /* Default to using normal stack */ bool nested_altstack = on_sig_stack(regs->sp); bool entering_altstack = false; unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; u32 pkru; /* redzone */ if (!ia32_frame) sp -= 128; /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { /* * This checks nested_altstack via sas_ss_flags(). Sensible * programs use SS_AUTODISARM, which disables that check, and * programs that don't use SS_AUTODISARM get compatible. */ if (sas_ss_flags(sp) == 0) { sp = current->sas_ss_sp + current->sas_ss_size; entering_altstack = true; } } else if (ia32_frame && !nested_altstack && regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) { /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; entering_altstack = true; } sp = fpu__alloc_mathframe(sp, ia32_frame, &buf_fx, &math_size); *fpstate = (void __user *)sp; sp -= frame_size; if (ia32_frame) /* * Align the stack pointer according to the i386 ABI, * i.e. so that on function entry ((sp + 4) & 15) == 0. */ sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; else sp = round_down(sp, FRAME_ALIGNMENT) - 8; /* * If we are on the alternate signal stack and would overflow it, don't. * Return an always-bogus address instead so we will die with SIGSEGV. */ if (unlikely((nested_altstack || entering_altstack) && !__on_sig_stack(sp))) { if (show_unhandled_signals && printk_ratelimit()) pr_info("%s[%d] overflowed sigaltstack\n", current->comm, task_pid_nr(current)); return (void __user *)-1L; } /* Update PKRU to enable access to the alternate signal stack. */ pkru = sig_prepare_pkru(); /* save i387 and extended state */ if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) { /* * Restore PKRU to the original, user-defined value; disable * extra pkeys enabled for the alternate signal stack, if any. */ write_pkru(pkru); return (void __user *)-1L; } return (void __user *)sp; } /* * There are four different struct types for signal frame: sigframe_ia32, * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case * -- the largest size. It means the size for 64-bit apps is a bit more * than needed, but this keeps the code simple. */ #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) # define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct sigframe_ia32) #else # define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct rt_sigframe) #endif /* * The FP state frame contains an XSAVE buffer which must be 64-byte aligned. * If a signal frame starts at an unaligned address, extra space is required. * This is the max alignment padding, conservatively. */ #define MAX_XSAVE_PADDING 63UL /* * The frame data is composed of the following areas and laid out as: * * ------------------------- * | alignment padding | * ------------------------- * | (f)xsave frame | * ------------------------- * | fsave header | * ------------------------- * | alignment padding | * ------------------------- * | siginfo + ucontext | * ------------------------- */ /* max_frame_size tells userspace the worst case signal stack size. */ static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING; max_frame_size += fpu_default_state_size + MAX_XSAVE_PADDING; /* Userspace expects an aligned size. */ max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); return 0; } early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { return max_frame_size; } static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) return ia32_setup_rt_frame(ksig, regs); else return ia32_setup_frame(ksig, regs); } else if (is_x32_frame(ksig)) { return x32_setup_rt_frame(ksig, regs); } else { return x64_setup_rt_frame(ksig, regs); } } static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; struct fpu *fpu = ¤t->thread.fpu; if (v8086_mode(regs)) save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL); /* Are we from a system call? */ if (syscall_get_nr(current, regs) != -1) { /* If so, check system call restarting.. */ switch (syscall_get_error(current, regs)) { case -ERESTART_RESTARTBLOCK: case -ERESTARTNOHAND: regs->ax = -EINTR; break; case -ERESTARTSYS: if (!(ksig->ka.sa.sa_flags & SA_RESTART)) { regs->ax = -EINTR; break; } fallthrough; case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; break; } } /* * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now * so that register information in the sigcontext is correct and * then notify the tracer before entering the signal handler. */ stepping = test_thread_flag(TIF_SINGLESTEP); if (stepping) user_disable_single_step(current); failed = (setup_rt_frame(ksig, regs) < 0); if (!failed) { /* * Clear the direction flag as per the ABI for function entry. * * Clear RF when entering the signal handler, because * it might disable possible debug exception from the * signal handler. * * Clear TF for the case when it wasn't set by debugger to * avoid the recursive send_sigtrap() in SIGTRAP handler. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); /* * Ensure the signal handler starts with the new fpu state. */ fpu__clear_user_states(fpu); } signal_setup_done(failed, ksig, stepping); } static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_IA32_EMULATION if (current->restart_block.arch_data & TS_COMPAT) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); #else return __NR_restart_syscall; #endif } /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ void arch_do_signal_or_restart(struct pt_regs *regs) { struct ksignal ksig; if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; } /* Did we come from a system call? */ if (syscall_get_nr(current, regs) != -1) { /* Restart the system call - no handlers present */ switch (syscall_get_error(current, regs)) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; break; case -ERESTART_RESTARTBLOCK: regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } } /* * If there's no signal to deliver, we just put the saved sigmask * back. */ restore_saved_sigmask(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) { struct task_struct *me = current; if (show_unhandled_signals && printk_ratelimit()) { printk("%s" "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx", task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } force_sig(SIGSEGV); } #ifdef CONFIG_DYNAMIC_SIGFRAME #ifdef CONFIG_STRICT_SIGALTSTACK_SIZE static bool strict_sigaltstack_size __ro_after_init = true; #else static bool strict_sigaltstack_size __ro_after_init = false; #endif static int __init strict_sas_size(char *arg) { return kstrtobool(arg, &strict_sigaltstack_size) == 0; } __setup("strict_sas_size", strict_sas_size); /* * MINSIGSTKSZ is 2048 and can't be changed despite the fact that AVX512 * exceeds that size already. As such programs might never use the * sigaltstack they just continued to work. While always checking against * the real size would be correct, this might be considered a regression. * * Therefore avoid the sanity check, unless enforced by kernel * configuration or command line option. * * When dynamic FPU features are supported, the check is also enforced when * the task has permissions to use dynamic features. Tasks which have no * permission are checked against the size of the non-dynamic feature set * if strict checking is enabled. This avoids forcing all tasks on the * system to allocate large sigaltstacks even if they are never going * to use a dynamic feature. As this is serialized via sighand::siglock * any permission request for a dynamic feature either happened already * or will see the newly install sigaltstack size in the permission checks. */ bool sigaltstack_size_valid(size_t ss_size) { unsigned long fsize = max_frame_size - fpu_default_state_size; u64 mask; lockdep_assert_held(¤t->sighand->siglock); if (!fpu_state_size_dynamic() && !strict_sigaltstack_size) return true; fsize += current->group_leader->thread.fpu.perm.__user_state_size; if (likely(ss_size > fsize)) return true; if (strict_sigaltstack_size) return ss_size > fsize; mask = current->group_leader->thread.fpu.perm.__state_perm; if (mask & XFEATURE_MASK_USER_DYNAMIC) return ss_size > fsize; return true; } #endif /* CONFIG_DYNAMIC_SIGFRAME */ |
| 8 3 5 34 2 10 7 7 7 105 3 3 10 91 95 2 93 4 97 4 93 100 50 6 4 2 38 39 | 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 /* * This contains the io-permission bitmap code - written by obz, with changes * by Linus. 32/64 bits code unification by Miguel Botón. */ #include <linux/capability.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/bitmap.h> #include <linux/ioport.h> #include <linux/sched.h> #include <linux/slab.h> #include <asm/io_bitmap.h> #include <asm/desc.h> #include <asm/syscalls.h> #ifdef CONFIG_X86_IOPL_IOPERM static atomic64_t io_bitmap_sequence; void io_bitmap_share(struct task_struct *tsk) { /* Can be NULL when current->thread.iopl_emul == 3 */ if (current->thread.io_bitmap) { /* * Take a refcount on current's bitmap. It can be used by * both tasks as long as none of them changes the bitmap. */ refcount_inc(¤t->thread.io_bitmap->refcnt); tsk->thread.io_bitmap = current->thread.io_bitmap; } set_tsk_thread_flag(tsk, TIF_IO_BITMAP); } static void task_update_io_bitmap(struct task_struct *tsk) { struct thread_struct *t = &tsk->thread; if (t->iopl_emul == 3 || t->io_bitmap) { /* TSS update is handled on exit to user space */ set_tsk_thread_flag(tsk, TIF_IO_BITMAP); } else { clear_tsk_thread_flag(tsk, TIF_IO_BITMAP); /* Invalidate TSS */ preempt_disable(); tss_update_io_bitmap(); preempt_enable(); } } void io_bitmap_exit(struct task_struct *tsk) { struct io_bitmap *iobm = tsk->thread.io_bitmap; tsk->thread.io_bitmap = NULL; task_update_io_bitmap(tsk); if (iobm && refcount_dec_and_test(&iobm->refcnt)) kfree(iobm); } /* * This changes the io permissions bitmap in the current task. */ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) { struct thread_struct *t = ¤t->thread; unsigned int i, max_long; struct io_bitmap *iobm; if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) return -EINVAL; if (turn_on && (!capable(CAP_SYS_RAWIO) || security_locked_down(LOCKDOWN_IOPORT))) return -EPERM; /* * If it's the first ioperm() call in this thread's lifetime, set the * IO bitmap up. ioperm() is much less timing critical than clone(), * this is why we delay this operation until now: */ iobm = t->io_bitmap; if (!iobm) { /* No point to allocate a bitmap just to clear permissions */ if (!turn_on) return 0; iobm = kmalloc(sizeof(*iobm), GFP_KERNEL); if (!iobm) return -ENOMEM; memset(iobm->bitmap, 0xff, sizeof(iobm->bitmap)); refcount_set(&iobm->refcnt, 1); } /* * If the bitmap is not shared, then nothing can take a refcount as * current can obviously not fork at the same time. If it's shared * duplicate it and drop the refcount on the original one. */ if (refcount_read(&iobm->refcnt) > 1) { iobm = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL); if (!iobm) return -ENOMEM; refcount_set(&iobm->refcnt, 1); io_bitmap_exit(current); } /* * Store the bitmap pointer (might be the same if the task already * head one). Must be done here so freeing the bitmap when all * permissions are dropped has the pointer set up. */ t->io_bitmap = iobm; /* Mark it active for context switching and exit to user mode */ set_thread_flag(TIF_IO_BITMAP); /* * Update the tasks bitmap. The update of the TSS bitmap happens on * exit to user mode. So this needs no protection. */ if (turn_on) bitmap_clear(iobm->bitmap, from, num); else bitmap_set(iobm->bitmap, from, num); /* * Search for a (possibly new) maximum. This is simple and stupid, * to keep it obviously correct: */ max_long = UINT_MAX; for (i = 0; i < IO_BITMAP_LONGS; i++) { if (iobm->bitmap[i] != ~0UL) max_long = i; } /* All permissions dropped? */ if (max_long == UINT_MAX) { io_bitmap_exit(current); return 0; } iobm->max = (max_long + 1) * sizeof(unsigned long); /* * Update the sequence number to force a TSS update on return to * user mode. */ iobm->sequence = atomic64_inc_return(&io_bitmap_sequence); return 0; } SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) { return ksys_ioperm(from, num, turn_on); } /* * The sys_iopl functionality depends on the level argument, which if * granted for the task is used to enable access to all 65536 I/O ports. * * This does not use the IOPL mechanism provided by the CPU as that would * also allow the user space task to use the CLI/STI instructions. * * Disabling interrupts in a user space task is dangerous as it might lock * up the machine and the semantics vs. syscalls and exceptions is * undefined. * * Setting IOPL to level 0-2 is disabling I/O permissions. Level 3 * 3 enables them. * * IOPL is strictly per thread and inherited on fork. */ SYSCALL_DEFINE1(iopl, unsigned int, level) { struct thread_struct *t = ¤t->thread; unsigned int old; if (level > 3) return -EINVAL; old = t->iopl_emul; /* No point in going further if nothing changes */ if (level == old) return 0; /* Trying to gain more privileges? */ if (level > old) { if (!capable(CAP_SYS_RAWIO) || security_locked_down(LOCKDOWN_IOPORT)) return -EPERM; } t->iopl_emul = level; task_update_io_bitmap(current); return 0; } #else /* CONFIG_X86_IOPL_IOPERM */ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) { return -ENOSYS; } SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) { return -ENOSYS; } SYSCALL_DEFINE1(iopl, unsigned int, level) { return -ENOSYS; } #endif |
| 1498 | 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 | // SPDX-License-Identifier: GPL-2.0 struct io_tctx_node { struct list_head ctx_node; struct task_struct *task; struct io_ring_ctx *ctx; }; int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); void io_uring_del_tctx_node(unsigned long index); int __io_uring_add_tctx_node(struct io_ring_ctx *ctx); int __io_uring_add_tctx_node_from_submit(struct io_ring_ctx *ctx); void io_uring_clean_tctx(struct io_uring_task *tctx); void io_uring_unreg_ringfd(void); int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, unsigned nr_args); int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, unsigned nr_args); /* * Note that this task has used io_uring. We use it for cancelation purposes. */ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; if (likely(tctx && tctx->last == ctx)) return 0; return __io_uring_add_tctx_node_from_submit(ctx); } |
| 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Dynamic loading of modules into the kernel. * * Rewritten by Richard Henderson <rth@tamu.edu> Dec 1996 * Rewritten again by Rusty Russell, 2002 */ #ifndef _LINUX_MODULE_H #define _LINUX_MODULE_H #include <linux/list.h> #include <linux/stat.h> #include <linux/buildid.h> #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> #include <linux/rbtree_latch.h> #include <linux/error-injection.h> #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> #include <linux/dynamic_debug.h> #include <linux/percpu.h> #include <asm/module.h> #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN struct modversion_info { unsigned long crc; char name[MODULE_NAME_LEN]; }; struct module; struct exception_table_entry; struct module_kobject { struct kobject kobj; struct module *mod; struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; } __randomize_layout; struct module_attribute { struct attribute attr; ssize_t (*show)(const struct module_attribute *, struct module_kobject *, char *); ssize_t (*store)(const struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); void (*free)(struct module *); }; struct module_version_attribute { struct module_attribute mattr; const char *module_name; const char *version; }; extern ssize_t __modver_version_show(const struct module_attribute *, struct module_kobject *, char *); extern const struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); extern void cleanup_module(void); #ifndef MODULE /** * module_init() - driver initialization entry point * @x: function to be run at kernel boot time or module insertion * * module_init() will either be called during do_initcalls() (if * builtin) or at module insertion time (if a module). There can only * be one per module. */ #define module_init(x) __initcall(x); /** * module_exit() - driver exit entry point * @x: function to be run when driver is removed * * module_exit() will wrap the driver clean-up code * with cleanup_module() when used with rmmod when * the driver is a module. If the driver is statically * compiled into the kernel, module_exit() has no effect. * There can only be one per module. */ #define module_exit(x) __exitcall(x); #else /* MODULE */ /* * In most cases loadable modules do not need custom * initcall levels. There are still some valid cases where * a driver may be needed early if built in, and does not * matter when built as a loadable module. Like bus * snooping debug drivers. */ #define early_initcall(fn) module_init(fn) #define core_initcall(fn) module_init(fn) #define core_initcall_sync(fn) module_init(fn) #define postcore_initcall(fn) module_init(fn) #define postcore_initcall_sync(fn) module_init(fn) #define arch_initcall(fn) module_init(fn) #define subsys_initcall(fn) module_init(fn) #define subsys_initcall_sync(fn) module_init(fn) #define fs_initcall(fn) module_init(fn) #define fs_initcall_sync(fn) module_init(fn) #define rootfs_initcall(fn) module_init(fn) #define device_initcall(fn) module_init(fn) #define device_initcall_sync(fn) module_init(fn) #define late_initcall(fn) module_init(fn) #define late_initcall_sync(fn) module_init(fn) #define console_initcall(fn) module_init(fn) /* Each module must use one module_init(). */ #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ int init_module(void) __copy(initfn) \ __attribute__((alias(#initfn))); \ ___ADDRESSABLE(init_module, __initdata); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ void cleanup_module(void) __copy(exitfn) \ __attribute__((alias(#exitfn))); \ ___ADDRESSABLE(cleanup_module, __exitdata); #endif /* This means "can be init if no module support, otherwise module load may call it." */ #ifdef CONFIG_MODULES #define __init_or_module #define __initdata_or_module #define __initconst_or_module #define __INIT_OR_MODULE .text #define __INITDATA_OR_MODULE .data #define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits #else #define __init_or_module __init #define __initdata_or_module __initdata #define __initconst_or_module __initconst #define __INIT_OR_MODULE __INIT #define __INITDATA_OR_MODULE __INITDATA #define __INITRODATA_OR_MODULE __INITRODATA #endif /*CONFIG_MODULES*/ struct module_kobject *lookup_or_create_module_kobject(const char *name); /* Generic info of form tag = "info" */ #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) /* Soft module dependencies. See man modprobe.d for details. * Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz") */ #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) /* * Weak module dependencies. See man modprobe.d for details. * Example: MODULE_WEAKDEP("module-foo") */ #define MODULE_WEAKDEP(_weakdep) MODULE_INFO(weakdep, _weakdep) /* * MODULE_FILE is used for generating modules.builtin * So, make it no-op when this is being built as a module */ #ifdef MODULE #define MODULE_FILE #else #define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE); #endif /* * The following license idents are currently accepted as indicating free * software modules * * "GPL" [GNU Public License v2] * "GPL v2" [GNU Public License v2] * "GPL and additional rights" [GNU Public License v2 rights and more] * "Dual BSD/GPL" [GNU Public License v2 * or BSD license choice] * "Dual MIT/GPL" [GNU Public License v2 * or MIT license choice] * "Dual MPL/GPL" [GNU Public License v2 * or Mozilla license choice] * * The following other idents are available * * "Proprietary" [Non free products] * * Both "GPL v2" and "GPL" (the latter also in dual licensed strings) are * merely stating that the module is licensed under the GPL v2, but are not * telling whether "GPL v2 only" or "GPL v2 or later". The reason why there * are two variants is a historic and failed attempt to convey more * information in the MODULE_LICENSE string. For module loading the * "only/or later" distinction is completely irrelevant and does neither * replace the proper license identifiers in the corresponding source file * nor amends them in any way. The sole purpose is to make the * 'Proprietary' flagging work and to refuse to bind symbols which are * exported with EXPORT_SYMBOL_GPL when a non free module is loaded. * * In the same way "BSD" is not a clear license information. It merely * states, that the module is licensed under one of the compatible BSD * license variants. The detailed and correct license information is again * to be found in the corresponding source files. * * There are dual licensed components, but when running with Linux it is the * GPL that is relevant so this is a non issue. Similarly LGPL linked with GPL * is a GPL combined work. * * This exists for several reasons * 1. So modinfo can show license info for users wanting to vet their setup * is free * 2. So the community can ignore bug reports including proprietary modules * 3. So vendors can do likewise based on their own policies */ #define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license) /* * Author(s), use "Name <email>" or just "Name", for multiple * authors use multiple MODULE_AUTHOR() statements/lines. */ #define MODULE_AUTHOR(_author) MODULE_INFO(author, _author) /* What your module does. */ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ extern typeof(name) __mod_device_table__##type##__##name \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) #endif /* Version of form [<epoch>:]<version>[-<extra-version>]. * Or for CVS/RCS ID version, everything but the number is stripped. * <epoch>: A (small) unsigned integer which allows you to start versions * anew. If not mentioned, it's zero. eg. "2:1.0" is after * "1:2.0". * <version>: The <version> may contain only alphanumerics and the * character `.'. Ordered by numeric sort for numeric parts, * ascii sort for ascii parts (as per RPM or DEB algorithm). * <extraversion>: Like <version>, but inserted for local * customizations, eg "rh3" or "rusty1". * Using this automatically adds a checksum of the .c files and the * local headers in "srcversion". */ #if defined(MODULE) || !defined(CONFIG_SYSFS) #define MODULE_VERSION(_version) MODULE_INFO(version, _version) #else #define MODULE_VERSION(_version) \ MODULE_INFO(version, _version); \ static const struct module_version_attribute __modver_attr \ __used __section("__modver") \ __aligned(__alignof__(struct module_version_attribute)) \ = { \ .mattr = { \ .attr = { \ .name = "version", \ .mode = S_IRUGO, \ }, \ .show = __modver_version_show, \ }, \ .module_name = KBUILD_MODNAME, \ .version = _version, \ } #endif /* Optional firmware file (or files) needed by the module * format is simply firmware file name. Multiple firmware * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) #define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, ns) struct notifier_block; #ifdef CONFIG_MODULES extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); #define symbol_get(x) ({ \ static const char __notrim[] \ __used __section(".no_trim_symbol") = __stringify(x); \ (typeof(&x))(__symbol_get(__stringify(x))); }) /* modules using other modules: kdb wants to see this. */ struct module_use { struct list_head source_list; struct list_head target_list; struct module *source, *target; }; enum module_state { MODULE_STATE_LIVE, /* Normal state. */ MODULE_STATE_COMING, /* Full formed, running module_init. */ MODULE_STATE_GOING, /* Going away. */ MODULE_STATE_UNFORMED, /* Still setting it up. */ }; struct mod_tree_node { struct module *mod; struct latch_tree_node node; }; enum mod_mem_type { MOD_TEXT = 0, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, MOD_MEM_NUM_TYPES, MOD_INVALID = -1, }; #define mod_mem_type_is_init(type) \ ((type) == MOD_INIT_TEXT || \ (type) == MOD_INIT_DATA || \ (type) == MOD_INIT_RODATA) #define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) #define mod_mem_type_is_text(type) \ ((type) == MOD_TEXT || \ (type) == MOD_INIT_TEXT) #define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) #define mod_mem_type_is_core_data(type) \ (mod_mem_type_is_core(type) && \ mod_mem_type_is_data(type)) #define for_each_mod_mem_type(type) \ for (enum mod_mem_type (type) = 0; \ (type) < MOD_MEM_NUM_TYPES; (type)++) #define for_class_mod_mem_type(type, class) \ for_each_mod_mem_type(type) \ if (mod_mem_type_is_##class(type)) struct module_memory { void *base; bool is_rox; unsigned int size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; #endif }; #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ #define __module_memory_align ____cacheline_aligned #else #define __module_memory_align #endif struct mod_kallsyms { Elf_Sym *symtab; unsigned int num_symtab; char *strtab; char *typetab; }; #ifdef CONFIG_LIVEPATCH /** * struct klp_modinfo - ELF information preserved from the livepatch module * * @hdr: ELF header * @sechdrs: Section header table * @secstrings: String table for the section headers * @symndx: The symbol table section index */ struct klp_modinfo { Elf_Ehdr hdr; Elf_Shdr *sechdrs; char *secstrings; unsigned int symndx; }; #endif struct module { enum module_state state; /* Member of list of modules */ struct list_head list; /* Unique handle for this module */ char name[MODULE_NAME_LEN]; #ifdef CONFIG_STACKTRACE_BUILD_ID /* Module build ID */ unsigned char build_id[BUILD_ID_SIZE_MAX]; #endif /* Sysfs stuff. */ struct module_kobject mkobj; struct module_attribute *modinfo_attrs; const char *version; const char *srcversion; struct kobject *holders_dir; /* Exported symbols */ const struct kernel_symbol *syms; const u32 *crcs; unsigned int num_syms; #ifdef CONFIG_ARCH_USES_CFI_TRAPS s32 *kcfi_traps; s32 *kcfi_traps_end; #endif /* Kernel parameters. */ #ifdef CONFIG_SYSFS struct mutex param_lock; #endif struct kernel_param *kp; unsigned int num_kp; /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; const u32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_MODULE_SIG /* Signature was verified. */ bool sig_ok; #endif bool async_probe_requested; /* Exception table */ unsigned int num_exentries; struct exception_table_entry *extable; /* Startup function. */ int (*init)(void); struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; unsigned long taints; /* same bits as kernel:taint_flags */ #ifdef CONFIG_GENERIC_BUG /* Support for BUG */ unsigned num_bugs; struct list_head bug_list; struct bug_entry *bug_table; #endif #ifdef CONFIG_KALLSYMS /* Protected by RCU and/or module_mutex: use rcu_dereference() */ struct mod_kallsyms __rcu *kallsyms; struct mod_kallsyms core_kallsyms; /* Section attributes */ struct module_sect_attrs *sect_attrs; /* Notes attributes */ struct module_notes_attrs *notes_attrs; #endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ char *args; #ifdef CONFIG_SMP /* Per-cpu data. */ void __percpu *percpu; unsigned int percpu_size; #endif void *noinstr_text_start; unsigned int noinstr_text_size; #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; tracepoint_ptr_t *tracepoints_ptrs; #endif #ifdef CONFIG_TREE_SRCU unsigned int num_srcu_structs; struct srcu_struct **srcu_struct_ptrs; #endif #ifdef CONFIG_BPF_EVENTS unsigned int num_bpf_raw_events; struct bpf_raw_event_map *bpf_raw_events; #endif #ifdef CONFIG_DEBUG_INFO_BTF_MODULES unsigned int btf_data_size; unsigned int btf_base_data_size; void *btf_data; void *btf_base_data; #endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; unsigned int num_jump_entries; #endif #ifdef CONFIG_TRACING unsigned int num_trace_bprintk_fmt; const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call **trace_events; unsigned int num_trace_events; struct trace_eval_map **trace_evals; unsigned int num_trace_evals; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD unsigned int num_ftrace_callsites; unsigned long *ftrace_callsites; #endif #ifdef CONFIG_KPROBES void *kprobes_text_start; unsigned int kprobes_text_size; unsigned long *kprobe_blacklist; unsigned int num_kprobe_blacklist; #endif #ifdef CONFIG_HAVE_STATIC_CALL_INLINE int num_static_call_sites; struct static_call_site *static_call_sites; #endif #if IS_ENABLED(CONFIG_KUNIT) int num_kunit_init_suites; struct kunit_suite **kunit_init_suites; int num_kunit_suites; struct kunit_suite **kunit_suites; #endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ bool klp_alive; /* ELF information */ struct klp_modinfo *klp_info; #endif #ifdef CONFIG_PRINTK_INDEX unsigned int printk_index_size; struct pi_entry **printk_index_start; #endif #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; /* What modules do I depend on? */ struct list_head target_list; /* Destruction function. */ void (*exit)(void); atomic_t refcnt; #endif #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; unsigned int num_ctors; #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif #ifdef CONFIG_DYNAMIC_DEBUG_CORE struct _ddebug_info dyndbg_info; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) { return sym->st_value; } #endif /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ static inline bool module_is_live(struct module *mod) { return mod->state != MODULE_STATE_GOING; } static inline bool module_is_coming(struct module *mod) { return mod->state == MODULE_STATE_COMING; } struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline bool within_module_mem_type(unsigned long addr, const struct module *mod, enum mod_mem_type type) { unsigned long base, size; base = (unsigned long)mod->mem[type].base; size = mod->mem[type].size; return addr - base < size; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { for_class_mod_mem_type(type, core) { if (within_module_mem_type(addr, mod, type)) return true; } return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { for_class_mod_mem_type(type, init) { if (within_module_mem_type(addr, mod, type)) return true; } return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return within_module_init(addr, mod) || within_module_core(addr, mod); } /* Search for module by name: must be in a RCU critical section. */ struct module *find_module(const char *name); extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(__stringify(x)) void symbol_put_addr(void *addr); /* Sometimes we know we already have a refcount, and it's easier not to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); /** * try_module_get() - take module refcount unless module is being removed * @module: the module we should check for * * Only try to get a module reference count if the module is not being removed. * This call will fail if the module is in the process of being removed. * * Care must also be taken to ensure the module exists and is alive prior to * usage of this call. This can be gauranteed through two means: * * 1) Direct protection: you know an earlier caller must have increased the * module reference through __module_get(). This can typically be achieved * by having another entity other than the module itself increment the * module reference count. * * 2) Implied protection: there is an implied protection against module * removal. An example of this is the implied protection used by kernfs / * sysfs. The sysfs store / read file operations are guaranteed to exist * through the use of kernfs's active reference (see kernfs_active()) and a * sysfs / kernfs file removal cannot happen unless the same file is not * active. Therefore, if a sysfs file is being read or written to the module * which created it must still exist. It is therefore safe to use * try_module_get() on module sysfs store / read ops. * * One of the real values to try_module_get() is the module_is_live() check * which ensures that the caller of try_module_get() can yield to userspace * module removal requests and gracefully fail if the module is on its way out. * * Returns true if the reference count was successfully incremented. */ extern bool try_module_get(struct module *module); /** * module_put() - release a reference count to a module * @module: the module we should release a reference count for * * If you successfully bump a reference count to a module with try_module_get(), * when you are finished you must call module_put() to release that reference * count. */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ static inline bool try_module_get(struct module *module) { return !module || module_is_live(module); } static inline void module_put(struct module *module) { } static inline void __module_get(struct module *module) { } #define symbol_put(x) do { } while (0) #define symbol_put_addr(p) do { } while (0) #endif /* CONFIG_MODULE_UNLOAD */ /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ ({ \ struct module *__mod = (mod); \ __mod ? __mod->name : "kernel"; \ }) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); extern void print_modules(void); static inline bool module_requested_async_probing(struct module *module) { return module && module->async_probe_requested; } static inline bool is_livepatch_module(struct module *mod) { #ifdef CONFIG_LIVEPATCH return mod->klp; #else return false; #endif } void set_module_sig_enforced(void); void module_for_each_mod(int(*func)(struct module *mod, void *data), void *data); #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) { return NULL; } static inline struct module *__module_text_address(unsigned long addr) { return NULL; } static inline bool is_module_address(unsigned long addr) { return false; } static inline bool is_module_percpu_address(unsigned long addr) { return false; } static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) { return false; } static inline bool is_module_text_address(unsigned long addr) { return false; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return false; } /* Get/put a kernel symbol (calls should be symmetric) */ #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); }) #define symbol_put(x) do { } while (0) #define symbol_put_addr(x) do { } while (0) static inline void __module_get(struct module *module) { } static inline bool try_module_get(struct module *module) { return true; } static inline void module_put(struct module *module) { } #define module_name(mod) "kernel" static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ return 0; } static inline int unregister_module_notifier(struct notifier_block *nb) { return 0; } #define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { } static inline bool module_requested_async_probing(struct module *module) { return false; } static inline void set_module_sig_enforced(void) { } /* Dereference module function descriptor */ static inline void *dereference_module_function_descriptor(struct module *mod, void *ptr) { return ptr; } static inline bool module_is_coming(struct module *mod) { return false; } static inline void module_for_each_mod(int(*func)(struct module *mod, void *data), void *data) { } #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS extern struct kset *module_kset; extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) /* BELOW HERE ALL THESE ARE OBSOLETE AND WILL VANISH */ #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); void module_bug_cleanup(struct module *); #else /* !CONFIG_GENERIC_BUG */ static inline void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { } static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_MITIGATION_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) { return true; } #endif #ifdef CONFIG_MODULE_SIG bool is_module_sig_enforced(void); static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ static inline bool is_module_sig_enforced(void) { return false; } static inline bool module_sig_ok(struct module *module) { return true; } #endif /* CONFIG_MODULE_SIG */ #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data); /* For kallsyms to ask for address resolution. namebuf should be at * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if * symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported); /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); #else /* CONFIG_MODULES && CONFIG_KALLSYMS */ static inline int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; } /* For kallsyms to ask for address resolution. NULL means not found. */ static inline int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { return 0; } static inline int lookup_module_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { return -ERANGE; } static inline unsigned long module_kallsyms_lookup_name(const char *name) { return 0; } static inline unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) { return 0; } #endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Connection Data Control (CDC) * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #ifndef SMC_CDC_H #define SMC_CDC_H #include <linux/kernel.h> /* max_t */ #include <linux/atomic.h> #include <linux/in.h> #include <linux/compiler.h> #include "smc.h" #include "smc_core.h" #include "smc_wr.h" #define SMC_CDC_MSG_TYPE 0xFE /* in network byte order */ union smc_cdc_cursor { /* SMC cursor */ struct { __be16 reserved; __be16 wrap; __be32 count; }; #ifdef KERNEL_HAS_ATOMIC64 atomic64_t acurs; /* for atomic processing */ #else u64 acurs; /* for atomic processing */ #endif } __aligned(8); /* in network byte order */ struct smc_cdc_msg { struct smc_wr_rx_hdr common; /* .type = 0xFE */ u8 len; /* 44 */ __be16 seqno; __be32 token; union smc_cdc_cursor prod; union smc_cdc_cursor cons; /* piggy backed "ack" */ struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; u8 reserved[18]; }; /* SMC-D cursor format */ union smcd_cdc_cursor { struct { u16 wrap; u32 count; struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; } __packed; #ifdef KERNEL_HAS_ATOMIC64 atomic64_t acurs; /* for atomic processing */ #else u64 acurs; /* for atomic processing */ #endif } __aligned(8); /* CDC message for SMC-D */ struct smcd_cdc_msg { struct smc_wr_rx_hdr common; /* Type = 0xFE */ u8 res1[7]; union smcd_cdc_cursor prod; union smcd_cdc_cursor cons; u8 res3[8]; } __aligned(8); static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { return conn->local_rx_ctrl.conn_state_flags.peer_conn_abort || conn->local_rx_ctrl.conn_state_flags.peer_conn_closed; } static inline bool smc_cdc_rxed_any_close_or_senddone( struct smc_connection *conn) { return smc_cdc_rxed_any_close(conn) || conn->local_rx_ctrl.conn_state_flags.peer_done_writing; } static inline void smc_curs_add(int size, union smc_host_cursor *curs, int value) { curs->count += value; if (curs->count >= size) { curs->wrap++; curs->count -= size; } } /* Copy cursor src into tgt */ static inline void smc_curs_copy(union smc_host_cursor *tgt, union smc_host_cursor *src, struct smc_connection *conn) { #ifndef KERNEL_HAS_ATOMIC64 unsigned long flags; spin_lock_irqsave(&conn->acurs_lock, flags); tgt->acurs = src->acurs; spin_unlock_irqrestore(&conn->acurs_lock, flags); #else atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); #endif } static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt, union smc_cdc_cursor *src, struct smc_connection *conn) { #ifndef KERNEL_HAS_ATOMIC64 unsigned long flags; spin_lock_irqsave(&conn->acurs_lock, flags); tgt->acurs = src->acurs; spin_unlock_irqrestore(&conn->acurs_lock, flags); #else atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); #endif } static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, union smcd_cdc_cursor *src, struct smc_connection *conn) { #ifndef KERNEL_HAS_ATOMIC64 unsigned long flags; spin_lock_irqsave(&conn->acurs_lock, flags); tgt->acurs = src->acurs; spin_unlock_irqrestore(&conn->acurs_lock, flags); #else atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); #endif } /* calculate cursor difference between old and new, where old <= new and * difference cannot exceed size */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) { if (old->wrap != new->wrap) return max_t(int, 0, ((size - old->count) + new->count)); return max_t(int, 0, (new->count - old->count)); } /* calculate cursor difference between old and new - returns negative * value in case old > new */ static inline int smc_curs_comp(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) { if (old->wrap > new->wrap || (old->wrap == new->wrap && old->count > new->count)) return -smc_curs_diff(size, new, old); return smc_curs_diff(size, old, new); } /* calculate cursor difference between old and new, where old <= new and * difference may exceed size */ static inline int smc_curs_diff_large(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) { if (old->wrap < new->wrap) return min_t(int, (size - old->count) + new->count + (new->wrap - old->wrap - 1) * size, size); if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ return min_t(int, (size - old->count) + new->count + (new->wrap + 0xffff - old->wrap) * size, size); return max_t(int, 0, (new->count - old->count)); } static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, union smc_host_cursor *save, struct smc_connection *conn) { smc_curs_copy(save, local, conn); peer->count = htonl(save->count); peer->wrap = htons(save->wrap); /* peer->reserved = htons(0); must be ensured by caller */ } static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer, struct smc_connection *conn, union smc_host_cursor *save) { struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; peer->common.type = local->common.type; peer->len = local->len; peer->seqno = htons(local->seqno); peer->token = htonl(local->token); smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn); smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; } static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local, union smc_cdc_cursor *peer, struct smc_connection *conn) { union smc_host_cursor temp, old; union smc_cdc_cursor net; smc_curs_copy(&old, local, conn); smc_curs_copy_net(&net, peer, conn); temp.count = ntohl(net.count); temp.wrap = ntohs(net.wrap); if ((old.wrap > temp.wrap) && temp.wrap) return; if ((old.wrap == temp.wrap) && (old.count > temp.count)) return; smc_curs_copy(local, &temp, conn); } static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_cdc_msg *peer, struct smc_connection *conn) { local->common.type = peer->common.type; local->len = peer->len; local->seqno = ntohs(peer->seqno); local->token = ntohl(peer->token); smc_cdc_cursor_to_host(&local->prod, &peer->prod, conn); smc_cdc_cursor_to_host(&local->cons, &peer->cons, conn); local->prod_flags = peer->prod_flags; local->conn_state_flags = peer->conn_state_flags; } static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smcd_cdc_msg *peer, struct smc_connection *conn) { union smc_host_cursor temp; temp.wrap = peer->prod.wrap; temp.count = peer->prod.count; smc_curs_copy(&local->prod, &temp, conn); temp.wrap = peer->cons.wrap; temp.count = peer->cons.count; smc_curs_copy(&local->cons, &temp, conn); local->prod_flags = peer->cons.prod_flags; local->conn_state_flags = peer->cons.conn_state_flags; } static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_cdc_msg *peer, struct smc_connection *conn) { if (conn->lgr->is_smcd) smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer, conn); else smcr_cdc_msg_to_host(local, peer, conn); } struct smc_cdc_tx_pend { struct smc_connection *conn; /* socket connection */ union smc_host_cursor cursor; /* tx sndbuf cursor sent */ union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ u16 ctrl_seq; /* conn. tx sequence # */ }; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_link *link, struct smc_wr_buf **wr_buf, struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend); int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn); int smcd_cdc_msg_send(struct smc_connection *conn); int smcr_cdc_msg_send_validation(struct smc_connection *conn, struct smc_cdc_tx_pend *pend, struct smc_wr_buf *wr_buf); int smc_cdc_init(void) __init; void smcd_cdc_rx_init(struct smc_connection *conn); #endif /* SMC_CDC_H */ |
| 27 221 221 1 32 264 264 263 264 271 221 264 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> #include <net/flow_offload.h> #include <net/netfilter/nf_flow_table.h> struct flow_offload_xdp_ft { struct list_head head; struct nf_flowtable *ft; struct rcu_head rcuhead; }; struct flow_offload_xdp { struct hlist_node hnode; unsigned long net_device_addr; struct list_head head; }; #define NF_XDP_HT_BITS 4 static DEFINE_HASHTABLE(nf_xdp_hashtable, NF_XDP_HT_BITS); static DEFINE_MUTEX(nf_xdp_hashtable_lock); /* caller must hold rcu read lock */ struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev) { unsigned long key = (unsigned long)dev; struct flow_offload_xdp *iter; hash_for_each_possible_rcu(nf_xdp_hashtable, iter, hnode, key) { if (key == iter->net_device_addr) { struct flow_offload_xdp_ft *ft_elem; /* The user is supposed to insert a given net_device * just into a single nf_flowtable so we always return * the first element here. */ ft_elem = list_first_or_null_rcu(&iter->head, struct flow_offload_xdp_ft, head); return ft_elem ? ft_elem->ft : NULL; } } return NULL; } static int nf_flowtable_by_dev_insert(struct nf_flowtable *ft, const struct net_device *dev) { struct flow_offload_xdp *iter, *elem = NULL; unsigned long key = (unsigned long)dev; struct flow_offload_xdp_ft *ft_elem; ft_elem = kzalloc(sizeof(*ft_elem), GFP_KERNEL_ACCOUNT); if (!ft_elem) return -ENOMEM; ft_elem->ft = ft; mutex_lock(&nf_xdp_hashtable_lock); hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) { if (key == iter->net_device_addr) { elem = iter; break; } } if (!elem) { elem = kzalloc(sizeof(*elem), GFP_KERNEL_ACCOUNT); if (!elem) goto err_unlock; elem->net_device_addr = key; INIT_LIST_HEAD(&elem->head); hash_add_rcu(nf_xdp_hashtable, &elem->hnode, key); } list_add_tail_rcu(&ft_elem->head, &elem->head); mutex_unlock(&nf_xdp_hashtable_lock); return 0; err_unlock: mutex_unlock(&nf_xdp_hashtable_lock); kfree(ft_elem); return -ENOMEM; } static void nf_flowtable_by_dev_remove(struct nf_flowtable *ft, const struct net_device *dev) { struct flow_offload_xdp *iter, *elem = NULL; unsigned long key = (unsigned long)dev; mutex_lock(&nf_xdp_hashtable_lock); hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) { if (key == iter->net_device_addr) { elem = iter; break; } } if (elem) { struct flow_offload_xdp_ft *ft_elem, *ft_next; list_for_each_entry_safe(ft_elem, ft_next, &elem->head, head) { if (ft_elem->ft == ft) { list_del_rcu(&ft_elem->head); kfree_rcu(ft_elem, rcuhead); } } if (list_empty(&elem->head)) hash_del_rcu(&elem->hnode); else elem = NULL; } mutex_unlock(&nf_xdp_hashtable_lock); if (elem) { synchronize_rcu(); kfree(elem); } } int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd) { switch (cmd) { case FLOW_BLOCK_BIND: return nf_flowtable_by_dev_insert(flowtable, dev); case FLOW_BLOCK_UNBIND: nf_flowtable_by_dev_remove(flowtable, dev); return 0; } WARN_ON_ONCE(1); return 0; } |
| 59 1 1 57 32 3 24 4 4 10 5 1 4 4 9 9 21 21 19 3 4 10 2 23 23 24 24 24 2 21 59 59 57 24 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2010: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> * Copyright (C) 2015: Linus Lüssing <linus.luessing@c0d3.blue> * * Based on the MLD support added to br_multicast.c by YOSHIFUJI Hideaki. */ #include <linux/skbuff.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/addrconf.h> #include <net/ip6_checksum.h> static int ipv6_mc_check_ip6hdr(struct sk_buff *skb) { const struct ipv6hdr *ip6h; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*ip6h); if (!pskb_may_pull(skb, offset)) return -EINVAL; ip6h = ipv6_hdr(skb); if (ip6h->version != 6) return -EINVAL; len = offset + ntohs(ip6h->payload_len); if (skb->len < len || len <= offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ipv6_mc_check_exthdrs(struct sk_buff *skb) { const struct ipv6hdr *ip6h; int offset; u8 nexthdr; __be16 frag_off; ip6h = ipv6_hdr(skb); if (ip6h->nexthdr != IPPROTO_HOPOPTS) return -ENOMSG; nexthdr = ip6h->nexthdr; offset = skb_network_offset(skb) + sizeof(*ip6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) return -EINVAL; if (nexthdr != IPPROTO_ICMPV6) return -ENOMSG; skb_set_transport_header(skb, offset); return 0; } static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct mld2_report); return ipv6_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ipv6_mc_check_mld_query(struct sk_buff *skb) { unsigned int transport_len = ipv6_transport_len(skb); struct mld_msg *mld; unsigned int len; /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) return -EINVAL; /* MLDv1? */ if (transport_len != sizeof(struct mld_msg)) { /* or MLDv2? */ if (transport_len < sizeof(struct mld2_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct mld2_query); if (!ipv6_mc_may_pull(skb, len)) return -EINVAL; } mld = (struct mld_msg *)skb_transport_header(skb); /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer * all-nodes destination address (ff02::1) for general queries */ if (ipv6_addr_any(&mld->mld_mca) && !ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) return -EINVAL; return 0; } static int ipv6_mc_check_mld_msg(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg); struct mld_msg *mld; if (!ipv6_mc_may_pull(skb, len)) return -ENODATA; mld = (struct mld_msg *)skb_transport_header(skb); switch (mld->mld_type) { case ICMPV6_MGM_REDUCTION: case ICMPV6_MGM_REPORT: return 0; case ICMPV6_MLD2_REPORT: return ipv6_mc_check_mld_reportv2(skb); case ICMPV6_MGM_QUERY: return ipv6_mc_check_mld_query(skb); default: return -ENODATA; } } static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo); } static int ipv6_mc_check_icmpv6(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct icmp6hdr); unsigned int transport_len = ipv6_transport_len(skb); struct sk_buff *skb_chk; if (!ipv6_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ipv6_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ipv6_mc_check_mld - checks whether this is a sane MLD packet * @skb: the skb to validate * * Checks whether an IPv6 packet is a valid MLD packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an ICMPv6 packet * with a hop-by-hop option. * -ENODATA: IP+ICMPv6 header with hop-by-hop option validation succeeded * but it is not an MLD packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ipv6_mc_check_mld(struct sk_buff *skb) { int ret; ret = ipv6_mc_check_ip6hdr(skb); if (ret < 0) return ret; ret = ipv6_mc_check_exthdrs(skb); if (ret < 0) return ret; ret = ipv6_mc_check_icmpv6(skb); if (ret < 0) return ret; return ipv6_mc_check_mld_msg(skb); } EXPORT_SYMBOL(ipv6_mc_check_mld); |
| 56883 2878 55848 6430 2808 9016 50181 876 9067 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> #include <linux/cleanup.h> #include <linux/err.h> struct file; extern void fput(struct file *); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); /* either a reference to struct file + flags * (cloned vs. borrowed, pos locked), with * flags stored in lower bits of value, * or empty (represented by 0). */ struct fd { unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 #define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) static inline bool fd_empty(struct fd f) { return unlikely(!f.word); } #define EMPTY_FD (struct fd){0} static inline struct fd BORROWED_FD(struct file *f) { return (struct fd){(unsigned long)f}; } static inline struct fd CLONED_FD(struct file *f) { return (struct fd){(unsigned long)f | FDPUT_FPUT}; } static inline void fdput(struct fd fd) { if (fd.word & FDPUT_FPUT) fput(fd_file(fd)); } extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); extern void __f_unlock_pos(struct file *); struct fd fdget(unsigned int fd); struct fd fdget_raw(unsigned int fd); struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { if (f.word & FDPUT_POS_UNLOCK) __f_unlock_pos(fd_file(f)); fdput(f); } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T)) /* * take_fd() will take care to set @fd to -EBADF ensuring that * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it * easier to rely on CLASS(get_unused_fd): * * struct file *f; * * CLASS(get_unused_fd, fd)(O_CLOEXEC); * if (fd < 0) * return fd; * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); */ #define take_fd(fd) __get_and_null(fd, -EBADF) extern void fd_install(unsigned int fd, struct file *file); int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; #endif /* __LINUX_FILE_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM udp #if !defined(_TRACE_UDP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_UDP_H #include <linux/udp.h> #include <linux/tracepoint.h> #include <trace/events/net_probe_common.h> TRACE_EVENT(udp_fail_queue_rcv_skb, TP_PROTO(int rc, struct sock *sk, struct sk_buff *skb), TP_ARGS(rc, sk, skb), TP_STRUCT__entry( __field(int, rc) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( const struct udphdr *uh = (const struct udphdr *)udp_hdr(skb); __entry->rc = rc; /* for filtering use */ __entry->sport = ntohs(uh->source); __entry->dport = ntohs(uh->dest); __entry->family = sk->sk_family; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, uh, __entry->saddr, __entry->daddr); ), TP_printk("rc=%d family=%s src=%pISpc dest=%pISpc", __entry->rc, show_family_name(__entry->family), __entry->saddr, __entry->daddr) ); #endif /* _TRACE_UDP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2537 10378 10162 2323 2535 2536 10539 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Latched RB-trees * * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> * * Since RB-trees have non-atomic modifications they're not immediately suited * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for * lockless lookups; we cannot guarantee they return a correct result. * * The simplest solution is a seqlock + RB-tree, this will allow lockless * lookups; but has the constraint (inherent to the seqlock) that read sides * cannot nest in write sides. * * If we need to allow unconditional lookups (say as required for NMI context * usage) we need a more complex setup; this data structure provides this by * employing the latch technique -- see @write_seqcount_latch_begin -- to * implement a latched RB-tree which does allow for unconditional lookups by * virtue of always having (at least) one stable copy of the tree. * * However, while we have the guarantee that there is at all times one stable * copy, this does not guarantee an iteration will not observe modifications. * What might have been a stable copy at the start of the iteration, need not * remain so for the duration of the iteration. * * Therefore, this does require a lockless RB-tree iteration to be non-fatal; * see the comment in lib/rbtree.c. Note however that we only require the first * condition -- not seeing partial stores -- because the latch thing isolates * us from loops. If we were to interrupt a modification the lookup would be * pointed at the stable tree and complete while the modification was halted. */ #ifndef RB_TREE_LATCH_H #define RB_TREE_LATCH_H #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/rcupdate.h> struct latch_tree_node { struct rb_node node[2]; }; struct latch_tree_root { seqcount_latch_t seq; struct rb_root tree[2]; }; /** * latch_tree_ops - operators to define the tree order * @less: used for insertion; provides the (partial) order between two elements. * @comp: used for lookups; provides the order between the search key and an element. * * The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * latch_tree_find(). */ struct latch_tree_ops { bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); int (*comp)(void *key, struct latch_tree_node *b); }; static __always_inline struct latch_tree_node * __lt_from_rb(struct rb_node *node, int idx) { return container_of(node, struct latch_tree_node, node[idx]); } static __always_inline void __lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) { struct rb_root *root = <r->tree[idx]; struct rb_node **link = &root->rb_node; struct rb_node *node = <n->node[idx]; struct rb_node *parent = NULL; struct latch_tree_node *ltp; while (*link) { parent = *link; ltp = __lt_from_rb(parent, idx); if (less(ltn, ltp)) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node_rcu(node, parent, link); rb_insert_color(node, root); } static __always_inline void __lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) { rb_erase(<n->node[idx], <r->tree[idx]); } static __always_inline struct latch_tree_node * __lt_find(void *key, struct latch_tree_root *ltr, int idx, int (*comp)(void *key, struct latch_tree_node *node)) { struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); struct latch_tree_node *ltn; int c; while (node) { ltn = __lt_from_rb(node, idx); c = comp(key, ltn); if (c < 0) node = rcu_dereference_raw(node->rb_left); else if (c > 0) node = rcu_dereference_raw(node->rb_right); else return ltn; } return NULL; } /** * latch_tree_insert() - insert @node into the trees @root * @node: nodes to insert * @root: trees to insert @node into * @ops: operators defining the node order * * It inserts @node into @root in an ordered fashion such that we can always * observe one complete tree. See the comment for write_seqcount_latch_begin(). * * The inserts use rcu_assign_pointer() to publish the element such that the * tree structure is stored before we can observe the new @node. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_insert(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { write_seqcount_latch_begin(&root->seq); __lt_insert(node, root, 0, ops->less); write_seqcount_latch(&root->seq); __lt_insert(node, root, 1, ops->less); write_seqcount_latch_end(&root->seq); } /** * latch_tree_erase() - removes @node from the trees @root * @node: nodes to remote * @root: trees to remove @node from * @ops: operators defining the node order * * Removes @node from the trees @root in an ordered fashion such that we can * always observe one complete tree. See the comment for * write_seqcount_latch_begin(). * * It is assumed that @node will observe one RCU quiescent state before being * reused of freed. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_erase(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { write_seqcount_latch_begin(&root->seq); __lt_erase(node, root, 0); write_seqcount_latch(&root->seq); __lt_erase(node, root, 1); write_seqcount_latch_end(&root->seq); } /** * latch_tree_find() - find the node matching @key in the trees @root * @key: search key * @root: trees to search for @key * @ops: operators defining the node order * * Does a lockless lookup in the trees @root for the node matching @key. * * It is assumed that this is called while holding the appropriate RCU read * side lock. * * If the operators define a partial order on the elements (there are multiple * elements which have the same key value) it is undefined which of these * elements will be found. Nor is it possible to iterate the tree to find * further elements with the same key value. * * Returns: a pointer to the node matching @key or NULL. */ static __always_inline struct latch_tree_node * latch_tree_find(void *key, struct latch_tree_root *root, const struct latch_tree_ops *ops) { struct latch_tree_node *node; unsigned int seq; do { seq = read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } #endif /* RB_TREE_LATCH_H */ |
| 12 48 48 50 50 50 430 50 392 392 391 392 6 346 153 391 392 958 958 958 35 854 167 788 81 855 854 35 738 4 739 14 336 41 40 38 40 2 50 41 426 88 72 65 24 429 392 430 429 430 430 42 430 430 430 430 430 17 19 429 1 14 12 2 379 50 428 174 332 330 329 5 429 429 427 3 1 428 134 392 32 392 392 6 392 346 2 153 227 39 61 13 226 6 226 228 191 5 87 2 87 368 429 429 429 429 428 581 4 582 50 50 47 47 6 6 4 47 47 47 46 6 380 381 322 322 381 384 83 381 248 381 50 651 14 50 50 50 48 6 48 33 5 14 45 14 45 46 39 48 48 623 623 622 623 1 623 666 653 13 13 13 12 5 13 13 11 11 48 48 14 48 39 48 45 48 48 48 48 48 48 48 48 50 45 44 48 1 48 44 45 45 45 45 45 48 47 48 48 48 1 15 48 46 48 47 48 47 47 47 47 47 47 41 47 47 47 47 2 46 39 44 32 7 37 46 4 46 46 46 45 46 46 48 48 48 1 46 48 48 48 48 46 48 47 48 45 45 48 48 46 42 48 48 1 47 48 48 48 18 46 47 14 48 48 48 45 50 50 6 48 50 50 6 10 48 50 48 48 48 48 6 48 48 48 48 48 48 2 48 48 48 48 48 48 48 48 48 48 6 3 40 1 26 38 38 41 41 41 37 37 41 41 33 48 26 48 48 26 26 48 48 14 14 14 14 28 28 19 26 50 50 50 46 47 47 47 3 33 33 10 46 37 46 50 2 2 50 1 50 48 50 50 5 50 50 50 50 50 5 50 50 5 50 50 50 47 50 50 50 6 6 48 50 49 50 50 50 50 50 50 40 50 50 47 47 44 35 47 40 50 50 50 50 50 50 48 50 46 50 50 50 50 50 48 47 50 50 47 46 50 47 50 40 50 50 47 50 14 14 14 50 50 50 50 50 50 50 50 50 49 41 49 50 50 50 50 50 50 50 50 50 2 49 50 50 49 50 49 50 50 50 50 50 50 50 49 50 50 50 41 49 48 49 50 50 50 50 50 50 35 34 50 50 50 50 50 50 2 2 2 1 2 2 1 1 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <linux/mmu_notifier.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; #ifdef CONFIG_MEMCG /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ int *proactive_swappiness; #endif /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Not allow cache_trim_mode to be turned on as part of reclaim? */ unsigned int no_cache_trim_mode:1; /* Has cache_trim_mode failed at least once? */ unsigned int cache_trim_mode_failed:1; /* Proactive reclaim invoked by userspace through memory.reclaim */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; /* Shared cgroup tree walk failed, rescan the whole tree */ unsigned int memcg_full_walk:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness = 60; #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /* * Returns true for reclaim on the root cgroup. This is true for direct * allocator reclaim and reclaim through cgroup interfaces on the root cgroup. */ static bool root_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup); } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { if (sc->proactive && sc->proactive_swappiness) return *sc->proactive_swappiness; return mem_cgroup_swappiness(memcg); } #else static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool root_reclaim(struct scan_control *sc) { return true; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { return READ_ONCE(vm_swappiness); } #endif /* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to * and including the specified highidx * @zone: The current zone in the iterator * @pgdat: The pgdat which node_zones are being iterated * @idx: The index variable * @highidx: The index of the highest zone to return * * This macro iterates through all managed zones up to and including the specified highidx. * The zone iterator enters an invalid state after macro call and must be reinitialized * before it can be used again. */ #define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx) \ for ((idx) = 0, (zone) = (pgdat)->node_zones; \ (idx) <= (highidx); \ (idx)++, (zone)++) \ if (!managed_zone(zone)) \ continue; \ else static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. */ static void flush_reclaim_state(struct scan_control *sc) { /* * Currently, reclaim_state->reclaimed includes three types of pages * freed outside of vmscan: * (1) Slab pages. * (2) Clean file pages from pruned inodes (on highmem systems). * (3) XFS freed buffer pages. * * For all of these cases, we cannot universally link the pages to a * single memcg. For example, a memcg-aware shrinker can free one object * charged to the target memcg, causing an entire page to be freed. * If we count the entire page as reclaimed from the memcg, we end up * overestimating the reclaimed amount (potentially under-reclaiming). * * Only count such pages for global reclaim to prevent under-reclaiming * from the target memcg; preventing unnecessary retries during memcg * charging and false positives from proactive reclaim. * * For uncommon cases where the freed pages were actually mostly * charged to the target memcg, we end up underestimating the reclaimed * amount. This should be fine. The freed pages will be uncharged * anyway, even if they are not counted here properly, and we will be * able to make forward progress in charging (which is usually in a * retry loop). * * We can go one step further, and report the uncharged objcg pages in * memcg reclaim, to make reporting more accurate and reduce * underestimation, but it's probably not worth the complexity for now. */ if (current->reclaim_state && root_reclaim(sc)) { sc->nr_reclaimed += current->reclaim_state->reclaimed; current->reclaim_state->reclaimed = 0; } } static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; if (next_demotion_node(nid) == NUMA_NO_NODE) return false; return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); /* * If there are no reclaimable file-backed or anonymous pages, * ensure zones with sufficient free pages are not skipped. * This prevents zones like DMA32 from being ignored in reclaim * scenarios where they can still help alleviate memory pressure. */ if (nr == 0) nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; struct zone *zone; for_each_managed_zone_pgdat(zone, lruvec_pgdat(lruvec), zid, zone_idx) { if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; struct mem_cgroup *memcg = NULL; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); return freed; } void drop_slab(void) { int nid; int shift = 0; unsigned long freed; do { freed = 0; for_each_online_node(nid) { if (fatal_signal_pending(current)) return; freed += drop_slab_node(nid); } } while ((freed >> shift++) > 1); } #define CHECK_RECLAIMER_OFFSET(type) \ do { \ BUILD_BUG_ON(PGSTEAL_##type - PGSTEAL_KSWAPD != \ PGDEMOTE_##type - PGDEMOTE_KSWAPD); \ BUILD_BUG_ON(PGSTEAL_##type - PGSTEAL_KSWAPD != \ PGSCAN_##type - PGSCAN_KSWAPD); \ } while (0) static int reclaimer_offset(struct scan_control *sc) { CHECK_RECLAIMER_OFFSET(DIRECT); CHECK_RECLAIMER_OFFSET(KHUGEPAGED); CHECK_RECLAIMER_OFFSET(PROACTIVE); if (current_is_kswapd()) return 0; if (current_is_khugepaged()) return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; if (sc->proactive) return PGSTEAL_PROACTIVE - PGSTEAL_KSWAPD; return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; struct zone *zone; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for_each_managed_zone_pgdat(zone, pgdat, i, MAX_NR_ZONES - 1) { reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle user workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_USER_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_folio_list() for each dirty folio. * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug, struct list_head *folio_list) { /* * If the folio is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this folio's queue, we can perform writeback even if that * will block. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, .swap_plug = plug, }; /* * The large shmem folio can be split if CONFIG_THP_SWAP is * not enabled or contiguous swap entries are failed to * allocate. */ if (shmem_mapping(mapping) && folio_test_large(folio)) wbc.list = folio_list; folio_set_reclaim(folio); res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } if (!folio_test_writeback(folio)) { /* synchronous write or broken a_ops? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (!folio_test_swapcache(folio)) spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio->swap; if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); __delete_from_swap_cache(folio, swap, shadow); memcg1_swapout(folio, swap); xa_unlock_irq(&mapping->i_pages); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: xa_unlock_irq(&mapping->i_pages); if (!folio_test_swapcache(folio)) spin_unlock(&mapping->host->i_lock); return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; #ifdef CONFIG_LRU_GEN /* * Only used on a mapped folio in the eviction (rmap walk) path, where promotion * needs to be done by taking the folio off the LRU list and then adding it back * with PG_active set. In contrast, the aging (page table walk) path uses * folio_update_gen(). */ static bool lru_gen_set_refs(struct folio *folio) { /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return false; } set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_workingset)); return true; } #else static bool lru_gen_set_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; unsigned long vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* * There are two cases to consider. * 1) Rmap lock contention: rotate. * 2) Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (lru_gen_enabled()) { if (!referenced_ptes) return FOLIOREF_RECLAIM; return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP; } referenced_folio = folio_test_clear_referenced(folio); if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } struct folio *alloc_migrate_folio(struct folio *src, unsigned long private) { struct folio *dst; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; dst = alloc_migration_target(src, (unsigned long)mtc); if (dst) return dst; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(src, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask, .reason = MR_DEMOTION, }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_migrate_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0, nr_demoted = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; folio_batch_init(&free_folios); memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; if (folio_contain_hwpoisoned_page(folio)) { unmap_poisoned_folio(folio, folio_pfn(folio), false); folio_unlock(folio); folio_put(folio); continue; } VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the folio for immediate * reclaim and continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask)) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, 1, NULL)) goto activate_locked; /* * Split partially mapped folios right away. * We can free the unmapped pages without IO. */ if (data_race(!list_empty(&folio->_deferred_list) && folio_test_partially_mapped(folio)) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOWARN)) { int __maybe_unused order = folio_order(folio); if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (nr_pages >= HPAGE_PMD_NR) { count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } #endif count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); if (folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOWARN)) goto activate_locked_split; } /* * Normally the folio will be dirtied in unmap because its * pte should be dirty. A special case is MADV_FREE page. The * page's pte could have dirty bit cleared but the folio's * SwapBacked flag is still set because clearing the dirty bit * and SwapBacked flag has no lock protected. For such folio, * unmap will not set dirty bit for it, so folio reclaim will * not write the folio out. This can cause data corruption when * the folio is swapped in later. Always setting the dirty flag * for the folio solves the problem. */ folio_mark_dirty(folio); } } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; /* * Without TTU_SYNC, try_to_unmap will only begin to * hold PTL from the first present PTE within a large * folio. Some initial PTEs might be skipped due to * races with parallel PTE writes in which PTEs can be * cleared temporarily before being written new present * values. This will lead to a large folio is still * mapped while some subpages have been partially * unmapped after try_to_unmap; TTU_SYNC helps * try_to_unmap acquire PTL from the first PTE, * eliminating the influence of temporary PTE values. */ if (folio_test_large(folio)) flags |= TTU_SYNC; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } /* * Folio is unmapped now so it cannot be newly pinned anymore. * No point in trying to reclaim folio if it is pinned. * Furthermore we don't want to reclaim underlying fs metadata * if the folio is pinned and thus potentially modified by the * pinning process as that may upset the filesystem. */ if (folio_maybe_dma_pinned(folio)) goto activate_locked; mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug, folio_list)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: /* * If shmem folio is split when writeback to swap, * the tail pages will make their own pass through * this function and be accounted then. */ if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } goto activate_locked; case PAGE_SUCCESS: if (nr_pages > 1 && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); } continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ nr_demoted = demote_folio_list(&demote_folios, pgdat); nr_reclaimed += nr_demoted; stat->nr_demoted += nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ list_splice_init(&demote_folios, folio_list); /* * goto retry to reclaim the undemoted folios in folio_list if * desired. * * Reclaiming directly from top tier nodes is not often desired * due to it breaking the LRU ordering: in general memory * should be reclaimed from lower tier nodes and demoted from * top tier nodes. * * However, disabling reclaim from top tier nodes entirely * would cause ooms in edge scenarios where lower tier memory * is unreclaimable for whatever reason, eg memory being * mlocked or too hot to reclaim. We can disable reclaim * from top tier nodes in proactive reclaim though as that is * not real memory pressure. */ if (!sc->proactive) { do_demote_pass = false; goto retry; } } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !__folio_test_movable(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; unsigned long max_nr_skipped = 0; LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; /* Using max_nr_skipped to prevent hard LOCKUP*/ if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED && (folio_zonenum(folio) > sc->reclaim_idx)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; max_nr_skipped++; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: true if the folio was removed from an LRU list. * false if the folio was not on an LRU list. */ bool folio_isolate_lru(struct folio *folio) { bool ret = false; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = true; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static bool too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return false; if (!writeback_throttling_sane(sc)) return false; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if (gfp_has_io_fs(sc->gfp_mask)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; struct folio_batch free_folios; folio_batch_init(&free_folios); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } if (free_folios.nr) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = PGSCAN_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc), stat.nr_demoted); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&lruvec->lru_lock); lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; bool file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_needs_release(folio) && folio_trylock(folio)) { filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&lruvec->lru_lock); if (nr_rotated) lru_note_cost(lruvec, file, 0, nr_rotated); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &stat, true); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } trace_mm_vmscan_reclaim_pages(pgdat->node_id, sc.nr_scanned, nr_reclaimed, &stat); return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats in rate-limited way as we don't need * most accurate stats here. We may switch to regular stats flushing * in the future once it is cheap enough. */ mem_cgroup_flush_stats_ratelimited(sc->target_mem_cgroup); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) && !sc->no_cache_trim_mode) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; struct zone *zone; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for_each_managed_zone_pgdat(zone, pgdat, z, MAX_NR_ZONES - 1) { total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } static inline void calculate_pressure_balance(struct scan_control *sc, int swappiness, u64 *fraction, u64 *denominator) { unsigned long anon_cost, file_cost, total_cost; unsigned long ap, fp; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[WORKINGSET_ANON] = ap; fraction[WORKINGSET_FILE] = fp; *denominator = ap + fp; } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); int swappiness = sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; calculate_pressure_balance(sc, swappiness, fraction, &denominator); out: for_each_evictable_lru(lru) { bool file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct pglist_data *pgdat, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(pgdat->node_id, sc); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif static bool should_walk_mmu(void) { return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK); } static bool should_clear_pmd_young(void) { return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG); } /****************************************************************************** * shorthand helpers ******************************************************************************/ #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } #define evictable_min_seq(min_seq, swappiness) \ min((min_seq)[!(swappiness)], (min_seq)[(swappiness) <= MAX_SWAPPINESS]) #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) #define for_each_evictable_type(type, swappiness) \ for ((type) = !(swappiness); (type) <= ((swappiness) <= MAX_SWAPPINESS); (type)++) #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* see the comment in mem_cgroup_lruvec() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &pgdat->__lruvec; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!sc->may_swap) return 0; if (!can_demote(pgdat->node_id, sc) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return sc_swappiness(sc, memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { int type; for (type = 0; type < ANON_AND_FILE; type++) { int n = get_nr_gens(lruvec, type); if (n < MIN_NR_GENS || n > MAX_NR_GENS) return false; } return true; } /****************************************************************************** * Bloom filters ******************************************************************************/ /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = mm_state->filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(mm_state->filters[gen], filter); } /****************************************************************************** * mm_struct list ******************************************************************************/ #ifdef CONFIG_LRU_GEN_WALKS_MMU static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return &lruvec->mm_state; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { int key; struct mm_struct *mm; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return NULL; clear_bit(key, &mm->lru_gen.bitmap); return mmget_not_zero(mm) ? mm : NULL; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* the first addition since the last iteration */ if (mm_state->tail == &mm_list->fifo) mm_state->tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* where the current iteration continues after */ if (mm_state->head == &mm->lru_gen.list) mm_state->head = mm_state->head->prev; /* where the last iteration ended before */ if (mm_state->tail == &mm->lru_gen.list) mm_state->tail = mm_state->tail->next; } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; /* migration can happen before addition */ if (!mm->lru_gen.memcg) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { return NULL; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return NULL; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { return NULL; } #endif static void reset_mm_stats(struct lru_gen_mm_walk *walk, bool last) { int i; int hist; struct lruvec *lruvec = walk->lruvec; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); hist = lru_hist_from_seq(walk->seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(mm_state->stats[hist][i], mm_state->stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(walk->seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(mm_state->stats[hist][i], 0); } } static bool iterate_mm_list(struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = false; struct mm_struct *mm = NULL; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* * mm_state->seq is incremented after each iteration of mm_list. There * are three interesting cases for this page table walker: * 1. It tries to start a new iteration with a stale max_seq: there is * nothing left to do. * 2. It started the next iteration: it needs to reset the Bloom filter * so that a fresh set of PTE tables can be recorded. * 3. It ended the current iteration: it needs to reset the mm stats * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->seq); if (walk->seq <= mm_state->seq) goto done; if (!mm_state->head) mm_state->head = &mm_list->fifo; if (mm_state->head == &mm_list->fifo) first = true; do { mm_state->head = mm_state->head->next; if (mm_state->head == &mm_list->fifo) { WRITE_ONCE(mm_state->seq, mm_state->seq + 1); last = true; break; } /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == mm_state->head) { mm_state->tail = mm_state->head->next; walk->force_scan = true; } } while (!(mm = get_next_mm(walk))); done: if (*iter || last) reset_mm_stats(walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(mm_state, walk->seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < seq); if (seq > mm_state->seq) { mm_state->head = NULL; mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * PID controller ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { int i; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->gain = gain; pos->refaulted = pos->total = 0; for (i = tier % MAX_NR_TIERS; i <= min(tier, MAX_NR_TIERS - 1); i++) { pos->refaulted += lrugen->avg_refaulted[type][i] + atomic_long_read(&lrugen->refaulted[hist][type][i]); pos->total += lrugen->avg_total[type][i] + lrugen->protected[hist][type][i] + atomic_long_read(&lrugen->evicted[hist][type][i]); } } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + lrugen->protected[hist][type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); WRITE_ONCE(lrugen->protected[hist][type][tier], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) { set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced)); return -1; } do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) return -1; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lruvec *lruvec = walk->lruvec; struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (!vma_has_recency(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->swappiness; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->swappiness; if (walk->swappiness > MAX_SWAPPINESS) return true; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return -1; return pfn; } static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return -1; return pfn; } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct folio *folio = pfn_folio(pfn); if (folio_lru_gen(folio) < 0) return NULL; if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg(folio) != memcg) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio, int new_gen, bool dirty) { int old_gen; if (!folio) return; if (dirty && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); if (walk) { old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } else if (lru_gen_set_refs(folio)) { old_gen = folio_lru_gen(folio); if (old_gen >= 0 && old_gen != new_gen) folio_activate(folio); } } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; bool dirty; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int gen = lru_gen_from_seq(max_seq); pmd_t pmdval; pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { pte_unmap(pte); return true; } if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { pte_unmap_unlock(pte, ptl); return false; } arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; pte_t ptent = ptep_get(pte + i); total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(args->vma, addr, pte + i)) continue; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pte_dirty(ptent)) dirty = true; young++; walk->mm_stats[MM_LEAF_YOUNG]++; } walk_update_folio(walk, last, gen, dirty); last = NULL; if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte, ptl); return suitable_to_scan(total, young); } static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; bool dirty; pmd_t *pmd; spinlock_t *ptl; struct folio *last = NULL; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int gen = lru_gen_from_seq(max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*first == -1) { *first = addr; bitmap_zero(bitmap, MIN_LRU_BATCH); return; } i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *first); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; if (!pmd_present(pmd[i])) goto next; if (!pmd_trans_huge(pmd[i])) { if (!walk->force_scan && should_clear_pmd_young() && !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); if (pfn == -1) goto next; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) goto next; if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pmd_dirty(pmd[i])) dirty = true; walk->mm_stats[MM_LEAF_YOUNG]++; next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); walk_update_folio(walk, last, gen, dirty); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *first = -1; } static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; DECLARE_BITMAP(bitmap, MIN_LRU_BATCH); unsigned long first = -1; struct lru_gen_mm_walk *walk = args->private; struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmdp_get_lockless(pmd + i); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } if (pmd_trans_huge(val)) { struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; if (pfn != -1) walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } if (!walk->force_scan && should_clear_pmd_young() && !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); } if (!walk->force_scan && !test_bloom_filter(mm_state, walk->seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(mm_state, walk->seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; int err; struct lruvec *lruvec = walk->lruvec; walk->next_addr = FIRST_USER_ADDRESS; do { DEFINE_MAX_SEQ(lruvec); err = -EBUSY; /* another thread might have called inc_max_seq() */ if (walk->seq != max_seq) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!walk && force_alloc) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type ? swappiness > MAX_SWAPPINESS : !swappiness) goto done; /* prevent cold/hot inversion if the type is evictable */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); /* don't count the workingset being lazily promoted */ if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { int tier = lru_tier_from_refs(refs, workingset); int delta = folio_nr_pages(folio); WRITE_ONCE(lrugen->protected[hist][type][tier], lrugen->protected[hist][type][tier] + delta); } if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness) { int gen, type, zone; bool success = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for_each_evictable_type(type, swappiness) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } min_seq[type]++; } next: ; } /* see the comment on lru_gen_folio */ if (swappiness && swappiness <= MAX_SWAPPINESS) { unsigned long seq = lrugen->max_seq - MIN_NR_GENS; if (min_seq[LRU_GEN_ANON] > seq && min_seq[LRU_GEN_FILE] < seq) min_seq[LRU_GEN_ANON] = seq; else if (min_seq[LRU_GEN_FILE] > seq && min_seq[LRU_GEN_ANON] < seq) min_seq[LRU_GEN_FILE] = seq; } for_each_evictable_type(type, swappiness) { if (min_seq[type] <= lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness) { bool success; int prev, next; int type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; restart: if (seq < READ_ONCE(lrugen->max_seq)) return false; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); success = seq == lrugen->max_seq; if (!success) goto unlock; for (type = 0; type < ANON_AND_FILE; type++) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; if (inc_min_seq(lruvec, type, swappiness)) continue; spin_unlock_irq(&lruvec->lru_lock); cond_resched(); goto restart; } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); unlock: spin_unlock_irq(&lruvec->lru_lock); return success; } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) return inc_max_seq(lruvec, seq, swappiness); /* see the comment in iterate_mm_list() */ if (seq <= READ_ONCE(mm_state->seq)) return false; /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!should_walk_mmu()) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk = set_mm_walk(NULL, true); if (!walk) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk->lruvec = lruvec; walk->seq = seq; walk->swappiness = swappiness; walk->force_scan = force_scan; do { success = iterate_mm_list(walk, &mm); if (mm) walk_mm(mm, walk); } while (mm); done: if (success) { success = inc_max_seq(lruvec, seq, swappiness); WARN_ON_ONCE(!success); } return success; } /****************************************************************************** * working set protection ******************************************************************************/ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) { int priority; unsigned long reclaimable; if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* * Determine the initial priority based on * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); /* * The estimation is based on LRU pages only, so cap it to prevent * overshoots of shrinker objects by large margins. */ sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); } static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; int swappiness = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } /* whether the size is big enough to be helpful */ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total; } static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { int gen; unsigned long birth; int swappiness = get_swappiness(lruvec, sc); struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; gen = lru_gen_from_seq(evictable_min_seq(min_seq, swappiness)); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); mem_cgroup_calculate_protection(NULL, memcg); if (!reclaimable) reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /****************************************************************************** * rmap/PT walk feedback ******************************************************************************/ /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; bool dirty; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; struct folio *last = NULL; int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); int gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (!ptep_clear_young_notify(vma, addr, pte)) return false; if (spin_is_contended(pvmw->ptl)) return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start == PAGE_SIZE) return true; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2; end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2; } } arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pte_t ptent = ptep_get(pte + i); pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; folio = get_pfn_folio(pfn, memcg, pgdat); if (!folio) continue; if (!ptep_clear_young_notify(vma, addr, pte + i)) continue; if (last != folio) { walk_update_folio(walk, last, gen, dirty); last = folio; dirty = false; } if (pte_dirty(ptent)) dirty = true; young++; } walk_update_folio(walk, last, gen, dirty); arch_leave_lazy_mmu_mode(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); return true; } /****************************************************************************** * memcg LRU ******************************************************************************/ /* see the comment on MEMCG_NR_GENS */ enum { MEMCG_LRU_NOP, MEMCG_LRU_HEAD, MEMCG_LRU_TAIL, MEMCG_LRU_OLD, MEMCG_LRU_YOUNG, }; static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); seg = 0; new = old = lruvec->lrugen.gen; /* see the comment on MEMCG_NR_GENS */ if (op == MEMCG_LRU_HEAD) seg = MEMCG_LRU_HEAD; else if (op == MEMCG_LRU_TAIL) seg = MEMCG_LRU_TAIL; else if (op == MEMCG_LRU_OLD) new = get_memcg_gen(pgdat->memcg_lru.seq); else if (op == MEMCG_LRU_YOUNG) new = get_memcg_gen(pgdat->memcg_lru.seq + 1); else VM_WARN_ON_ONCE(true); WRITE_ONCE(lruvec->lrugen.seg, seg); WRITE_ONCE(lruvec->lrugen.gen, new); hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); else hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } #ifdef CONFIG_MEMCG void lru_gen_online_memcg(struct mem_cgroup *memcg) { int gen; int nid; int bin = get_random_u32_below(MEMCG_NR_BINS); for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); gen = get_memcg_gen(pgdat->memcg_lru.seq); lruvec->lrugen.gen = gen; hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_offline_memcg(struct mem_cgroup *memcg) { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); } } void lru_gen_release_memcg(struct mem_cgroup *memcg) { int gen; int nid; for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); if (hlist_nulls_unhashed(&lruvec->lrugen.list)) goto unlock; gen = lruvec->lrugen.gen; hlist_nulls_del_init_rcu(&lruvec->lrugen.list); pgdat->memcg_lru.nr_memcgs[gen]--; if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); unlock: spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); } #endif /* CONFIG_MEMCG */ /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, int tier_idx) { bool success; bool dirty, writeback; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); bool workingset = folio_test_workingset(folio); int tier = lru_tier_from_refs(refs, workingset); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) { gen = folio_inc_gen(lruvec, folio, false); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); /* don't count the workingset being lazily promoted */ if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); WRITE_ONCE(lrugen->protected[hist][type][tier], lrugen->protected[hist][type][tier] + delta); } return true; } /* ineligible */ if (!folio_test_lru(folio) || zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } dirty = folio_test_dirty(folio); writeback = folio_test_writeback(folio); if (type == LRU_GEN_FILE && dirty) { sc->nr.file_taken += delta; if (!writeback) sc->nr.unqueued_dirty += delta; } /* waiting for writeback */ if (writeback || (type == LRU_GEN_FILE && dirty)) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* swap constrained */ if (!(sc->gfp_mask & __GFP_IO) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags, LRU_REFS_MASK, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int i; int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int skipped = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped_zone += delta; } if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } if (skipped_zone) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = PGSCAN_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } __count_memcg_events(memcg, item, isolated); __count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); if (type == LRU_GEN_FILE) sc->nr.file_taken += isolated; /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (2:3). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 2, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 3, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness) { struct ctrl_pos sp, pv; if (swappiness <= MIN_SWAPPINESS + 1) return LRU_GEN_FILE; if (swappiness >= MAX_SWAPPINESS) return LRU_GEN_ANON; /* * Compare the sum of all tiers of anon with that of file to determine * which type to scan. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv); return positive_ctrl_err(&sp, &pv); } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type = get_type_to_scan(lruvec, swappiness); for_each_evictable_type(i, swappiness) { int scanned; int tier = get_tier_idx(lruvec, type); *type_scanned = type; scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) return scanned; type = !type; } return 0; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (evictable_min_seq(lrugen->min_seq, swappiness) + MIN_NR_GENS > lrugen->max_seq) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { DEFINE_MIN_SEQ(lruvec); if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) && !folio_test_dirty(folio) && !folio_test_writeback(folio)) { list_move(&folio->lru, &clean); continue; } /* don't add rejected folios to the oldest generation */ if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type]) set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active)); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) { walk->lruvec = lruvec; reset_batch_size(walk); } __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(sc), stat.nr_demoted); item = PGSTEAL_KSWAPD + reclaimer_offset(sc); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); __count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } return scanned; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, int swappiness, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long size = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); *nr_to_scan = 0; /* have to run aging, since eviction is not possible anymore */ if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq) return true; for_each_evictable_type(type, swappiness) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } *nr_to_scan = size; /* better to run aging even though eviction is still possible */ return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { bool success; unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; success = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan); /* try to scrape all its memory if this memcg was deleted */ if (nr_to_scan && !mem_cgroup_online(memcg)) return nr_to_scan; /* try to get away with not aging at the default priority */ if (!success || sc->priority == DEF_PRIORITY) return nr_to_scan >> sc->priority; /* stop scanning this lruvec as it's low on cold folios */ return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { int i; enum zone_watermarks mark; /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) return false; if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; /* check the order to exclude compaction-induced reclaim */ if (!current_is_kswapd() || sc->order) return false; mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? WMARK_PROMO : WMARK_HIGH; for (i = 0; i <= sc->reclaim_idx; i++) { struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) return false; } /* kswapd should abort if all eligible zones are safe */ return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; int swappiness = get_swappiness(lruvec, sc); while (true) { int delta; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); if (nr_to_scan <= 0) break; delta = evict_folios(lruvec, sc, swappiness); if (!delta) break; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, sc)) break; cond_resched(); } /* * If too many file cache in the coldest generation can't be evicted * due to being dirty, wake up the flusher. */ if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) wakeup_flusher_threads(WB_REASON_VMSCAN); /* whether this lruvec should be rotated */ return nr_to_scan < 0; } static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) { bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); } success = try_to_shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); flush_reclaim_state(sc); if (success && mem_cgroup_online(memcg)) return MEMCG_LRU_YOUNG; if (!success && lruvec_is_sizable(lruvec, sc)) return 0; /* one retry if offlined or too small */ return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) { int op; int gen; int bin; int first_bin; struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct hlist_nulls_node *pos; gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; rcu_read_lock(); hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { if (op) { lru_gen_rotate_memcg(lruvec, op); op = 0; } mem_cgroup_put(memcg); memcg = NULL; if (gen != READ_ONCE(lrugen->gen)) continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); if (!mem_cgroup_tryget(memcg)) { lru_gen_release_memcg(memcg); memcg = NULL; continue; } rcu_read_unlock(); op = shrink_one(lruvec, sc); rcu_read_lock(); if (should_abort_scan(lruvec, sc)) break; } rcu_read_unlock(); if (op) lru_gen_rotate_memcg(lruvec, op); mem_cgroup_put(memcg); if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ if (gen != get_nulls_value(pos)) goto restart; /* try the rest of the bins of the current generation */ bin = get_memcg_bin(bin + 1); if (bin != first_bin) goto restart; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; VM_WARN_ON_ONCE(root_reclaim(sc)); VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(NULL, sc->proactive); if (try_to_shrink_lruvec(lruvec, sc)) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); clear_mm_walk(); blk_finish_plug(&plug); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; unsigned long reclaimed = sc->nr_reclaimed; VM_WARN_ON_ONCE(!root_reclaim(sc)); /* * Unmapped clean folios are already prioritized. Scanning for more of * them is likely futile and can cause high reclaim latency when there * is a large number of memcgs. */ if (!sc->may_writepage || !sc->may_unmap) goto done; lru_add_drain(); blk_start_plug(&plug); set_mm_walk(pgdat, sc->proactive); set_initial_priority(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed = 0; if (mem_cgroup_disabled()) shrink_one(&pgdat->__lruvec, sc); else shrink_many(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed += reclaimed; clear_mm_walk(); blk_finish_plug(&plug); done: if (sc->nr_reclaimed > reclaimed) pgdat->kswapd_failures = 0; } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (should_walk_mmu()) caps |= BIT(LRU_GEN_MM_WALK); if (should_clear_pmd_young()) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return sysfs_emit(buf, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); n[2] = READ_ONCE(lrugen->protected[hist][type][tier]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } if (!mm_state) return; seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = evictable_min_seq(min_seq, MAX_SWAPPINESS / 2); else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, int swappiness, bool force_scan) { DEFINE_MAX_SEQ(lruvec); if (seq > max_seq) return -EINVAL; return try_to_inc_max_seq(lruvec, max_seq, swappiness, force_scan) ? 0 : -EEXIST; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < evictable_min_seq(min_seq, swappiness)) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(lruvec, sc, swappiness)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); if (!mem_cgroup_tryget(memcg)) memcg = NULL; rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; lruvec = get_lruvec(memcg, nid); if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); else if (swappiness > MAX_SWAPPINESS + 1) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL, true)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness = -1; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, &swappiness, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_pgdat(struct pglist_data *pgdat) { int i, j; spin_lock_init(&pgdat->memcg_lru.lock); for (i = 0; i < MEMCG_NR_GENS; i++) { for (j = 0; j < MEMCG_NR_BINS; j++) INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); } } void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); if (mm_state) mm_state->seq = MIN_NR_GENS; } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { struct lru_gen_mm_list *mm_list = get_mm_list(memcg); if (!mm_list) return; INIT_LIST_HEAD(&mm_list->fifo); spin_lock_init(&mm_list->lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo)); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); lruvec->lrugen.list.next = LIST_POISON1; if (!mm_state) continue; for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(mm_state->filters[i]); mm_state->filters[i] = NULL; } } } #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled() && !root_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; struct zone *zone; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for_each_managed_zone_pgdat(zone, pgdat, z, sc->reclaim_idx) { unsigned long watermark = min_wmark_pages(zone); /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, watermark, sc->reclaim_idx, 0)) return false; if (compaction_suitable(zone, sc->order, watermark, sc->reclaim_idx)) return false; } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, }; struct mem_cgroup_reclaim_cookie *partial = &reclaim; struct mem_cgroup *memcg; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree, using an iterator state that * persists across invocations. This strikes a balance between * fairness and allocation latency. * * For kswapd, reliable forward progress is more important * than a quick return to idle. Always do full walks. */ if (current_is_kswapd() || sc->memcg_full_walk) partial = NULL; memcg = mem_cgroup_iter(target_memcg, NULL, partial); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(target_memcg, memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(target_memcg, memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); /* If partial walks are allowed, bail once goal is reached */ if (partial && sc->nr_reclaimed >= sc->nr_to_reclaim) { mem_cgroup_iter_break(target_memcg, memcg); break; } } while ((memcg = mem_cgroup_iter(target_memcg, memcg, partial))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { memset(&sc->nr, 0, sizeof(sc->nr)); lru_gen_shrink_node(pgdat, sc); return; } target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); flush_reclaim_state(sc); nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, nr_node_reclaimed); if (nr_node_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so forcibly stall * until some pages complete writeback. */ if (sc->nr.immediate) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* * Tag a node/memcg as congested if all the dirty pages were marked * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in reclaim_throttle(). */ if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) { if (cgroup_reclaim(sc) && writeback_throttling_sane(sc)) set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags); if (current_is_kswapd()) set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags); } /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) || test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags))) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; else if (sc->cache_trim_mode) sc->cache_trim_mode_failed = 1; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; if (!gfp_compaction_allowed(sc->gfp_mask)) return false; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return true; /* * Direct reclaim usually targets the min watermark, but compaction * takes time to run and there are potentially other callers using the * pages just freed. So target a higher buffer to give compaction a * reasonable chance of completing and allocating the pages. * * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone); if (compaction_suitable(zone, sc->order, watermark, sc->reclaim_idx)) return true; return false; } static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { /* * If reclaim is making progress greater than 12% efficiency then * wake all the NOPROGRESS throttled tasks. */ if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; if (waitqueue_active(wqh)) wake_up(wqh); return; } /* * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages * under writeback and marked for immediate reclaim at the tail of the * LRU. */ if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } if (!first_pgdat) first_pgdat = zone->zone_pgdat; /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[WORKINGSET_ANON] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { if (!sc->proactive) vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree to meet the reclaim goal while * keeping latency low. Since the iterator state is shared * among all direct reclaim invocations (to retain fairness * among cgroups), though, high concurrency can result in * individual threads not seeing enough cgroups to make * meaningful forward progress. Avoid false OOMs in this case. */ if (!sc->memcg_full_walk) { sc->priority = initial_priority; sc->memcg_full_walk = 1; goto retry; } /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for_each_managed_zone_pgdat(zone, pgdat, i, ZONE_NORMAL) { if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state_snapshot(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); else /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .proactive_swappiness = swappiness, .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (lru_gen_enabled()) { lru_gen_age_node(pgdat, sc); return; } if (!can_age_anon_pages(pgdat, sc)) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { enum zone_stat_item item; unsigned long free_pages; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) mark = promo_wmark_pages(zone); else mark = high_wmark_pages(zone); /* * In defrag_mode, watermarks must be met in whole * blocks to avoid polluting allocator fallbacks. * * However, kswapd usually cannot accomplish this on * its own and needs kcompactd support. Once it's * reclaimed a compaction gap, and kswapd_shrink_node * has dropped order, simply ensure there are enough * base pages for compaction, wake kcompactd & sleep. */ if (defrag_mode && order) item = NR_FREE_PAGES_BLOCKS; else item = NR_FREE_PAGES; /* * When there is a high number of CPUs in the system, * the cumulative error from the vmstat per-cpu cache * can blur the line between the watermarks. In that * case, be safe and get an accurate snapshot. * * TODO: NR_FREE_PAGES_BLOCKS moves in steps of * pageblock_nr_pages, while the vmstat pcp threshold * is limited to 125. On many configurations that * counter won't actually be per-cpu cached. But keep * things simple for now; revisit when somebody cares. */ free_pages = zone_page_state(zone, item); if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark) free_pages = zone_page_state_snapshot(zone, item); if (__zone_watermark_ok(zone, order, mark, highest_zoneidx, 0, free_pages)) return true; } /* * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_NODE_CONGESTED, &lruvec->flags); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; unsigned long nr_reclaimed = sc->nr_reclaimed; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for_each_managed_zone_pgdat(zone, pgdat, z, sc->reclaim_idx) { sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; /* account for progress from mm_account_reclaimed_pages() */ return max(sc->nr_scanned, sc->nr_reclaimed - nr_reclaimed) >= sc->nr_to_reclaim; } /* Page allocator PCP high watermark is lowered if reclaim is active. */ static inline void update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) { int i; struct zone *zone; for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { if (active) set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); else clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); } } static inline void set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, true); } static inline void clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, false); } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; bool was_frozen; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging, to give pages a chance to be * referenced before reclaiming. All pages are rotated * regardless of classzone as this is about consistent aging. */ kswapd_age_node(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(_THIS_IP_); ret = kthread_freezable_should_stop(&was_frozen); __fs_reclaim_acquire(_THIS_IP_); if (was_frozen || ret) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); /* * Restart only if it went through the priority loop all the way, * but cache_trim_mode didn't work. */ if (!sc.nr_reclaimed && sc.priority < 1 && !sc.no_cache_trim_mode && sc.cache_trim_mode_failed) { sc.no_cache_trim_mode = 1; goto restart; } if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: clear_reclaim_active(pgdat, highest_zoneidx); /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool was_frozen; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); if (kthread_freezable_should_stop(&was_frozen)) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (was_frozen) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. */ void __meminit kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ pr_err("Failed to start kswapd on node %d，ret=%ld\n", nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); pgdat->kswapd = NULL; } else { wake_up_process(pgdat->kswapd); } } pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kswapd_stop(int nid) { pg_data_t *pgdat = NODE_DATA(nid); struct task_struct *kswapd; pgdat_kswapd_lock(pgdat); kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); pgdat->kswapd = NULL; } pgdat_kswapd_unlock(pgdat); } static const struct ctl_table vmscan_sysctl_table[] = { { .procname = "swappiness", .data = &vm_swappiness, .maxlen = sizeof(vm_swappiness), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO_HUNDRED, }, #ifdef CONFIG_NUMA { .procname = "zone_reclaim_mode", .data = &node_reclaim_mode, .maxlen = sizeof(node_reclaim_mode), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, } #endif }; static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); register_sysctl_init("vm", vmscan_sysctl_table); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); psi_memstall_enter(&pflags); delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP */ noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit_lock(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (ret) count_vm_event(PGSCAN_ZONE_RECLAIM_SUCCESS); else count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list * @fbatch: Batch of lru folios to check. * * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru folios. */ void check_move_unevictable_folios(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < fbatch->nr; i++) { struct folio *folio = fbatch->folios[i]; int nr_pages = folio_nr_pages(folio); pgscanned += nr_pages; /* block memcg migration while the folio moves between lrus */ if (!folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_evictable(folio) && folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); pgrescued += nr_pages; } folio_set_lru(folio); } if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); unlock_page_lruvec_irq(lruvec); } else if (pgscanned) { count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |
| 1283 1277 4 1048 529 208 161 159 1 527 451 78 1203 1202 1205 930 927 668 1205 1206 2 2 1 46 2 1289 48 301 1 1144 1285 1289 1289 1285 1 1259 7 864 864 852 12 744 22 100 830 8 4 3 9 790 64 841 841 541 843 843 843 843 842 843 83 83 83 82 291 291 291 291 291 52 52 52 50 52 51 52 52 51 51 42 238 239 239 239 174 239 304 1 301 5 301 301 296 2 1 54 242 6 290 209 83 1 82 45 27 58 55 51 52 50 50 50 4 30 189 77 188 174 92 69 1 227 175 1 69 62 17 1453 1068 1070 1071 39 914 442 1391 1170 497 1035 1279 703 15 122 1275 2 8 77 487 169 1201 507 1165 45 227 228 228 187 167 19 102 74 117 502 511 512 415 101 102 102 102 101 102 514 514 510 572 81 514 574 572 2 4 568 5 571 17 458 20 100 87 2 1 1 57 11 30 2 5 16 471 11 543 10 553 523 118 100 516 515 46 484 3 1 197 367 515 515 6 500 313 31 502 466 39 353 195 75 16 10 9 1 1 72 72 70 72 63 2 347 212 11 54 53 1 440 440 10 81 371 370 430 583 491 113 522 99 486 5 468 17 480 96 483 482 469 17 14 79 481 429 482 483 483 482 331 15 166 15 180 161 438 49 65 325 325 3 322 140 54 34 106 106 106 157 158 5 34 140 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 output functions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_output.c * * Changes: * A.N.Kuznetsov : airthmetics in fragmentation. * extension headers are implemented. * route changes now work. * ip6_forward does not confuse sniffers. * etc. * * H. von Brand : Added missing #include <linux/string.h> * Imran Patel : frag id should be in NBO * Kazunori MIYAZAWA @USAGI * : add ip6_append_data and related functions * for datagram xmit */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/in6.h> #include <linux/tcp.h> #include <linux/route.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/bpf-cgroup.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/sock.h> #include <net/snmp.h> #include <net/gso.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/rawv6.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/checksum.h> #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *daddr, *nexthop; struct ipv6hdr *hdr; struct neighbour *neigh; int ret; /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOMEM; } rcu_read_unlock(); } hdr = ipv6_hdr(skb); daddr = &hdr->daddr; if (ipv6_addr_is_multicast(daddr)) { if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, daddr, &hdr->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing is not supported in any case. */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); if (hdr->hop_limit == 0) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len); if (IPV6_ADDR_MC_SCOPE(daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && !(dev->flags & IFF_LOOPBACK)) { kfree_skb(skb); return 0; } } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (IS_ERR_OR_NULL(neigh)) { if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dev, false); if (IS_ERR(neigh)) { rcu_read_unlock(); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return -EINVAL; } } sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } static int ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* Please see corresponding comment in ip_finish_output_gso * describing the cases where GSO segment length exceeds the * egress MTU. */ features = netif_skb_features(skb); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); /* Last GSO segment can be smaller than gso_size (and MTU). * Adding a fragment header would produce an "atomic fragment", * which is considered harmful (RFC-8021). Avoid that. */ err = segs->len > mtu ? ip6_fragment(net, sk, segs, ip6_finish_output2) : ip6_finish_output2(net, sk, segs); if (err && ret == 0) ret = err; } return ret; } static int ip6_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && !skb_gso_validate_network_len(skb, mtu)) return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); return ip6_finish_output2(net, sk, skb); } static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip6_skb_dst_mtu(skb); if (skb_is_gso(skb)) return ip6_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); return ip6_finish_output2(net, sk, skb); } static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: case NET_XMIT_CN: return __ip6_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; } return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } EXPORT_SYMBOL(ip6_output); bool ip6_autoflowlabel(struct net *net, const struct sock *sk) { if (!inet6_test_bit(AUTOFLOWLABEL_SET, sk)) return ip6_default_np_autolabel(net); return inet6_test_bit(AUTOFLOWLABEL, sk); } /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified * by calls to skb_set_owner_w() and ipv6_local_error(), * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); struct hop_jumbo_hdr *hop_jumbo; int hoplen = sizeof(*hop_jumbo); unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu; head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev); if (opt) head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOBUFS; } rcu_read_unlock(); } if (opt) { seg_len += opt->opt_nflen + opt->opt_flen; if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop, &fl6->saddr); } if (unlikely(seg_len > IPV6_MAXPLEN)) { hop_jumbo = skb_push(skb, hoplen); hop_jumbo->nexthdr = proto; hop_jumbo->hdrlen = 0; hop_jumbo->tlv_type = IPV6_TLV_JUMBO; hop_jumbo->tlv_len = 4; hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen); proto = IPPROTO_HOPOPTS; seg_len = 0; IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO; } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ if (np) hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, sk), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; hdr->saddr = fl6->saddr; hdr->daddr = *first_hop; skb->protocol = htons(ETH_P_IPV6); skb->priority = priority; skb->mark = mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out((struct sock *)sk, skb); if (unlikely(!skb)) return 0; /* hooks should never assume socket lock is held. * we promote our socket to non const */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, (struct sock *)sk, skb, NULL, dev, dst_output); } skb->dev = dev; /* ipv6_local_error() does not require socket lock, * we promote our socket to non const */ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } EXPORT_SYMBOL(ip6_xmit); static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; struct sock *last = NULL; read_lock(&ip6_ra_lock); for (ra = ip6_ra_chain; ra; ra = ra->next) { struct sock *sk = ra->sk; if (sk && ra->sel == sel && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == skb->dev->ifindex)) { if (inet6_test_bit(RTALERT_ISOLATE, sk) && !net_eq(sock_net(sk), dev_net(skb->dev))) { continue; } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) rawv6_rcv(last, skb2); } last = sk; } } if (last) { rawv6_rcv(last, skb); read_unlock(&ip6_ra_lock); return 1; } read_unlock(&ip6_ra_lock); return 0; } static int ip6_forward_proxy_check(struct sk_buff *skb) { struct ipv6hdr *hdr = ipv6_hdr(skb); u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; if (ipv6_ext_hdr(nexthdr)) { offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) return 0; } else offset = sizeof(struct ipv6hdr); if (nexthdr == IPPROTO_ICMPV6) { struct icmp6hdr *icmp6; if (!pskb_may_pull(skb, (skb_network_header(skb) + offset + 1 - skb->data))) return 0; icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (icmp6->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: /* For reaction involving unicast neighbor discovery * message destined to the proxied address, pass it to * input function. */ return 1; default: break; } } /* * The proxying router can't forward traffic sent to a link-local * address, so signal the sender and discard the packet. This * behavior is clarified by the MIPv6 specification. */ if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) { dst_link_failure(skb); return -1; } return 0; } static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); return 0; } #endif skb_clear_tstamp(skb); return dst_output(net, sk, skb); } static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; /* ipv6 conntrack defrag sets max_frag_size + ignore_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; if (skb->ignore_df) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) goto error; if (skb->pkt_type != PACKET_HOST) goto drop; if (unlikely(skb->sk)) goto drop; if (skb_warn_if_lro(skb)) goto drop; if (!READ_ONCE(net->ipv6.devconf_all->disable_policy) && (!idev || !READ_ONCE(idev->cnf.disable_policy)) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } skb_forward_csum(skb); /* * We DO NOT make any processing on * RA packets, pushing them to user level AS IS * without ane WARRANTY that application will be able * to interpret them. The reason is that we * cannot make anything clever here. * * We are not end-node, so that if packet contains * AH/ESP, we cannot make anything. * Defragmentation also would be mistake, RA packets * cannot be fragmented, because there is no warranty * that different fragments will go along one path. --ANK */ if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { if (ip6_call_ra_chain(skb, ntohs(opt->ra))) return 0; } /* * check and decrement ttl */ if (hdr->hop_limit <= 1) { icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return -ETIMEDOUT; } /* XXX: idev->cnf.proxy_ndp? */ if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { /* It's tempting to decrease the hop limit * here by 1, as we do at the end of the * function too. * * But that would be incorrect, as proxying is * not forwarding. The ip6_input function * will handle this packet locally, and it * depends on the hop limit being unchanged. * * One example is the NDP hop limit, that * always has to stay 255, but other would be * similar checks around RA packets, where the * user can even change the desired limit. */ return ip6_input(skb); } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); SKB_DR_SET(reason, XFRM_POLICY); goto drop; } dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ if (IP6CB(skb)->iif == dst->dev->ifindex && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct inet_peer *peer; struct rt6_info *rt; /* * incoming and outgoing devices are the same * send a redirect. */ rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else target = &hdr->daddr; rcu_read_lock(); peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); rcu_read_unlock(); } else { int addrtype = ipv6_addr_type(&hdr->saddr); /* This check is security critical. */ if (addrtype == IPV6_ADDR_ANY || addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOT_NEIGHBOUR, 0); goto error; } } __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); mtu = ip6_dst_mtu_maybe_forward(dst, true); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ hdr->hop_limit--; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, dst->dev, ip6_forward_finish); error: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); SKB_DR_SET(reason, IP_INADDRERRORS); drop: kfree_skb_reason(skb, reason); return -EINVAL; } static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; skb_dst_drop(to); skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); skb_copy_secmark(to, from); } int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter) { unsigned int first_len; struct frag_hdr *fh; /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!iter->tmp_hdr) return -ENOMEM; iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->hlen = hlen; iter->frag_id = frag_id; iter->nexthdr = nexthdr; __skb_pull(skb, hlen); fh = __skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), iter->tmp_hdr, hlen); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); fh->identification = frag_id; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); return 0; } EXPORT_SYMBOL(ip6_fraglist_init); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter) { struct sk_buff *frag = iter->frag; unsigned int hlen = iter->hlen; struct frag_hdr *fh; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = __skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iter->tmp_hdr, hlen); iter->offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = iter->nexthdr; fh->reserved = 0; fh->frag_off = htons(iter->offset); if (frag->next) fh->frag_off |= htons(IP6_MF); fh->identification = iter->frag_id; ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } EXPORT_SYMBOL(ip6_fraglist_prepare); void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state) { state->prevhdr = prevhdr; state->nexthdr = nexthdr; state->frag_id = frag_id; state->hlen = hlen; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->hroom = hdr_room; state->troom = needed_tailroom; state->offset = 0; } EXPORT_SYMBOL(ip6_frag_init); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state) { u8 *prevhdr = state->prevhdr, *fragnexthdr_offset; struct sk_buff *frag; struct frag_hdr *fh; unsigned int len; len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) len &= ~7; /* Allocate buffer */ frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) + state->hroom + state->troom, GFP_ATOMIC); if (!frag) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, state->hroom); skb_put(frag, len + state->hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen); frag->transport_header = (frag->network_header + state->hlen + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen); fragnexthdr_offset = skb_network_header(frag); fragnexthdr_offset += prevhdr - skb_network_header(skb); *fragnexthdr_offset = NEXTHDR_FRAGMENT; /* * Build fragment header. */ fh->nexthdr = state->nexthdr; fh->reserved = 0; fh->identification = state->frag_id; /* * Copy a block of the IP datagram. */ BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag), len)); state->left -= len; fh->frag_off = htons(state->offset); if (state->left > 0) fh->frag_off |= htons(IP6_MF); ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); state->ptr += len; state->offset += len; return frag; } EXPORT_SYMBOL(ip6_frag_next); int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; u8 tstamp_type = skb->tstamp_type; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; int hroom, err = 0; __be32 frag_id; u8 *prevhdr, nexthdr = 0; err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) goto fail; hlen = err; nexthdr = *prevhdr; nexthdr_offset = prevhdr - skb_network_header(skb); mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ if (unlikely(!skb->ignore_df && skb->len > mtu)) goto fail_toobig; if (IP6CB(skb)->frag_max_size) { if (IP6CB(skb)->frag_max_size > mtu) goto fail_toobig; /* don't send fragments larger than what we received */ mtu = IP6CB(skb)->frag_max_size; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; } if (np) { u32 frag_size = READ_ONCE(np->frag_size); if (frag_size && frag_size < mtu) mtu = frag_size; } if (mtu < hlen + sizeof(struct frag_hdr) + 8) goto fail_toobig; mtu -= hlen + sizeof(struct frag_hdr); frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); struct ip6_fraglist_iter iter; struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb) || skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id, &iter); if (err < 0) goto fail; /* We prevent @rt from being freed. */ rcu_read_lock(); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) ip6_fraglist_prepare(skb, &iter); skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip6_fraglist_next(&iter); } kfree(iter.tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); rcu_read_unlock(); return 0; } kfree_skb_list(iter.frag); IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); rcu_read_unlock(); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom, LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { frag = ip6_frag_next(skb, &state); if (IS_ERR(frag)) { err = PTR_ERR(frag); goto fail; } /* * Put this fragment into the sending queue. */ skb_set_delivery_time(frag, tstamp, tstamp_type); err = output(net, sk, frag); if (err) goto fail; IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); consume_skb(skb); return err; fail_toobig: icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; } static inline int ip6_rt_check(const struct rt6key *rt_key, const struct in6_addr *fl_addr, const struct in6_addr *addr_cache) { return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && (!addr_cache || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt; if (!dst) goto out; if (dst->ops->family != AF_INET6) { dst_release(dst); return NULL; } rt = dst_rt6_info(dst); /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, * and MSG_DONTROUTE --ANK (980726) * * 1. ip6_rt_check(): If route was host route, * check that cached destination is current. * If it is network route, we still may * check its validity using saved pointer * to the last used address: daddr_cache. * We do not want to save whole address now, * (because main consumer of this service * is tcp, which has not this problem), * so that the last trick works only on connected * sockets. * 2. oif also should be the same. */ if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) || #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; } out: return dst; } static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; struct rt6_info *rt; #endif int err; int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, * the route-specific preferred source forces the * ip6_route_output call _before_ ip6_route_get_saddr. * * In source specific routing (no src=any default route), * ip6_route_output will fail given src=any saddr, though, so * that's why we try it again later. */ if (ipv6_addr_any(&fl6->saddr)) { struct fib6_info *from; struct rt6_info *rt; *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : dst_rt6_info(*dst); rcu_read_lock(); from = rt ? rcu_dereference(rt->from) : NULL; err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0, fl6->flowi6_l3mdev, &fl6->saddr); rcu_read_unlock(); if (err) goto out_err_release; /* If we had an erroneous initial result, pretend it * never existed and let the SA-enabled version take * over. */ if ((*dst)->error) { dst_release(*dst); *dst = NULL; } if (fl6->flowi6_oif) flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) goto out_err_release; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * Here if the dst entry we've looked up * has a neighbour entry that is in the INCOMPLETE * state and the src address from the flow is * marked as OPTIMISTIC, we release the found * dst entry and replace it instead with the * dst entry of the nexthop router */ rt = dst_rt6_info(*dst); rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock(); if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); if (ifp) in6_ifa_put(ifp); if (redirect) { /* * We need to get the dst entry for the * default router instead */ dst_release(*dst); memcpy(&fl_gw6, fl6, sizeof(struct flowi6)); memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr)); *dst = ip6_route_output(net, sk, &fl_gw6); err = (*dst)->error; if (err) goto out_err_release; } } #endif if (ipv6_addr_v4mapped(&fl6->saddr) && !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { err = -EAFNOSUPPORT; goto out_err_release; } return 0; out_err_release: dst_release(*dst); *dst = NULL; if (err == -ENETUNREACH) IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); return err; } /** * ip6_dst_lookup - perform route lookup on flow * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @dst: pointer to dst_entry * for result * @fl6: flow to lookup * * This function performs a route lookup on the given flow. * * It returns zero on success, or a standard errno code on error. */ int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { *dst = NULL; return ip6_dst_lookup_tail(net, sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** * ip6_dst_lookup_flow - perform route lookup on flow with ipsec * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * * This function performs a route lookup on the given flow. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); /** * ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow * @sk: socket which provides the dst cache and route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * @connected: whether @sk is connected or not * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. * It will take the socket dst lock when operating on the dst cache. * As a result, this function can only be used in process context. * * In addition, for a connected socket, cache the dst in the socket * if the current cache is not valid. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected) { struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); dst = ip6_sk_dst_check(sk, dst, fl6); if (dst) return dst; dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); return dst; } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (!skb) { /* first fragment, reserve header_len */ *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); } } static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu, frag_size; struct ipv6_txoptions *nopt, *opt = ipc6->opt; /* callers pass dst together with a reference, set it first so * ip6_cork_release() can put it down even in case of an error. */ cork->base.dst = &rt->dst; /* * setup for corking */ if (opt) { if (WARN_ON(v6_cork->opt)) return -EINVAL; nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); if (unlikely(!nopt)) return -ENOBUFS; nopt->tot_len = sizeof(*opt); nopt->opt_flen = opt->opt_flen; nopt->opt_nflen = opt->opt_nflen; nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS; nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS; nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); if (opt->hopopt && !nopt->hopopt) return -ENOBUFS; nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); if (opt->srcrt && !nopt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; v6_cork->dontfrag = ipc6->dontfrag; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst)); frag_size = READ_ONCE(np->frag_size); if (frag_size && frag_size < mtu) mtu = frag_size; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; cork->base.mark = ipc6->sockc.mark; cork->base.priority = ipc6->sockc.priority; sock_tx_timestamp(sk, &ipc6->sockc, &cork->base.tx_flags); if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) { cork->base.flags |= IPCORK_TS_OPT_ID; cork->base.ts_opt_id = ipc6->sockc.ts_opt_id; } cork->base.length = 0; cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; } static int __ip6_append_data(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, unsigned int flags) { struct sk_buff *skb, *skb_prev = NULL; struct inet_cork *cork = &cork_full->base; struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; int dst_exthdrlen = 0; int hh_len; int copy; int err; int offset = 0; bool zc = false; u32 tskey = 0; struct rt6_info *rt = dst_rt6_info(cork->dst); bool paged, hold_tskey = false, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; skb = skb_peek_tail(queue); if (!skb) { exthdrlen = opt ? opt->opt_flen : 0; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } paged = !!cork->gso_size; mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) goto emsgsize; maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ if (headersize + transhdrlen > mtu) goto emsgsize; if (cork->length + length > mtu - headersize && v6_cork->dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); goto emsgsize; } if (ip6_sk_ignore_df(sk)) maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; else maxnonfragsize = mtu; if (cork->length + length > maxnonfragsize - headersize) { emsgsize: pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0); ipv6_local_error(sk, EMSGSIZE, fl6, pmtu); return -EMSGSIZE; } /* CHECKSUM_PARTIAL only with no extension headers and when * we are not going to fragment */ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && (!(flags & MSG_MORE) || cork->gso_size) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } else if ((flags & MSG_SPLICE_PAGES) && length) { if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) /* We need an empty buffer to attach stuff to */ paged = true; else flags &= ~MSG_SPLICE_PAGES; } if (cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { if (cork->flags & IPCORK_TS_OPT_ID) { tskey = cork->ts_opt_id; } else { tskey = atomic_inc_return(&sk->sk_tskey) - 1; hold_tskey = true; } } /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ cork->length += length; if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ if (skb) fraggap = skb->len - maxfraglen; else fraggap = 0; /* update mtu and maxfraglen if necessary */ if (!skb || !skb_prev) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len; alloc_extra += dst_exthdrlen; alloc_extra += rt->dst.trailer_len; /* We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloc_extra += sizeof(struct frag_hdr); if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen; pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; if (datalen != length + fraggap) { /* * this is not the last fragment, the trailer * space is regarded as data space. */ datalen += rt->dst.trailer_len; } fraglen = datalen + fragheaderlen; copy = datalen - transhdrlen - fraggap - pagedlen; /* [!] NOTE: copy may be negative if pagedlen>0 * because then the equation may reduces to -fraggap. */ if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) { err = -EINVAL; goto error; } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = csummode; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); /* * Find where to start putting bytes */ data = skb_put(skb, fraglen - pagedlen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } if (copy > 0 && INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } else if (flags & MSG_SPLICE_PAGES) { copy = 0; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; /* Only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; err = -EIO; if (WARN_ON_ONCE(copy > msg->msg_iter.count)) goto error; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) goto error; copy = err; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); if (hold_tskey) atomic_dec(&sk->sk_tskey); return err; } int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int exthdrlen; int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, ipc6, rt); if (err) return err; inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { transhdrlen = 0; } return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } EXPORT_SYMBOL_GPL(ip6_append_data); static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) { struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; skb_dst_set(skb, dst); } static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { struct ipv6_txoptions *opt = v6_cork->opt; kfree(opt->dst0opt); kfree(opt->dst1opt); kfree(opt->hopopt); kfree(opt->srcrt); kfree(opt); v6_cork->opt = NULL; } if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; } } struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr *final_dst; struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; struct rt6_info *rt = dst_rt6_info(cork->base.dst); struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); __skb_pull(skb, skb_network_header_len(skb)); final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, sk), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; skb->priority = cork->base.priority; skb->mark = cork->base.mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); else skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid); ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; if (sk->sk_socket->type == SOCK_RAW && !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } ip6_cork_release(cork, v6_cork); out: return skb; } int ip6_send_skb(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return err; } int ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; skb = ip6_finish_skb(sk); if (!skb) return 0; return ip6_send_skb(skb); } EXPORT_SYMBOL_GPL(ip6_push_pending_frames); static void __ip6_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) { if (skb_dst(skb)) IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } ip6_cork_release(cork, v6_cork); } void ip6_flush_pending_frames(struct sock *sk) { __ip6_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err; if (flags & MSG_PROBE) { dst_release(&rt->dst); return NULL; } __skb_queue_head_init(&queue); cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); } err = __ip6_append_data(sk, &queue, cork, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags); if (err) { __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); } return __ip6_make_skb(sk, &queue, cork, &v6_cork); } |
| 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 | /* * net/tipc/ib_media.c: Infiniband bearer support for TIPC * * Copyright (c) 2013 Patrick McHardy <kaber@trash.net> * * Based on eth_media.c, which carries the following copyright notice: * * Copyright (c) 2001-2007, Ericsson AB * Copyright (c) 2005-2008, 2011, Wind River Systems * 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 <linux/if_infiniband.h> #include "core.h" #include "bearer.h" #define TIPC_MAX_IB_LINK_WIN 500 /* convert InfiniBand address (media address format) media address to string */ static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) { if (str_size < 60) /* 60 = 19 * strlen("xx:") + strlen("xx\0") */ return 1; sprintf(str_buf, "%20phC", a->value); return 0; } /* Convert from media address format to discovery message addr format */ static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr) { memset(msg, 0, TIPC_MEDIA_INFO_SIZE); memcpy(msg, addr->value, INFINIBAND_ALEN); return 0; } /* Convert raw InfiniBand address format to media addr format */ static int tipc_ib_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, const char *msg) { memset(addr, 0, sizeof(*addr)); memcpy(addr->value, msg, INFINIBAND_ALEN); addr->media_id = TIPC_MEDIA_TYPE_IB; addr->broadcast = !memcmp(msg, b->bcast_addr.value, INFINIBAND_ALEN); return 0; } /* Convert discovery msg addr format to InfiniBand media addr format */ static int tipc_ib_msg2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg) { return tipc_ib_raw2addr(b, addr, msg); } /* InfiniBand media registration info */ struct tipc_media ib_media_info = { .send_msg = tipc_l2_send_msg, .enable_media = tipc_enable_l2_media, .disable_media = tipc_disable_l2_media, .addr2str = tipc_ib_addr2str, .addr2msg = tipc_ib_addr2msg, .msg2addr = tipc_ib_msg2addr, .raw2addr = tipc_ib_raw2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .min_win = TIPC_DEF_LINK_WIN, .max_win = TIPC_MAX_IB_LINK_WIN, .type_id = TIPC_MEDIA_TYPE_IB, .hwaddr_len = INFINIBAND_ALEN, .name = "ib" }; |
| 101 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 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_DCCP_H #define _UAPI_LINUX_DCCP_H #include <linux/types.h> #include <asm/byteorder.h> /** * struct dccp_hdr - generic part of DCCP packet header * * @dccph_sport - Relevant port on the endpoint that sent this packet * @dccph_dport - Relevant port on the other endpoint * @dccph_doff - Data Offset from the start of the DCCP header, in 32-bit words * @dccph_ccval - Used by the HC-Sender CCID * @dccph_cscov - Parts of the packet that are covered by the Checksum field * @dccph_checksum - Internet checksum, depends on dccph_cscov * @dccph_x - 0 = 24 bit sequence number, 1 = 48 * @dccph_type - packet type, see DCCP_PKT_ prefixed macros * @dccph_seq - sequence number high or low order 24 bits, depends on dccph_x */ struct dccp_hdr { __be16 dccph_sport, dccph_dport; __u8 dccph_doff; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 dccph_cscov:4, dccph_ccval:4; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 dccph_ccval:4, dccph_cscov:4; #else #error "Adjust your <asm/byteorder.h> defines" #endif __sum16 dccph_checksum; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 dccph_x:1, dccph_type:4, dccph_reserved:3; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 dccph_reserved:3, dccph_type:4, dccph_x:1; #else #error "Adjust your <asm/byteorder.h> defines" #endif __u8 dccph_seq2; __be16 dccph_seq; }; /** * struct dccp_hdr_ext - the low bits of a 48 bit seq packet * * @dccph_seq_low - low 24 bits of a 48 bit seq packet */ struct dccp_hdr_ext { __be32 dccph_seq_low; }; /** * struct dccp_hdr_request - Connection initiation request header * * @dccph_req_service - Service to which the client app wants to connect */ struct dccp_hdr_request { __be32 dccph_req_service; }; /** * struct dccp_hdr_ack_bits - acknowledgment bits common to most packets * * @dccph_resp_ack_nr_high - 48 bit ack number high order bits, contains GSR * @dccph_resp_ack_nr_low - 48 bit ack number low order bits, contains GSR */ struct dccp_hdr_ack_bits { __be16 dccph_reserved1; __be16 dccph_ack_nr_high; __be32 dccph_ack_nr_low; }; /** * struct dccp_hdr_response - Connection initiation response header * * @dccph_resp_ack - 48 bit Acknowledgment Number Subheader (5.3) * @dccph_resp_service - Echoes the Service Code on a received DCCP-Request */ struct dccp_hdr_response { struct dccp_hdr_ack_bits dccph_resp_ack; __be32 dccph_resp_service; }; /** * struct dccp_hdr_reset - Unconditionally shut down a connection * * @dccph_reset_ack - 48 bit Acknowledgment Number Subheader (5.6) * @dccph_reset_code - one of %dccp_reset_codes * @dccph_reset_data - the Data 1 ... Data 3 fields from 5.6 */ struct dccp_hdr_reset { struct dccp_hdr_ack_bits dccph_reset_ack; __u8 dccph_reset_code, dccph_reset_data[3]; }; enum dccp_pkt_type { DCCP_PKT_REQUEST = 0, DCCP_PKT_RESPONSE, DCCP_PKT_DATA, DCCP_PKT_ACK, DCCP_PKT_DATAACK, DCCP_PKT_CLOSEREQ, DCCP_PKT_CLOSE, DCCP_PKT_RESET, DCCP_PKT_SYNC, DCCP_PKT_SYNCACK, DCCP_PKT_INVALID, }; #define DCCP_NR_PKT_TYPES DCCP_PKT_INVALID static inline unsigned int dccp_packet_hdr_len(const __u8 type) { if (type == DCCP_PKT_DATA) return 0; if (type == DCCP_PKT_DATAACK || type == DCCP_PKT_ACK || type == DCCP_PKT_SYNC || type == DCCP_PKT_SYNCACK || type == DCCP_PKT_CLOSE || type == DCCP_PKT_CLOSEREQ) return sizeof(struct dccp_hdr_ack_bits); if (type == DCCP_PKT_REQUEST) return sizeof(struct dccp_hdr_request); if (type == DCCP_PKT_RESPONSE) return sizeof(struct dccp_hdr_response); return sizeof(struct dccp_hdr_reset); } enum dccp_reset_codes { DCCP_RESET_CODE_UNSPECIFIED = 0, DCCP_RESET_CODE_CLOSED, DCCP_RESET_CODE_ABORTED, DCCP_RESET_CODE_NO_CONNECTION, DCCP_RESET_CODE_PACKET_ERROR, DCCP_RESET_CODE_OPTION_ERROR, DCCP_RESET_CODE_MANDATORY_ERROR, DCCP_RESET_CODE_CONNECTION_REFUSED, DCCP_RESET_CODE_BAD_SERVICE_CODE, DCCP_RESET_CODE_TOO_BUSY, DCCP_RESET_CODE_BAD_INIT_COOKIE, DCCP_RESET_CODE_AGGRESSION_PENALTY, DCCP_MAX_RESET_CODES /* Leave at the end! */ }; /* DCCP options */ enum { DCCPO_PADDING = 0, DCCPO_MANDATORY = 1, DCCPO_MIN_RESERVED = 3, DCCPO_MAX_RESERVED = 31, DCCPO_CHANGE_L = 32, DCCPO_CONFIRM_L = 33, DCCPO_CHANGE_R = 34, DCCPO_CONFIRM_R = 35, DCCPO_NDP_COUNT = 37, DCCPO_ACK_VECTOR_0 = 38, DCCPO_ACK_VECTOR_1 = 39, DCCPO_TIMESTAMP = 41, DCCPO_TIMESTAMP_ECHO = 42, DCCPO_ELAPSED_TIME = 43, DCCPO_MAX = 45, DCCPO_MIN_RX_CCID_SPECIFIC = 128, /* from sender to receiver */ DCCPO_MAX_RX_CCID_SPECIFIC = 191, DCCPO_MIN_TX_CCID_SPECIFIC = 192, /* from receiver to sender */ DCCPO_MAX_TX_CCID_SPECIFIC = 255, }; /* maximum size of a single TLV-encoded DCCP option (sans type/len bytes) */ #define DCCP_SINGLE_OPT_MAXLEN 253 /* DCCP CCIDS */ enum { DCCPC_CCID2 = 2, DCCPC_CCID3 = 3, }; /* DCCP features (RFC 4340 section 6.4) */ enum dccp_feature_numbers { DCCPF_RESERVED = 0, DCCPF_CCID = 1, DCCPF_SHORT_SEQNOS = 2, DCCPF_SEQUENCE_WINDOW = 3, DCCPF_ECN_INCAPABLE = 4, DCCPF_ACK_RATIO = 5, DCCPF_SEND_ACK_VECTOR = 6, DCCPF_SEND_NDP_COUNT = 7, DCCPF_MIN_CSUM_COVER = 8, DCCPF_DATA_CHECKSUM = 9, /* 10-127 reserved */ DCCPF_MIN_CCID_SPECIFIC = 128, DCCPF_SEND_LEV_RATE = 192, /* RFC 4342, sec. 8.4 */ DCCPF_MAX_CCID_SPECIFIC = 255, }; /* DCCP socket control message types for cmsg */ enum dccp_cmsg_type { DCCP_SCM_PRIORITY = 1, DCCP_SCM_QPOLICY_MAX = 0xFFFF, /* ^-- Up to here reserved exclusively for qpolicy parameters */ DCCP_SCM_MAX }; /* DCCP priorities for outgoing/queued packets */ enum dccp_packet_dequeueing_policy { DCCPQ_POLICY_SIMPLE, DCCPQ_POLICY_PRIO, DCCPQ_POLICY_MAX }; /* DCCP socket options */ #define DCCP_SOCKOPT_PACKET_SIZE 1 /* XXX deprecated, without effect */ #define DCCP_SOCKOPT_SERVICE 2 #define DCCP_SOCKOPT_CHANGE_L 3 #define DCCP_SOCKOPT_CHANGE_R 4 #define DCCP_SOCKOPT_GET_CUR_MPS 5 #define DCCP_SOCKOPT_SERVER_TIMEWAIT 6 #define DCCP_SOCKOPT_SEND_CSCOV 10 #define DCCP_SOCKOPT_RECV_CSCOV 11 #define DCCP_SOCKOPT_AVAILABLE_CCIDS 12 #define DCCP_SOCKOPT_CCID 13 #define DCCP_SOCKOPT_TX_CCID 14 #define DCCP_SOCKOPT_RX_CCID 15 #define DCCP_SOCKOPT_QPOLICY_ID 16 #define DCCP_SOCKOPT_QPOLICY_TXQLEN 17 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 /* maximum number of services provided on the same listening port */ #define DCCP_SERVICE_LIST_MAX_LEN 32 #endif /* _UAPI_LINUX_DCCP_H */ |
| 13 13 3 7 3 8 1 2 1 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/dax.h> #include <linux/overflow.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> /* * Performs necessary checks before doing a clone. * * Can adjust amount of bytes to clone via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the clone should be allowed. */ static int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; uint64_t count = *req_count; uint64_t bcount; loff_t size_in, size_out; loff_t bs = inode_out->i_sb->s_blocksize; int ret; /* The start of both ranges must be aligned to an fs block. */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) return -EINVAL; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EINVAL; size_in = i_size_read(inode_in); size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ if ((remap_flags & REMAP_FILE_DEDUP) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; /* Ensure the infile range is within the infile. */ if (pos_in >= size_in) return -EINVAL; count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* * If the user wanted us to link to the infile's EOF, round up to the * next block boundary for this check. * * Otherwise, make sure the count is also block-aligned, having * already confirmed the starting offsets' block alignment. */ if (pos_in + count == size_in && (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) { bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) count = ALIGN_DOWN(count, bs); bcount = count; } /* Don't allow overlapped cloning within the same file. */ if (inode_in == inode_out && pos_out + bcount > pos_in && pos_out < pos_in + bcount) return -EINVAL; /* * We shortened the request but the caller can't deal with that, so * bounce the request back to userspace. */ if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) return -EINVAL; *req_count = count; return 0; } int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { int mask = write ? MAY_WRITE : MAY_READ; loff_t tmp; int ret; if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely(check_add_overflow(pos, len, &tmp))) return -EINVAL; ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, &pos, len); } EXPORT_SYMBOL_GPL(remap_verify_area); /* * Ensure that we don't remap a partial EOF block in the middle of something * else. Assume that the offsets have already been checked for block * alignment. * * For clone we only link a partial EOF block above or at the destination file's * EOF. For deduplication we accept a partial EOF block only if it ends at the * destination file's EOF (can not link it into the middle of a file). * * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; if (pos_out + *len < i_size_read(inode_out)) new_len &= ~blkmask; if (new_len == *len) return 0; if (remap_flags & REMAP_FILE_CAN_SHORTEN) { *len = new_len; return 0; } return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* Read a page's worth of file data into the page cache. */ static struct folio *vfs_dedupe_get_folio(struct file *file, loff_t pos) { return read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file); } /* * Lock two folios, ensuring that we lock in offset order if the folios * are from the same file. */ static void vfs_lock_two_folios(struct folio *folio1, struct folio *folio2) { /* Always lock in order of increasing index. */ if (folio1->index > folio2->index) swap(folio1, folio2); folio_lock(folio1); if (folio1 != folio2) folio_lock(folio2); } /* Unlock two folios, being careful not to unlock the same folio twice. */ static void vfs_unlock_two_folios(struct folio *folio1, struct folio *folio2) { folio_unlock(folio1); if (folio1 != folio2) folio_unlock(folio2); } /* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. */ static int vfs_dedupe_file_range_compare(struct file *src, loff_t srcoff, struct file *dest, loff_t dstoff, loff_t len, bool *is_same) { bool same = true; int error = -EINVAL; while (len) { struct folio *src_folio, *dst_folio; void *src_addr, *dst_addr; loff_t cmp_len = min(PAGE_SIZE - offset_in_page(srcoff), PAGE_SIZE - offset_in_page(dstoff)); cmp_len = min(cmp_len, len); if (cmp_len <= 0) goto out_error; src_folio = vfs_dedupe_get_folio(src, srcoff); if (IS_ERR(src_folio)) { error = PTR_ERR(src_folio); goto out_error; } dst_folio = vfs_dedupe_get_folio(dest, dstoff); if (IS_ERR(dst_folio)) { error = PTR_ERR(dst_folio); folio_put(src_folio); goto out_error; } vfs_lock_two_folios(src_folio, dst_folio); /* * Now that we've locked both folios, make sure they're still * mapped to the file data we're interested in. If not, * someone is invalidating pages on us and we lose. */ if (!folio_test_uptodate(src_folio) || !folio_test_uptodate(dst_folio) || src_folio->mapping != src->f_mapping || dst_folio->mapping != dest->f_mapping) { same = false; goto unlock; } src_addr = kmap_local_folio(src_folio, offset_in_folio(src_folio, srcoff)); dst_addr = kmap_local_folio(dst_folio, offset_in_folio(dst_folio, dstoff)); flush_dcache_folio(src_folio); flush_dcache_folio(dst_folio); if (memcmp(src_addr, dst_addr, cmp_len)) same = false; kunmap_local(dst_addr); kunmap_local(src_addr); unlock: vfs_unlock_two_folios(src_folio, dst_folio); folio_put(dst_folio); folio_put(src_folio); if (!same) break; srcoff += cmp_len; dstoff += cmp_len; len -= cmp_len; } *is_same = same; return 0; out_error: return error; } /* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. * * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { loff_t isize = i_size_read(inode_in); if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; *len = isize - pos_in; if (*len == 0) return 0; } /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); if (!same_inode) inode_dio_wait(inode_out); ret = filemap_write_and_wait_range(inode_in->i_mapping, pos_in, pos_in + *len - 1); if (ret) return ret; ret = filemap_write_and_wait_range(inode_out->i_mapping, pos_out, pos_out + *len - 1); if (ret) return ret; /* * Check that the extents are the same. */ if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; if (!IS_DAX(inode_in)) ret = vfs_dedupe_file_range_compare(file_in, pos_in, file_out, pos_out, *len, &is_same); else if (dax_read_ops) ret = dax_dedupe_file_range_compare(inode_in, pos_in, inode_out, pos_out, *len, &is_same, dax_read_ops); else return -EINVAL; if (ret) return ret; if (!is_same) return -EBADE; } ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* If can't alter the file contents, we're done. */ if (!(remap_flags & REMAP_FILE_DEDUP)) ret = file_modified(file_out); return ret; } int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { return __generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, remap_flags, NULL); } EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; ret = generic_file_rw_checks(file_in, file_out); if (ret < 0) return ret; if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file_in, pos_in, len, false); if (ret) return ret; ret = remap_verify_area(file_out, pos_out, len, true); if (ret) return ret; file_start_write(file_out); ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, remap_flags); file_end_write(file_out); if (ret < 0) return ret; fsnotify_access(file_in); fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(vfs_clone_file_range); /* Check whether we are allowed to dedupe the destination file */ static bool may_dedupe_file(struct file *file) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); if (capable(CAP_SYS_ADMIN)) return true; if (file->f_mode & FMODE_WRITE) return true; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) return true; if (!inode_permission(idmap, inode, MAY_WRITE)) return true; return false; } loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_CAN_SHORTEN)); /* * This is redundant if called from vfs_dedupe_file_range(), but other * callers need it and it's not performance sesitive... */ ret = remap_verify_area(src_file, src_pos, len, false); if (ret) return ret; ret = remap_verify_area(dst_file, dst_pos, len, true); if (ret) return ret; /* * This needs to be called after remap_verify_area() because of * sb_start_write() and before may_dedupe_file() because the mount's * MAY_WRITE need to be checked with mnt_get_write_access_file() held. */ ret = mnt_want_write_file(dst_file); if (ret) return ret; ret = -EPERM; if (!may_dedupe_file(dst_file)) goto out_drop_write; ret = -EXDEV; if (file_inode(src_file)->i_sb != file_inode(dst_file)->i_sb) goto out_drop_write; ret = -EISDIR; if (S_ISDIR(file_inode(dst_file)->i_mode)) goto out_drop_write; ret = -EINVAL; if (!dst_file->f_op->remap_file_range) goto out_drop_write; if (len == 0) { ret = 0; goto out_drop_write; } ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, dst_pos, len, remap_flags | REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range_one); int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) { struct file_dedupe_range_info *info; struct inode *src = file_inode(file); u64 off; u64 len; int i; int ret; u16 count = same->dest_count; loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; if (same->reserved1 || same->reserved2) return -EINVAL; off = same->src_offset; len = same->src_length; if (S_ISDIR(src->i_mode)) return -EISDIR; if (!S_ISREG(src->i_mode)) return -EINVAL; if (!file->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file, off, len, false); if (ret < 0) return ret; ret = 0; if (off + len > i_size_read(src)) return -EINVAL; /* Arbitrary 1G limit on a single dedupe request, can be raised. */ len = min_t(u64, len, 1 << 30); /* pre-format output fields to sane values */ for (i = 0; i < count; i++) { same->info[i].bytes_deduped = 0ULL; same->info[i].status = FILE_DEDUPE_RANGE_SAME; } for (i = 0, info = same->info; i < count; i++, info++) { CLASS(fd, dst_fd)(info->dest_fd); if (fd_empty(dst_fd)) { info->status = -EBADF; goto next_loop; } if (info->reserved) { info->status = -EINVAL; goto next_loop; } deduped = vfs_dedupe_file_range_one(file, off, fd_file(dst_fd), info->dest_offset, len, REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) info->status = deduped; else info->bytes_deduped = len; next_loop: if (fatal_signal_pending(current)) break; } return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range); |
| 1 13 1 1 228 17 170 170 189 189 137 71 40 17 39 39 39 39 66 61 1 62 62 66 119 44 1 10 107 35 15 42 92 43 33 10 200 26 26 24 2 2 69 67 3 61 63 63 44 44 129 25 16 4 16 1 13 11 16 19 7 23 2 12 14 61 62 3 93 58 7 64 67 62 62 93 60 7 1 92 92 2 90 66 62 90 40 19 14 14 19 69 84 6 4 4 6 3 3 1 5 90 52 64 93 92 93 62 62 102 59 1 9 232 232 123 44 53 118 14 14 10 4 5 12 16 1 17 17 10 9 17 1 9 9 65 6 22 1 92 92 1 35 58 117 117 1 104 1 2 1 92 58 67 11 209 210 210 48 94 110 110 109 2 1 102 8 5 52 1 14 1 70 6 105 13 3 75 60 105 1 104 91 12 6 71 22 92 77 19 2 91 2 21 9 1 69 9 88 92 22 6 1 59 24 92 92 4 35 28 28 31 6 14 24 58 58 44 43 3 16 38 35 15 38 39 41 41 10 21 22 10 65 1 62 3 63 1 64 64 55 3 64 34 51 61 16 9 25 44 58 44 57 44 64 1 17 61 12 60 16 40 44 64 64 32 32 1 64 32 1 2 2 2 1 28 418 28 59 106 64 170 24 20 20 65 6 4 4 3795 3645 211 422 423 180 106 127 119 9 109 32 32 2 32 54 73 55 75 126 2 126 1 127 148 97 69 71 67 6 95 81 397 396 321 504 505 397 5 4 1 2 1 2 17 2 2 2 2 4 4 7 1 1 1 15 1 2 3 4 1 3 1 179 148 126 162 106 280 102 93 13 201 6 1 5 144 39 108 10 10 7 4 1 2 11 8 8 11 1 1 11 12 9 3 2 1 11 12 1 131 131 2 120 118 2 118 42 24 26 118 2 12 61 61 1 1 1 12 13 12 1 13 13 13 1 23 23 1 23 8 8 2 11 20 19 13 8 9 8 25 2 23 1 1 2 1 1 245 246 101 168 11 166 168 166 207 1 22 23 9 20 2 22 9 59 59 145 144 59 59 59 59 59 107 107 1 106 146 390 | 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 | // SPDX-License-Identifier: GPL-1.0+ /* * originally based on the dummy device. * * Copyright 1999, Thomas Davis, tadavis@lbl.gov. * Based on dummy.c, and eql.c devices. * * bonding.c: an Ethernet Bonding driver * * This is useful to talk to a Cisco EtherChannel compatible equipment: * Cisco 5500 * Sun Trunking (Solaris) * Alteon AceDirector Trunks * Linux Bonding * and probably many L2 switches ... * * How it works: * ifconfig bond0 ipaddress netmask up * will setup a network device, with an ip address. No mac address * will be assigned at this time. The hw mac address will come from * the first slave bonded to the channel. All slaves will then use * this hw mac address. * * ifconfig bond0 down * will release all slaves, marking them as down. * * ifenslave bond0 eth0 * will attach eth0 to bond0 as a slave. eth0 hw mac address will either * a: be used as initial mac address * b: if a hw mac address already is there, eth0's hw mac address * will then be set from bond0. * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/filter.h> #include <linux/interrupt.h> #include <linux/ptrace.h> #include <linux/ioport.h> #include <linux/in.h> #include <net/ip.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <linux/timer.h> #include <linux/socket.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/bitops.h> #include <linux/io.h> #include <asm/dma.h> #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/rtnetlink.h> #include <linux/smp.h> #include <linux/if_ether.h> #include <net/arp.h> #include <linux/mii.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/if_bonding.h> #include <linux/phy.h> #include <linux/jiffies.h> #include <linux/preempt.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/pkt_sched.h> #include <linux/rculist.h> #include <net/flow_dissector.h> #include <net/xfrm.h> #include <net/bonding.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #if IS_ENABLED(CONFIG_TLS_DEVICE) #include <net/tls.h> #endif #include <net/ip6_route.h> #include <net/netdev_lock.h> #include <net/xdp.h> #include "bonding_priv.h" /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int tx_queues = BOND_DEFAULT_TX_QUEUES; static int num_peer_notif = 1; static int miimon; static int updelay; static int downdelay; static int use_carrier = 1; static char *mode; static char *primary; static char *primary_reselect; static char *lacp_rate; static int min_links; static char *ad_select; static char *xmit_hash_policy; static int arp_interval; static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; static char *arp_all_targets; static char *fail_over_mac; static int all_slaves_active; static struct bond_params bonding_defaults; static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; static int packets_per_slave = 1; static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); module_param(tx_queues, int, 0); MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)"); module_param_named(num_grat_arp, num_peer_notif, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on " "failover event (alias of num_unsol_na)"); module_param_named(num_unsol_na, num_peer_notif, int, 0644); MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on " "failover event (alias of num_grat_arp)"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds"); module_param(downdelay, int, 0); MODULE_PARM_DESC(downdelay, "Delay before considering link down, " "in milliseconds"); module_param(use_carrier, int, 0); MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; " "0 for off, 1 for on (default)"); module_param(mode, charp, 0); MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, " "1 for active-backup, 2 for balance-xor, " "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, " "6 for balance-alb"); module_param(primary, charp, 0); MODULE_PARM_DESC(primary, "Primary network device to use"); module_param(primary_reselect, charp, 0); MODULE_PARM_DESC(primary_reselect, "Reselect primary slave " "once it comes up; " "0 for always (default), " "1 for only if speed of primary is " "better, " "2 for only on active slave " "failure"); module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; " "0 for slow, 1 for fast"); module_param(ad_select, charp, 0); MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; " "0 for stable (default), 1 for bandwidth, " "2 for count"); module_param(min_links, int, 0); MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier"); module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; " "0 for layer 2 (default), 1 for layer 3+4, " "2 for layer 2+3, 3 for encap layer 2+3, " "4 for encap layer 3+4, 5 for vlan+srcmac"); module_param(arp_interval, int, 0); MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); module_param_array(arp_ip_target, charp, NULL, 0); MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form"); module_param(arp_validate, charp, 0); MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; " "0 for none (default), 1 for active, " "2 for backup, 3 for all"); module_param(arp_all_targets, charp, 0); MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all"); module_param(fail_over_mac, charp, 0); MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to " "the same MAC; 0 for none (default), " "1 for active, 2 for follow"); module_param(all_slaves_active, int, 0); MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface " "by setting active flag for all slaves; " "0 for never (default), 1 for always."); module_param(resend_igmp, int, 0); MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on " "link failure"); module_param(packets_per_slave, int, 0); MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr " "mode; 0 for a random slave, 1 packet per " "slave (default), >1 packets per slave."); module_param(lp_interval, uint, 0); MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where " "the bonding driver sends learning packets to " "each slaves peer switch. The default is 1."); /*----------------------------- Global variables ----------------------------*/ #ifdef CONFIG_NET_POLL_CONTROLLER atomic_t netpoll_block_tx = ATOMIC_INIT(0); #endif unsigned int bond_net_id __read_mostly; static const struct flow_dissector_key flow_keys_bonding_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_ICMP, .offset = offsetof(struct flow_keys, icmp), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static struct flow_dissector flow_keys_bonding __read_mostly; /*-------------------------- Forward declarations ---------------------------*/ static int bond_init(struct net_device *bond_dev); static void bond_uninit(struct net_device *bond_dev); static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats); static void bond_slave_arr_handler(struct work_struct *work); static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod); static void bond_netdev_notify_work(struct work_struct *work); /*---------------------------- General routines -----------------------------*/ const char *bond_mode_name(int mode) { static const char *names[] = { [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)", [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)", [BOND_MODE_XOR] = "load balancing (xor)", [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)", [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation", [BOND_MODE_TLB] = "transmit load balancing", [BOND_MODE_ALB] = "adaptive load balancing", }; if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; return names[mode]; } /** * bond_dev_queue_xmit - Prepare skb for xmit. * * @bond: bond device that got this skb for tx. * @skb: hw accel VLAN tagged skb to transmit * @slave_dev: slave that is supposed to xmit this skbuff */ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { skb->dev = slave_dev; BUILD_BUG_ON(sizeof(skb->queue_mapping) != sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); if (unlikely(netpoll_tx_running(bond->dev))) return bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); return dev_queue_xmit(skb); } static bool bond_sk_check(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: case BOND_MODE_XOR: if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) return true; fallthrough; default: return false; } } bool bond_xdp_check(struct bonding *bond, int mode) { switch (mode) { case BOND_MODE_ROUNDROBIN: case BOND_MODE_ACTIVEBACKUP: return true; case BOND_MODE_8023AD: case BOND_MODE_XOR: /* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) return true; fallthrough; default: return false; } } /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, * We don't protect the slave list iteration with a lock because: * a. This operation is performed in IOCTL context, * b. The operation is protected by the RTNL semaphore in the 8021q code, * c. Holding a lock with BH disabled while directly calling a base driver * entry point is generally a BAD idea. * * The design of synchronization/protection for this operation in the 8021q * module is good for one or more VLAN devices over a single physical device * and cannot be extended for a teaming solution like bonding, so there is a * potential race condition here where a net device from the vlan group might * be referenced (either by a base driver or the 8021q code) while it is being * removed from the system. However, it turns out we're not making matters * worse, and if it works for regular VLAN usage it will work here too. */ /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct list_head *iter; int res; bond_for_each_slave(bond, slave, iter) { res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; } return 0; unwind: /* unwind to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { if (rollback_slave == slave) break; vlan_vid_del(rollback_slave->dev, proto, vid); } return res; } /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_for_each_slave(bond, slave, iter) vlan_vid_del(slave->dev, proto, vid); if (bond_is_lb(bond)) bond_alb_clear_vlan(bond, vid); return 0; } /*---------------------------------- XFRM -----------------------------------*/ #ifdef CONFIG_XFRM_OFFLOAD /** * bond_ipsec_dev - Get active device for IPsec offload * @xs: pointer to transformer state struct * * Context: caller must hold rcu_read_lock. * * Return: the device for ipsec offload, or NULL if not exist. **/ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct bonding *bond; struct slave *slave; bond = netdev_priv(bond_dev); if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return NULL; slave = rcu_dereference(bond->curr_active_slave); if (!slave) return NULL; if (!xs->xso.real_dev) return NULL; if (xs->xso.real_dev != slave->dev) pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n", bond_dev->name, slave->dev->name, xs->xso.real_dev->name); return slave->dev; } /** * bond_ipsec_add_sa - program device with a security association * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ static int bond_ipsec_add_sa(struct xfrm_state *xs, struct netlink_ext_ack *extack) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; int err; if (!bond_dev) return -EINVAL; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!real_dev) { err = -ENODEV; goto out; } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload"); err = -EINVAL; goto out; } ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL); if (!ipsec) { err = -ENOMEM; goto out; } xs->xso.real_dev = real_dev; err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack); if (!err) { ipsec->xs = xs; INIT_LIST_HEAD(&ipsec->list); mutex_lock(&bond->ipsec_lock); list_add(&ipsec->list, &bond->ipsec_list); mutex_unlock(&bond->ipsec_lock); } else { kfree(ipsec); } out: netdev_put(real_dev, &tracker); return err; } static void bond_ipsec_add_sa_all(struct bonding *bond) { struct net_device *bond_dev = bond->dev; struct net_device *real_dev; struct bond_ipsec *ipsec; struct slave *slave; slave = rtnl_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; if (!real_dev) return; mutex_lock(&bond->ipsec_lock); if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { if (!list_empty(&bond->ipsec_list)) slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_add\n", __func__); goto out; } list_for_each_entry(ipsec, &bond->ipsec_list, list) { /* If new state is added before ipsec_lock acquired */ if (ipsec->xs->xso.real_dev == real_dev) continue; ipsec->xs->xso.real_dev = real_dev; if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); ipsec->xs->xso.real_dev = NULL; } } out: mutex_unlock(&bond->ipsec_lock); } /** * bond_ipsec_del_sa - clear out this specific SA * @xs: pointer to transformer state struct **/ static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; if (!bond_dev) return; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!slave) goto out; if (!xs->xso.real_dev) goto out; WARN_ON(xs->xso.real_dev != real_dev); if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_delete(xs); out: netdev_put(real_dev, &tracker); mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (ipsec->xs == xs) { list_del(&ipsec->list); kfree(ipsec); break; } } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_del_sa_all(struct bonding *bond) { struct net_device *bond_dev = bond->dev; struct net_device *real_dev; struct bond_ipsec *ipsec; struct slave *slave; slave = rtnl_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; if (!real_dev) return; mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (!ipsec->xs->xso.real_dev) continue; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); } else { real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); if (real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs); } } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_free_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bonding *bond; struct slave *slave; if (!bond_dev) return; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!slave) goto out; if (!xs->xso.real_dev) goto out; WARN_ON(xs->xso.real_dev != real_dev); if (real_dev && real_dev->xfrmdev_ops && real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(xs); out: netdev_put(real_dev, &tracker); } /** * bond_ipsec_offload_ok - can this packet use the xfrm hw offload * @skb: current data packet * @xs: pointer to transformer state struct **/ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev || netif_is_bond_master(real_dev)) { rcu_read_unlock(); return false; } rcu_read_unlock(); return true; } /** * bond_advance_esn_state - ESN support for IPSec HW offload * @xs: pointer to transformer state struct **/ static void bond_advance_esn_state(struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) { pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs); out: rcu_read_unlock(); } /** * bond_xfrm_update_stats - Update xfrm state * @xs: pointer to transformer state struct **/ static void bond_xfrm_update_stats(struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_update_stats) { pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs); out: rcu_read_unlock(); } static const struct xfrmdev_ops bond_xfrmdev_ops = { .xdo_dev_state_add = bond_ipsec_add_sa, .xdo_dev_state_delete = bond_ipsec_del_sa, .xdo_dev_state_free = bond_ipsec_free_sa, .xdo_dev_offload_ok = bond_ipsec_offload_ok, .xdo_dev_state_advance_esn = bond_advance_esn_state, .xdo_dev_state_update_stats = bond_xfrm_update_stats, }; #endif /* CONFIG_XFRM_OFFLOAD */ /*------------------------------- Link status -------------------------------*/ /* Set the carrier state for the master according to the state of its * slaves. If any slaves are up, the master is up. In 802.3ad mode, * do special 802.3ad magic. * * Returns zero if carrier state does not change, nonzero if it does. */ int bond_set_carrier(struct bonding *bond) { struct list_head *iter; struct slave *slave; if (!bond_has_slaves(bond)) goto down; if (BOND_MODE(bond) == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); return 1; } return 0; } } down: if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); return 1; } return 0; } /* Get link speed and duplex from the slave's base driver * using ethtool. If for some reason the call fails or the * values are invalid, set speed and duplex to -1, * and return. Return 1 if speed or duplex settings are * UNKNOWN; 0 otherwise. */ static int bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; struct ethtool_link_ksettings ecmd; int res; slave->speed = SPEED_UNKNOWN; slave->duplex = DUPLEX_UNKNOWN; res = __ethtool_get_link_ksettings(slave_dev, &ecmd); if (res < 0) return 1; if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1)) return 1; switch (ecmd.base.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: return 1; } slave->speed = ecmd.base.speed; slave->duplex = ecmd.base.duplex; return 0; } const char *bond_slave_link_status(s8 link) { switch (link) { case BOND_LINK_UP: return "up"; case BOND_LINK_FAIL: return "going down"; case BOND_LINK_DOWN: return "down"; case BOND_LINK_BACK: return "going back"; default: return "unknown"; } } /* if <dev> supports MII link status reporting, check its link status. * * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), * depending upon the setting of the use_carrier parameter. * * Return either BMSR_LSTATUS, meaning that the link is up (or we * can't tell and just pretend it is), or 0, meaning that the link is * down. * * If reporting is non-zero, instead of faking link up, return -1 if * both ETHTOOL and MII ioctls fail (meaning the device does not * support them). If use_carrier is set, return whatever it says. * It'd be nice if there was a good way to tell if a driver supports * netif_carrier, but there really isn't. */ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_dev, int reporting) { const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct mii_ioctl_data *mii; struct ifreq ifr; int ret; if (!reporting && !netif_running(slave_dev)) return 0; if (bond->params.use_carrier) return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; /* Try to get link status using Ethtool first. */ if (slave_dev->ethtool_ops->get_link) { netdev_lock_ops(slave_dev); ret = slave_dev->ethtool_ops->get_link(slave_dev); netdev_unlock_ops(slave_dev); return ret ? BMSR_LSTATUS : 0; } /* Ethtool can't be used, fallback to MII ioctls. */ if (slave_ops->ndo_eth_ioctl) { /* TODO: set pointer to correct ioctl on a per team member * bases to make this more efficient. that is, once * we determine the correct ioctl, we will always * call it and not the others for that team * member. */ /* We cannot assume that SIOCGMIIPHY will also read a * register; not all network drivers (e.g., e100) * support that. */ /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ); mii = if_mii(&ifr); if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0) return mii->val_out & BMSR_LSTATUS; } } /* If reporting, report that either there's no ndo_eth_ioctl, * or both SIOCGMIIREG and get_link failed (meaning that we * cannot report link status). If not reporting, pretend * we're ok. */ return reporting ? -1 : BMSR_LSTATUS; } /*----------------------------- Multicast list ------------------------------*/ /* Push the promiscuity flag down to appropriate slaves */ static int bond_set_promiscuity(struct bonding *bond, int inc) { struct list_head *iter; int err = 0; if (bond_uses_primary(bond)) { struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); if (curr_active) err = dev_set_promiscuity(curr_active->dev, inc); } else { struct slave *slave; bond_for_each_slave(bond, slave, iter) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; } } return err; } /* Push the allmulti flag down to all slaves */ static int bond_set_allmulti(struct bonding *bond, int inc) { struct list_head *iter; int err = 0; if (bond_uses_primary(bond)) { struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); if (curr_active) err = dev_set_allmulti(curr_active->dev, inc); } else { struct slave *slave; bond_for_each_slave(bond, slave, iter) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; } } return err; } /* Retrieve the list of registered multicast addresses for the bonding * device and retransmit an IGMP JOIN request to the current active * slave. */ static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mcast_work.work); if (!rtnl_trylock()) { queue_delayed_work(bond->wq, &bond->mcast_work, 1); return; } call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); if (bond->igmp_retrans > 1) { bond->igmp_retrans--; queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); } rtnl_unlock(); } /* Flush bond's hardware addresses from slave */ static void bond_hw_addr_flush(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); dev_uc_unsync(slave_dev, bond_dev); dev_mc_unsync(slave_dev, bond_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) dev_mc_del(slave_dev, lacpdu_mcast_addr); } /*--------------------------- Active slave change ---------------------------*/ /* Update the hardware address list and promisc/allmulti for the new and * old active slaves (if any). Modes that are not using primary keep all * slaves up date at all times; only the modes that use primary need to call * this function to swap these settings during a failover. */ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) { if (old_active) { if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(old_active->dev, -1); if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); if (bond->dev->flags & IFF_UP) bond_hw_addr_flush(bond->dev, old_active->dev); bond_slave_ns_maddrs_add(bond, old_active); } if (new_active) { /* FIXME: Signal errors upstream. */ if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(new_active->dev, 1); if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); if (bond->dev->flags & IFF_UP) { netif_addr_lock_bh(bond->dev); dev_uc_sync(new_active->dev, bond->dev); dev_mc_sync(new_active->dev, bond->dev); netif_addr_unlock_bh(bond->dev); } bond_slave_ns_maddrs_del(bond, new_active); } } /** * bond_set_dev_addr - clone slave's address to bond * @bond_dev: bond net device * @slave_dev: slave net device * * Should be called with RTNL held. */ static int bond_set_dev_addr(struct net_device *bond_dev, struct net_device *slave_dev) { int err; slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", bond_dev, slave_dev, slave_dev->addr_len); err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); if (err) return err; __dev_addr_set(bond_dev, slave_dev->dev_addr, slave_dev->addr_len); bond_dev->addr_assign_type = NET_ADDR_STOLEN; call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev); return 0; } static struct slave *bond_get_old_active(struct bonding *bond, struct slave *new_active) { struct slave *slave; struct list_head *iter; bond_for_each_slave(bond, slave, iter) { if (slave == new_active) continue; if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr)) return slave; } return NULL; } /* bond_do_fail_over_mac * * Perform special MAC address swapping for fail_over_mac settings * * Called with RTNL */ static void bond_do_fail_over_mac(struct bonding *bond, struct slave *new_active, struct slave *old_active) { u8 tmp_mac[MAX_ADDR_LEN]; struct sockaddr_storage ss; int rv; switch (bond->params.fail_over_mac) { case BOND_FOM_ACTIVE: if (new_active) { rv = bond_set_dev_addr(bond->dev, new_active->dev); if (rv) slave_err(bond->dev, new_active->dev, "Error %d setting bond MAC from slave\n", -rv); } break; case BOND_FOM_FOLLOW: /* if new_active && old_active, swap them * if just old_active, do nothing (going to no active slave) * if just new_active, set new_active to bond's MAC */ if (!new_active) return; if (!old_active) old_active = bond_get_old_active(bond, new_active); if (old_active) { bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr, new_active->dev->addr_len); bond_hw_addr_copy(ss.__data, old_active->dev->dev_addr, old_active->dev->addr_len); ss.ss_family = new_active->dev->type; } else { bond_hw_addr_copy(ss.__data, bond->dev->dev_addr, bond->dev->addr_len); ss.ss_family = bond->dev->type; } rv = dev_set_mac_address(new_active->dev, (struct sockaddr *)&ss, NULL); if (rv) { slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n", -rv); goto out; } if (!old_active) goto out; bond_hw_addr_copy(ss.__data, tmp_mac, new_active->dev->addr_len); ss.ss_family = old_active->dev->type; rv = dev_set_mac_address(old_active->dev, (struct sockaddr *)&ss, NULL); if (rv) slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n", -rv); out: break; default: netdev_err(bond->dev, "bond_do_fail_over_mac impossible: bad policy %d\n", bond->params.fail_over_mac); break; } } /** * bond_choose_primary_or_current - select the primary or high priority slave * @bond: our bonding struct * * - Check if there is a primary link. If the primary link was set and is up, * go on and do link reselection. * * - If primary link is not set or down, find the highest priority link. * If the highest priority link is not current slave, set it as primary * link and do link reselection. */ static struct slave *bond_choose_primary_or_current(struct bonding *bond) { struct slave *prim = rtnl_dereference(bond->primary_slave); struct slave *curr = rtnl_dereference(bond->curr_active_slave); struct slave *slave, *hprio = NULL; struct list_head *iter; if (!prim || prim->link != BOND_LINK_UP) { bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { hprio = hprio ?: slave; if (slave->prio > hprio->prio) hprio = slave; } } if (hprio && hprio != curr) { prim = hprio; goto link_reselect; } if (!curr || curr->link != BOND_LINK_UP) return NULL; return curr; } if (bond->force_primary) { bond->force_primary = false; return prim; } link_reselect: if (!curr || curr->link != BOND_LINK_UP) return prim; /* At this point, prim and curr are both up */ switch (bond->params.primary_reselect) { case BOND_PRI_RESELECT_ALWAYS: return prim; case BOND_PRI_RESELECT_BETTER: if (prim->speed < curr->speed) return curr; if (prim->speed == curr->speed && prim->duplex <= curr->duplex) return curr; return prim; case BOND_PRI_RESELECT_FAILURE: return curr; default: netdev_err(bond->dev, "impossible primary_reselect %d\n", bond->params.primary_reselect); return curr; } } /** * bond_find_best_slave - select the best available slave to be the active one * @bond: our bonding struct */ static struct slave *bond_find_best_slave(struct bonding *bond) { struct slave *slave, *bestslave = NULL; struct list_head *iter; int mintime = bond->params.updelay; slave = bond_choose_primary_or_current(bond); if (slave) return slave; bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) return slave; if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) && slave->delay < mintime) { mintime = slave->delay; bestslave = slave; } } return bestslave; } /* must be called in RCU critical section or with RTNL held */ static bool bond_should_notify_peers(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); if (!slave || !bond->send_peer_notif || bond->send_peer_notif % max(1, bond->params.peer_notif_delay) != 0 || !netif_carrier_ok(bond->dev) || test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n", slave ? slave->dev->name : "NULL"); return true; } /** * bond_change_active_slave - change the active slave into the specified one * @bond: our bonding struct * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. * Setting include flags, mc-list, promiscuity, allmulti, etc. * * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP, * because it is apparently the best available slave we have, even though its * updelay hasn't timed out yet. * * Caller must hold RTNL. */ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) { struct slave *old_active; ASSERT_RTNL(); old_active = rtnl_dereference(bond->curr_active_slave); if (old_active == new_active) return; #ifdef CONFIG_XFRM_OFFLOAD bond_ipsec_del_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ if (new_active) { new_active->last_link_up = jiffies; if (new_active->link == BOND_LINK_BACK) { if (bond_uses_primary(bond)) { slave_info(bond->dev, new_active->dev, "making interface the new active one %d ms earlier\n", (bond->params.updelay - new_active->delay) * bond->params.miimon); } new_active->delay = 0; bond_set_slave_link_state(new_active, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(new_active, BOND_LINK_UP); if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { if (bond_uses_primary(bond)) slave_info(bond->dev, new_active->dev, "making interface the new active one\n"); } } if (bond_uses_primary(bond)) bond_hw_addr_swap(bond, new_active, old_active); if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) bond_set_slave_inactive_flags(old_active, BOND_SLAVE_NOTIFY_NOW); if (new_active) bond_set_slave_active_flags(new_active, BOND_SLAVE_NOTIFY_NOW); } else { rcu_assign_pointer(bond->curr_active_slave, new_active); } if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { if (old_active) bond_set_slave_inactive_flags(old_active, BOND_SLAVE_NOTIFY_NOW); if (new_active) { bool should_notify_peers = false; bond_set_slave_active_flags(new_active, BOND_SLAVE_NOTIFY_NOW); if (bond->params.fail_over_mac) bond_do_fail_over_mac(bond, new_active, old_active); if (netif_running(bond->dev)) { bond->send_peer_notif = bond->params.num_peer_notif * max(1, bond->params.peer_notif_delay); should_notify_peers = bond_should_notify_peers(bond); } call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); if (should_notify_peers) { bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } } } #ifdef CONFIG_XFRM_OFFLOAD bond_ipsec_add_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ /* resend IGMP joins since active slave has changed or * all were sent on curr_active_slave. * resend only if bond is brought up with the affected * bonding modes and the retransmission is enabled */ if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) && ((bond_uses_primary(bond) && new_active) || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) { bond->igmp_retrans = bond->params.resend_igmp; queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } /** * bond_select_active_slave - select a new active slave, if needed * @bond: our bonding struct * * This functions should be called when one of the following occurs: * - The old curr_active_slave has been released or lost its link. * - The primary_slave has got its link back. * - A slave has got its link back and there's no old curr_active_slave. * * Caller must hold RTNL. */ void bond_select_active_slave(struct bonding *bond) { struct slave *best_slave; int rv; ASSERT_RTNL(); best_slave = bond_find_best_slave(bond); if (best_slave != rtnl_dereference(bond->curr_active_slave)) { bond_change_active_slave(bond, best_slave); rv = bond_set_carrier(bond); if (!rv) return; if (netif_carrier_ok(bond->dev)) netdev_info(bond->dev, "active interface up!\n"); else netdev_info(bond->dev, "now running without any active interface!\n"); } } #ifdef CONFIG_NET_POLL_CONTROLLER static inline int slave_enable_netpoll(struct slave *slave) { struct netpoll *np; int err = 0; np = kzalloc(sizeof(*np), GFP_KERNEL); err = -ENOMEM; if (!np) goto out; err = __netpoll_setup(np, slave->dev); if (err) { kfree(np); goto out; } slave->np = np; out: return err; } static inline void slave_disable_netpoll(struct slave *slave) { struct netpoll *np = slave->np; if (!np) return; slave->np = NULL; __netpoll_free(np); } static void bond_poll_controller(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; struct list_head *iter; struct ad_info ad_info; if (BOND_MODE(bond) == BOND_MODE_8023AD) if (bond_3ad_get_active_agg_info(bond, &ad_info)) return; bond_for_each_slave_rcu(bond, slave, iter) { if (!bond_slave_is_up(slave)) continue; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = SLAVE_AD_INFO(slave)->port.aggregator; if (agg && agg->aggregator_identifier != ad_info.aggregator_id) continue; } netpoll_poll_dev(slave->dev); } } static void bond_netpoll_cleanup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_for_each_slave(bond, slave, iter) if (bond_slave_is_up(slave)) slave_disable_netpoll(slave); } static int bond_netpoll_setup(struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; struct slave *slave; int err = 0; bond_for_each_slave(bond, slave, iter) { err = slave_enable_netpoll(slave); if (err) { bond_netpoll_cleanup(dev); break; } } return err; } #else static inline int slave_enable_netpoll(struct slave *slave) { return 0; } static inline void slave_disable_netpoll(struct slave *slave) { } static void bond_netpoll_cleanup(struct net_device *bond_dev) { } #endif /*---------------------------------- IOCTL ----------------------------------*/ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t features) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; netdev_features_t mask; struct slave *slave; mask = features; features = netdev_base_features(features); bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, slave->dev->features, mask); } features = netdev_add_tso_features(features, mask); return features; } #define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_PARTIAL) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_GSO_SOFTWARE) #define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) static void bond_compute_features(struct bonding *bond) { netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; #ifdef CONFIG_XFRM_OFFLOAD netdev_features_t xfrm_features = BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ netdev_features_t mpls_features = BOND_MPLS_FEATURES; struct net_device *bond_dev = bond->dev; struct list_head *iter; struct slave *slave; unsigned short max_hard_header_len = ETH_HLEN; unsigned int tso_max_size = TSO_MAX_SIZE; u16 tso_max_segs = TSO_MAX_SEGS; if (!bond_has_slaves(bond)) goto done; vlan_features = netdev_base_features(vlan_features); mpls_features = netdev_base_features(mpls_features); bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, slave->dev->hw_enc_features, BOND_ENC_FEATURES); #ifdef CONFIG_XFRM_OFFLOAD xfrm_features = netdev_increment_features(xfrm_features, slave->dev->hw_enc_features, BOND_XFRM_FEATURES); #endif /* CONFIG_XFRM_OFFLOAD */ gso_partial_features = netdev_increment_features(gso_partial_features, slave->dev->gso_partial_features, BOND_GSO_PARTIAL_FEATURES); mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, BOND_MPLS_FEATURES); dst_release_flag &= slave->dev->priv_flags; if (slave->dev->hard_header_len > max_hard_header_len) max_hard_header_len = slave->dev->hard_header_len; tso_max_size = min(tso_max_size, slave->dev->tso_max_size); tso_max_segs = min(tso_max_segs, slave->dev->tso_max_segs); } bond_dev->hard_header_len = max_hard_header_len; done: bond_dev->gso_partial_features = gso_partial_features; bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_enc_features |= xfrm_features; #endif /* CONFIG_XFRM_OFFLOAD */ bond_dev->mpls_features = mpls_features; netif_set_tso_max_segs(bond_dev, tso_max_segs); netif_set_tso_max_size(bond_dev, tso_max_size); bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) && dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE; netdev_change_features(bond_dev); } static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { bool was_up = !!(bond_dev->flags & IFF_UP); dev_close(bond_dev); bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len; memcpy(bond_dev->broadcast, slave_dev->broadcast, slave_dev->addr_len); if (slave_dev->flags & IFF_POINTOPOINT) { bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } if (was_up) dev_open(bond_dev, NULL); } /* On bonding slaves other than the currently active slave, suppress * duplicates except for alb non-mcast/bcast. */ static bool bond_should_deliver_exact_match(struct sk_buff *skb, struct slave *slave, struct bonding *bond) { if (bond_is_slave_inactive(slave)) { if (BOND_MODE(bond) == BOND_MODE_ALB && skb->pkt_type != PACKET_BROADCAST && skb->pkt_type != PACKET_MULTICAST) return false; return true; } return false; } static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct slave *slave; struct bonding *bond; int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); int ret = RX_HANDLER_ANOTHER; skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) return RX_HANDLER_CONSUMED; *pskb = skb; slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; recv_probe = READ_ONCE(bond->recv_probe); if (recv_probe) { ret = recv_probe(skb, bond, slave); if (ret == RX_HANDLER_CONSUMED) { consume_skb(skb); return ret; } } /* * For packets determined by bond_should_deliver_exact_match() call to * be suppressed we want to make an exception for link-local packets. * This is necessary for e.g. LLDP daemons to be able to monitor * inactive slave links without being forced to bind to them * explicitly. * * At the same time, packets that are passed to the bonding master * (including link-local ones) can have their originating interface * determined via PACKET_ORIGDEV socket option. */ if (bond_should_deliver_exact_match(skb, slave, bond)) { if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) return RX_HANDLER_PASS; return RX_HANDLER_EXACT; } skb->dev = bond->dev; if (BOND_MODE(bond) == BOND_MODE_ALB && netif_is_bridge_port(bond->dev) && skb->pkt_type == PACKET_HOST) { if (unlikely(skb_cow_head(skb, skb->data - skb_mac_header(skb)))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, bond->dev->addr_len); } return ret; } static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return NETDEV_LAG_TX_TYPE_ROUNDROBIN; case BOND_MODE_ACTIVEBACKUP: return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; case BOND_MODE_BROADCAST: return NETDEV_LAG_TX_TYPE_BROADCAST; case BOND_MODE_XOR: case BOND_MODE_8023AD: return NETDEV_LAG_TX_TYPE_HASH; default: return NETDEV_LAG_TX_TYPE_UNKNOWN; } } static enum netdev_lag_hash bond_lag_hash_type(struct bonding *bond, enum netdev_lag_tx_type type) { if (type != NETDEV_LAG_TX_TYPE_HASH) return NETDEV_LAG_HASH_NONE; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_LAYER2: return NETDEV_LAG_HASH_L2; case BOND_XMIT_POLICY_LAYER34: return NETDEV_LAG_HASH_L34; case BOND_XMIT_POLICY_LAYER23: return NETDEV_LAG_HASH_L23; case BOND_XMIT_POLICY_ENCAP23: return NETDEV_LAG_HASH_E23; case BOND_XMIT_POLICY_ENCAP34: return NETDEV_LAG_HASH_E34; case BOND_XMIT_POLICY_VLAN_SRCMAC: return NETDEV_LAG_HASH_VLAN_SRCMAC; default: return NETDEV_LAG_HASH_UNKNOWN; } } static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; enum netdev_lag_tx_type type; int err; type = bond_lag_tx_type(bond); lag_upper_info.tx_type = type; lag_upper_info.hash_type = bond_lag_hash_type(bond, type); err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave, &lag_upper_info, extack); if (err) return err; slave->dev->flags |= IFF_SLAVE; return 0; } static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave) { netdev_upper_dev_unlink(slave->dev, bond->dev); slave->dev->flags &= ~IFF_SLAVE; } static void slave_kobj_release(struct kobject *kobj) { struct slave *slave = to_slave(kobj); struct bonding *bond = bond_get_bond_by_slave(slave); cancel_delayed_work_sync(&slave->notify_work); if (BOND_MODE(bond) == BOND_MODE_8023AD) kfree(SLAVE_AD_INFO(slave)); kfree(slave); } static struct kobj_type slave_ktype = { .release = slave_kobj_release, #ifdef CONFIG_SYSFS .sysfs_ops = &slave_sysfs_ops, #endif }; static int bond_kobj_init(struct slave *slave) { int err; err = kobject_init_and_add(&slave->kobj, &slave_ktype, &(slave->dev->dev.kobj), "bonding_slave"); if (err) kobject_put(&slave->kobj); return err; } static struct slave *bond_alloc_slave(struct bonding *bond, struct net_device *slave_dev) { struct slave *slave = NULL; slave = kzalloc(sizeof(*slave), GFP_KERNEL); if (!slave) return NULL; slave->bond = bond; slave->dev = slave_dev; INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); if (bond_kobj_init(slave)) return NULL; if (BOND_MODE(bond) == BOND_MODE_8023AD) { SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), GFP_KERNEL); if (!SLAVE_AD_INFO(slave)) { kobject_put(&slave->kobj); return NULL; } } return slave; } static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) { info->bond_mode = BOND_MODE(bond); info->miimon = bond->params.miimon; info->num_slaves = bond->slave_cnt; } static void bond_fill_ifslave(struct slave *slave, struct ifslave *info) { strcpy(info->slave_name, slave->dev->name); info->link = slave->link; info->state = bond_slave_state(slave); info->link_failure_count = slave->link_failure_count; } static void bond_netdev_notify_work(struct work_struct *_work) { struct slave *slave = container_of(_work, struct slave, notify_work.work); if (rtnl_trylock()) { struct netdev_bonding_info binfo; bond_fill_ifslave(slave, &binfo.slave); bond_fill_ifbond(slave->bond, &binfo.master); netdev_bonding_info_change(slave->dev, &binfo); rtnl_unlock(); } else { queue_delayed_work(slave->bond->wq, &slave->notify_work, 1); } } void bond_queue_slave_event(struct slave *slave) { queue_delayed_work(slave->bond->wq, &slave->notify_work, 0); } void bond_lower_state_changed(struct slave *slave) { struct netdev_lag_lower_state_info info; info.link_up = slave->link == BOND_LINK_UP || slave->link == BOND_LINK_FAIL; info.tx_enabled = bond_is_active_slave(slave); netdev_lower_state_changed(slave->dev, &info); } #define BOND_NL_ERR(bond_dev, extack, errmsg) do { \ if (extack) \ NL_SET_ERR_MSG(extack, errmsg); \ else \ netdev_err(bond_dev, "Error: %s\n", errmsg); \ } while (0) #define SLAVE_NL_ERR(bond_dev, slave_dev, extack, errmsg) do { \ if (extack) \ NL_SET_ERR_MSG(extack, errmsg); \ else \ slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg); \ } while (0) /* The bonding driver uses ether_setup() to convert a master bond device * to ARPHRD_ETHER, that resets the target netdevice's flags so we always * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP * if they were set */ static void bond_ether_setup(struct net_device *bond_dev) { unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP); ether_setup(bond_dev); bond_dev->flags |= IFF_MASTER | flags; bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } void bond_xdp_set_features(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); xdp_features_t val = NETDEV_XDP_ACT_MASK; struct list_head *iter; struct slave *slave; ASSERT_RTNL(); if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } bond_for_each_slave(bond, slave, iter) val &= slave->dev->xdp_features; val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY; xdp_set_features_flag(bond_dev, val); } /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct slave *new_slave = NULL, *prev_slave; struct sockaddr_storage ss; int link_reporting; int res = 0, i; if (slave_dev->flags & IFF_MASTER && !netif_is_bond_master(slave_dev)) { BOND_NL_ERR(bond_dev, extack, "Device type (master device) cannot be enslaved"); return -EPERM; } if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && slave_ops->ndo_eth_ioctl == NULL) { slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); } /* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device is in use and cannot be enslaved"); return -EBUSY; } if (bond_dev == slave_dev) { BOND_NL_ERR(bond_dev, extack, "Cannot enslave bond to itself."); return -EPERM; } /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n"); if (vlan_uses_dev(bond_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Can not enslave VLAN challenged device to VLAN enabled bond"); return -EPERM; } else { slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n"); } } else { slave_dbg(bond_dev, slave_dev, "is !NETIF_F_VLAN_CHALLENGED\n"); } if (slave_dev->features & NETIF_F_HW_ESP) slave_dbg(bond_dev, slave_dev, "is esp-hw-offload capable\n"); /* Old ifenslave binaries are no longer supported. These can * be identified with moderate accuracy by the state of the slave: * the current ifenslave will set the interface down prior to * enslaving it; the old ifenslave will not. */ if (slave_dev->flags & IFF_UP) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device can not be enslaved while up"); return -EPERM; } /* set bonding device ether type by slave - bonding netdevices are * created with ether_setup, so when the slave type is not ARPHRD_ETHER * there is a need to override some of the type dependent attribs/funcs. * * bond ether type mutual exclusion - don't allow slaves of dissimilar * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", bond_dev->type, slave_dev->type); res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, bond_dev); res = notifier_to_errno(res); if (res) { slave_err(bond_dev, slave_dev, "refused to change device type\n"); return -EBUSY; } /* Flush unicast and multicast addresses */ dev_uc_flush(bond_dev); dev_mc_flush(bond_dev); if (slave_dev->type != ARPHRD_ETHER) bond_setup_by_slave(bond_dev, slave_dev); else bond_ether_setup(bond_dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, bond_dev); } } else if (bond_dev->type != slave_dev->type) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device type is different from other slaves"); return -EINVAL; } if (slave_dev->type == ARPHRD_INFINIBAND && BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Only active-backup mode is supported for infiniband slaves"); res = -EOPNOTSUPP; goto err_undo_flags; } if (!slave_ops->ndo_set_mac_address || slave_dev->type == ARPHRD_INFINIBAND) { slave_warn(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address\n"); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && bond->params.fail_over_mac != BOND_FOM_ACTIVE) { if (!bond_has_slaves(bond)) { bond->params.fail_over_mac = BOND_FOM_ACTIVE; slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n"); } else { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); res = -EOPNOTSUPP; goto err_undo_flags; } } } call_netdevice_notifiers(NETDEV_JOIN, slave_dev); /* If this is the first slave, then we need to set the master's hardware * address to be the same as the slave's. */ if (!bond_has_slaves(bond) && bond->dev->addr_assign_type == NET_ADDR_RANDOM) { res = bond_set_dev_addr(bond->dev, slave_dev); if (res) goto err_undo_flags; } new_slave = bond_alloc_slave(bond, slave_dev); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } /* Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. */ new_slave->queue_id = 0; /* Save slave's original mtu and then set it to match the bond */ new_slave->original_mtu = slave_dev->mtu; res = dev_set_mtu(slave_dev, bond->dev->mtu); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling dev_set_mtu\n", res); goto err_free; } /* Save slave's original ("permanent") mac address for modes * that need it, and for restoring it upon release, and then * set it to the master's address */ bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr, slave_dev->addr_len); if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* Set slave to master's mac address. The application already * set the master's mac address to that of the first slave */ memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); ss.ss_family = slave_dev->type; res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, extack); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); goto err_restore_mtu; } } /* set no_addrconf flag before open to prevent IPv6 addrconf */ slave_dev->priv_flags |= IFF_NO_ADDRCONF; /* open the slave since the application closed it */ res = dev_open(slave_dev, extack); if (res) { slave_err(bond_dev, slave_dev, "Opening slave failed\n"); goto err_restore_mac; } slave_dev->priv_flags |= IFF_BONDING; /* initialize slave stats */ dev_get_stats(new_slave->dev, &new_slave->slave_stats); if (bond_is_lb(bond)) { /* bond_alb_init_slave() must be called before all other stages since * it might fail and we do not want to have to undo everything */ res = bond_alb_init_slave(bond, new_slave); if (res) goto err_close; } res = vlan_vids_add_by_dev(slave_dev, bond_dev); if (res) { slave_err(bond_dev, slave_dev, "Couldn't add bond vlan ids\n"); goto err_close; } prev_slave = bond_last_slave(bond); new_slave->delay = 0; new_slave->link_failure_count = 0; if (bond_update_speed_duplex(new_slave) && bond_needs_speed_duplex(bond)) new_slave->link = BOND_LINK_DOWN; new_slave->last_rx = jiffies - (msecs_to_jiffies(bond->params.arp_interval) + 1); for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) new_slave->target_last_arp_rx[i] = new_slave->last_rx; new_slave->last_tx = new_slave->last_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); if ((link_reporting == -1) && !bond->params.arp_interval) { /* miimon is set but a bonded network driver * does not support ETHTOOL/MII and * arp_interval is not set. Note: if * use_carrier is enabled, we will never go * here (because netif_carrier is always * supported); thus, we don't need to change * the messages for netif_carrier. */ slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n"); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n"); } } /* check for initial state */ new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { if (bond->params.updelay) { bond_set_slave_link_state(new_slave, BOND_LINK_BACK, BOND_SLAVE_NOTIFY_NOW); new_slave->delay = bond->params.updelay; } else { bond_set_slave_link_state(new_slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); } } else { bond_set_slave_link_state(new_slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); } } else if (bond->params.arp_interval) { bond_set_slave_link_state(new_slave, (netif_carrier_ok(slave_dev) ? BOND_LINK_UP : BOND_LINK_DOWN), BOND_SLAVE_NOTIFY_NOW); } else { bond_set_slave_link_state(new_slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); } if (new_slave->link != BOND_LINK_DOWN) new_slave->last_link_up = jiffies; slave_dbg(bond_dev, slave_dev, "Initial state of slave is BOND_LINK_%s\n", new_slave->link == BOND_LINK_DOWN ? "DOWN" : (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); if (bond_uses_primary(bond) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ if (strcmp(bond->params.primary, new_slave->dev->name) == 0) { rcu_assign_pointer(bond->primary_slave, new_slave); bond->force_primary = true; } } switch (BOND_MODE(bond)) { case BOND_MODE_ACTIVEBACKUP: bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ if (!prev_slave) { SLAVE_AD_INFO(new_slave)->id = 1; /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ bond_3ad_initialize(bond); } else { SLAVE_AD_INFO(new_slave)->id = SLAVE_AD_INFO(prev_slave)->id + 1; } bond_3ad_bind_slave(new_slave); break; case BOND_MODE_TLB: case BOND_MODE_ALB: bond_set_active_slave(new_slave); bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: slave_dbg(bond_dev, slave_dev, "This slave is always active in trunk mode\n"); /* always active in trunk mode */ bond_set_active_slave(new_slave); /* In trunking mode there is little meaning to curr_active_slave * anyway (it holds no special properties of the bond device), * so we can change it without calling change_active_interface() */ if (!rcu_access_pointer(bond->curr_active_slave) && new_slave->link == BOND_LINK_UP) rcu_assign_pointer(bond->curr_active_slave, new_slave); break; } /* switch(bond_mode) */ #ifdef CONFIG_NET_POLL_CONTROLLER if (bond->dev->npinfo) { if (slave_enable_netpoll(new_slave)) { slave_info(bond_dev, slave_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); res = -EBUSY; goto err_detach; } } #endif if (!(bond_dev->features & NETIF_F_LRO)) dev_disable_lro(slave_dev); res = netdev_rx_handler_register(slave_dev, bond_handle_frame, new_slave); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling netdev_rx_handler_register\n", res); goto err_detach; } res = bond_master_upper_dev_link(bond, new_slave, extack); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling bond_master_upper_dev_link\n", res); goto err_unregister; } bond_lower_state_changed(new_slave); res = bond_sysfs_slave_add(new_slave); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling bond_sysfs_slave_add\n", res); goto err_upper_unlink; } /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ if (!bond_uses_primary(bond)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { res = dev_set_promiscuity(slave_dev, 1); if (res) goto err_sysfs_del; } /* set allmulti level to new slave */ if (bond_dev->flags & IFF_ALLMULTI) { res = dev_set_allmulti(slave_dev, 1); if (res) { if (bond_dev->flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); goto err_sysfs_del; } } if (bond_dev->flags & IFF_UP) { netif_addr_lock_bh(bond_dev); dev_mc_sync_multiple(slave_dev, bond_dev); dev_uc_sync_multiple(slave_dev, bond_dev); netif_addr_unlock_bh(bond_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) dev_mc_add(slave_dev, lacpdu_mcast_addr); } } bond->slave_cnt++; bond_compute_features(bond); bond_set_carrier(bond); /* Needs to be called before bond_select_active_slave(), which will * remove the maddrs if the slave is selected as active slave. */ bond_slave_ns_maddrs_add(bond, new_slave); if (bond_uses_primary(bond)) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave does not support XDP"); res = -EOPNOTSUPP; goto err_sysfs_del; } } else if (bond->xdp_prog) { struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = bond->xdp_prog, .extack = extack, }; if (dev_xdp_prog_count(slave_dev) > 0) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave has XDP program loaded, please unload before enslaving"); res = -EOPNOTSUPP; goto err_sysfs_del; } res = dev_xdp_propagate(slave_dev, &xdp); if (res < 0) { /* ndo_bpf() sets extack error message */ slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); goto err_sysfs_del; } if (bond->xdp_prog) bpf_prog_inc(bond->xdp_prog); } bond_xdp_set_features(bond_dev); slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", bond_is_active_slave(new_slave) ? "an active" : "a backup", new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ bond_queue_slave_event(new_slave); return 0; /* Undo stages on error */ err_sysfs_del: bond_sysfs_slave_del(new_slave); err_upper_unlink: bond_upper_dev_unlink(bond, new_slave); err_unregister: netdev_rx_handler_unregister(slave_dev); err_detach: vlan_vids_del_by_dev(slave_dev, bond_dev); if (rcu_access_pointer(bond->primary_slave) == new_slave) RCU_INIT_POINTER(bond->primary_slave, NULL); if (rcu_access_pointer(bond->curr_active_slave) == new_slave) { block_netpoll_tx(); bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); unblock_netpoll_tx(); } /* either primary_slave or curr_active_slave might've changed */ synchronize_rcu(); slave_disable_netpoll(new_slave); err_close: if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's * MAC if this slave's MAC is in use by the bond, or at * least print a warning. */ bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr, new_slave->dev->addr_len); ss.ss_family = slave_dev->type; dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL); } err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu); err_free: kobject_put(&new_slave->kobj); err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ if (!bond_has_slaves(bond)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr)) eth_hw_addr_random(bond_dev); if (bond_dev->type != ARPHRD_ETHER) { dev_close(bond_dev); bond_ether_setup(bond_dev); } } return res; } /* Try to release the slave device <slave> from the bond device <master> * It is legal to access curr_active_slave without a lock because all the function * is RTNL-locked. If "all" is true it means that the function is being called * while destroying a bond interface and all slaves are being released. * * The rules for slave state should be: * for Active/Backup: * Active stays on all backups go down * for Bonded connections: * The first up interface should be left on and all others downed. */ static int __bond_release_one(struct net_device *bond_dev, struct net_device *slave_dev, bool all, bool unregister) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *oldcurrent; struct sockaddr_storage ss; int old_flags = bond_dev->flags; netdev_features_t old_features = bond_dev->features; /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || !netdev_has_upper_dev(slave_dev, bond_dev)) { slave_dbg(bond_dev, slave_dev, "cannot release slave\n"); return -EINVAL; } block_netpoll_tx(); slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ slave_info(bond_dev, slave_dev, "interface not enslaved\n"); unblock_netpoll_tx(); return -EINVAL; } bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); bond_sysfs_slave_del(slave); /* recompute stats just before removing the slave */ bond_get_stats(bond->dev, &bond->bond_stats); if (bond->xdp_prog) { struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = NULL, .extack = NULL, }; if (dev_xdp_propagate(slave_dev, &xdp)) slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); } /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ netdev_rx_handler_unregister(slave_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); bond_upper_dev_unlink(bond, slave); if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, slave); slave_info(bond_dev, slave_dev, "Releasing %s interface\n", bond_is_active_slave(slave) ? "active" : "backup"); oldcurrent = rcu_access_pointer(bond->curr_active_slave); RCU_INIT_POINTER(bond->current_arp_slave, NULL); if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) slave_warn(bond_dev, slave_dev, "the permanent HWaddr of slave - %pM - is still in use by bond - set the HWaddr of slave to a different address to avoid conflicts\n", slave->perm_hwaddr); } if (rtnl_dereference(bond->primary_slave) == slave) RCU_INIT_POINTER(bond->primary_slave, NULL); if (oldcurrent == slave) bond_change_active_slave(bond, NULL); /* Must be called after bond_change_active_slave () as the slave * might change from an active slave to a backup slave. Then it is * necessary to clear the maddrs on the backup slave. */ bond_slave_ns_maddrs_del(bond, slave); if (bond_is_lb(bond)) { /* Must be called only after the slave has been * detached from the list and the curr_active_slave * has been cleared (if our_slave == old_current), * but before a new active slave is selected. */ bond_alb_deinit_slave(bond, slave); } if (all) { RCU_INIT_POINTER(bond->curr_active_slave, NULL); } else if (oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. */ bond_select_active_slave(bond); } bond_set_carrier(bond); if (!bond_has_slaves(bond)) eth_hw_addr_random(bond_dev); unblock_netpoll_tx(); synchronize_rcu(); bond->slave_cnt--; if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } bond_compute_features(bond); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n"); vlan_vids_del_by_dev(slave_dev, bond_dev); /* If the mode uses primary, then this case was handled above by * bond_change_active_slave(..., NULL) */ if (!bond_uses_primary(bond)) { /* unset promiscuity level from slave * NOTE: The NETDEV_CHANGEADDR call above may change the value * of the IFF_PROMISC flag in the bond_dev, but we need the * value of that flag before that change, as that was the value * when this slave was attached, so we cache at the start of the * function and use it here. Same goes for ALLMULTI below */ if (old_flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); /* unset allmulti level from slave */ if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); if (old_flags & IFF_UP) bond_hw_addr_flush(bond_dev, slave_dev); } slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* restore original ("permanent") mac address */ bond_hw_addr_copy(ss.__data, slave->perm_hwaddr, slave->dev->addr_len); ss.ss_family = slave_dev->type; dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL); } if (unregister) { netdev_lock_ops(slave_dev); __dev_set_mtu(slave_dev, slave->original_mtu); netdev_unlock_ops(slave_dev); } else { dev_set_mtu(slave_dev, slave->original_mtu); } if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; bond_xdp_set_features(bond_dev); kobject_put(&slave->kobj); return 0; } /* A wrapper used because of ndo_del_link */ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) { return __bond_release_one(bond_dev, slave_dev, false, false); } /* First release a slave and then destroy the bond if no more slaves are left. * Must be under rtnl_lock when this function is called. */ static int bond_release_and_destroy(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); if (ret == 0 && !bond_has_slaves(bond) && bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); unregister_netdevice(bond_dev); } return ret; } static void bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = netdev_priv(bond_dev); bond_fill_ifbond(bond, info); } static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; int i = 0, res = -ENODEV; struct slave *slave; bond_for_each_slave(bond, slave, iter) { if (i++ == (int)info->slave_id) { res = 0; bond_fill_ifslave(slave, info); break; } } return res; } /*-------------------------------- Monitoring -------------------------------*/ /* called with rcu_read_lock() */ static int bond_miimon_inspect(struct bonding *bond) { bool ignore_updelay = false; int link_state, commit = 0; struct list_head *iter; struct slave *slave; if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { ignore_updelay = !rcu_dereference(bond->curr_active_slave); } else { struct bond_up_slave *usable_slaves; usable_slaves = rcu_dereference(bond->usable_slaves); if (usable_slaves && usable_slaves->count == 0) ignore_updelay = true; } bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); link_state = bond_check_dev_link(bond, slave->dev, 0); switch (slave->link) { case BOND_LINK_UP: if (link_state) continue; bond_propose_link_state(slave, BOND_LINK_FAIL); commit++; slave->delay = bond->params.downdelay; if (slave->delay && net_ratelimit()) { slave_info(bond->dev, slave->dev, "link status down for %sinterface, disabling it in %d ms\n", (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) ? (bond_is_active_slave(slave) ? "active " : "backup ") : "", bond->params.downdelay * bond->params.miimon); } fallthrough; case BOND_LINK_FAIL: if (link_state) { /* recovered before downdelay expired */ bond_propose_link_state(slave, BOND_LINK_UP); slave->last_link_up = jiffies; if (net_ratelimit()) slave_info(bond->dev, slave->dev, "link status up again after %d ms\n", (bond->params.downdelay - slave->delay) * bond->params.miimon); commit++; continue; } if (slave->delay <= 0) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; continue; } slave->delay--; break; case BOND_LINK_DOWN: if (!link_state) continue; bond_propose_link_state(slave, BOND_LINK_BACK); commit++; slave->delay = bond->params.updelay; if (slave->delay && net_ratelimit()) { slave_info(bond->dev, slave->dev, "link status up, enabling it in %d ms\n", ignore_updelay ? 0 : bond->params.updelay * bond->params.miimon); } fallthrough; case BOND_LINK_BACK: if (!link_state) { bond_propose_link_state(slave, BOND_LINK_DOWN); if (net_ratelimit()) slave_info(bond->dev, slave->dev, "link status down again after %d ms\n", (bond->params.updelay - slave->delay) * bond->params.miimon); commit++; continue; } if (ignore_updelay) slave->delay = 0; if (slave->delay <= 0) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; ignore_updelay = false; continue; } slave->delay--; break; } } return commit; } static void bond_miimon_link_change(struct bonding *bond, struct slave *slave, char link) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: bond_3ad_handle_link_change(slave, link); break; case BOND_MODE_TLB: case BOND_MODE_ALB: bond_alb_handle_link_change(bond, slave, link); break; case BOND_MODE_XOR: bond_update_slave_arr(bond, NULL); break; } } static void bond_miimon_commit(struct bonding *bond) { struct slave *slave, *primary, *active; bool do_failover = false; struct list_head *iter; ASSERT_RTNL(); bond_for_each_slave(bond, slave, iter) { switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: /* For 802.3ad mode, check current slave speed and * duplex again in case its port was disabled after * invalid speed/duplex reporting but recovered before * link monitoring could make a decision on the actual * link status */ if (BOND_MODE(bond) == BOND_MODE_8023AD && slave->link == BOND_LINK_UP) bond_3ad_adapter_speed_duplex_changed(slave); continue; case BOND_LINK_UP: if (bond_update_speed_duplex(slave) && bond_needs_speed_duplex(bond)) { slave->link = BOND_LINK_DOWN; if (net_ratelimit()) slave_warn(bond->dev, slave->dev, "failed to get link speed/duplex\n"); continue; } bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); slave->last_link_up = jiffies; primary = rtnl_dereference(bond->primary_slave); if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* prevent it from being the active one */ bond_set_backup_slave(slave); } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); } slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, slave->duplex ? "full" : "half"); bond_miimon_link_change(bond, slave, BOND_LINK_UP); active = rtnl_dereference(bond->curr_active_slave); if (!active || slave == primary || slave->prio > active->prio) do_failover = true; continue; case BOND_LINK_DOWN: if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_8023AD) bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n"); bond_miimon_link_change(bond, slave, BOND_LINK_DOWN); if (slave == rcu_access_pointer(bond->curr_active_slave)) do_failover = true; continue; default: slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", slave->link_new_state); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); continue; } } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } bond_set_carrier(bond); } /* bond_mii_monitor * * Really a wrapper that splits the mii monitor into two phases: an * inspection, then (if inspection indicates something needs to be done) * an acquisition of appropriate locks followed by a commit phase to * implement whatever link state changes are indicated. */ static void bond_mii_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mii_work.work); bool should_notify_peers = false; bool commit; unsigned long delay; struct slave *slave; struct list_head *iter; delay = msecs_to_jiffies(bond->params.miimon); if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); commit = !!bond_miimon_inspect(bond); if (bond->send_peer_notif) { rcu_read_unlock(); if (rtnl_trylock()) { bond->send_peer_notif--; rtnl_unlock(); } } else { rcu_read_unlock(); } if (commit) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; should_notify_peers = false; goto re_arm; } bond_for_each_slave(bond, slave, iter) { bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER); } bond_miimon_commit(bond); rtnl_unlock(); /* might sleep, hold no other locks */ } re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); if (should_notify_peers) { if (!rtnl_trylock()) return; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); rtnl_unlock(); } } static int bond_upper_dev_walk(struct net_device *upper, struct netdev_nested_priv *priv) { __be32 ip = *(__be32 *)priv->data; return ip == bond_confirm_addr(upper, 0, ip); } static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { struct netdev_nested_priv priv = { .data = (void *)&ip, }; bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) return true; rcu_read_lock(); if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv)) ret = true; rcu_read_unlock(); return ret; } #define BOND_VLAN_PROTO_NONE cpu_to_be16(0xffff) static bool bond_handle_vlan(struct slave *slave, struct bond_vlan_tag *tags, struct sk_buff *skb) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct bond_vlan_tag *outer_tag = tags; if (!tags || tags->vlan_proto == BOND_VLAN_PROTO_NONE) return true; tags++; /* Go through all the tags backwards and add them to the packet */ while (tags->vlan_proto != BOND_VLAN_PROTO_NONE) { if (!tags->vlan_id) { tags++; continue; } slave_dbg(bond_dev, slave_dev, "inner tag: proto %X vid %X\n", ntohs(outer_tag->vlan_proto), tags->vlan_id); skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto, tags->vlan_id); if (!skb) { net_err_ratelimited("failed to insert inner VLAN tag\n"); return false; } tags++; } /* Set the outer tag */ if (outer_tag->vlan_id) { slave_dbg(bond_dev, slave_dev, "outer tag: proto %X vid %X\n", ntohs(outer_tag->vlan_proto), outer_tag->vlan_id); __vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto, outer_tag->vlan_id); } return true; } /* We go to the (large) trouble of VLAN tagging ARP frames because * switches in VLAN mode (especially if ports are configured as * "native" to a VLAN) might not pass non-tagged frames. */ static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip, __be32 src_ip, struct bond_vlan_tag *tags) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct sk_buff *skb; slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n", arp_op, &dest_ip, &src_ip); skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); if (!skb) { net_err_ratelimited("ARP packet allocation failed\n"); return; } if (bond_handle_vlan(slave, tags, skb)) { slave_update_last_tx(slave); arp_xmit(skb); } return; } /* Validate the device path between the @start_dev and the @end_dev. * The path is valid if the @end_dev is reachable through device * stacking. * When the path is validated, collect any vlan information in the * path. */ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level) { struct bond_vlan_tag *tags; struct net_device *upper; struct list_head *iter; if (start_dev == end_dev) { tags = kcalloc(level + 1, sizeof(*tags), GFP_ATOMIC); if (!tags) return ERR_PTR(-ENOMEM); tags[level].vlan_proto = BOND_VLAN_PROTO_NONE; return tags; } netdev_for_each_upper_dev_rcu(start_dev, upper, iter) { tags = bond_verify_device_path(upper, end_dev, level + 1); if (IS_ERR_OR_NULL(tags)) { if (IS_ERR(tags)) return tags; continue; } if (is_vlan_dev(upper)) { tags[level].vlan_proto = vlan_dev_vlan_proto(upper); tags[level].vlan_id = vlan_dev_vlan_id(upper); } return tags; } return NULL; } static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { struct rtable *rt; struct bond_vlan_tag *tags; __be32 *targets = bond->params.arp_targets, addr; int i; for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { slave_dbg(bond->dev, slave->dev, "%s: target %pI4\n", __func__, &targets[i]); tags = NULL; /* Find out through which dev should the packet go */ rt = ip_route_output(dev_net(bond->dev), targets[i], 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) { /* there's no route to target - try to send arp * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) pr_warn_once("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", bond->dev->name, &targets[i]); bond_arp_send(slave, ARPOP_REQUEST, targets[i], 0, tags); continue; } /* bond device itself */ if (rt->dst.dev == bond->dev) goto found; rcu_read_lock(); tags = bond_verify_device_path(bond->dev, rt->dst.dev, 0); rcu_read_unlock(); if (!IS_ERR_OR_NULL(tags)) goto found; /* Not our device - skip */ slave_dbg(bond->dev, slave->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n", &targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL"); ip_rt_put(rt); continue; found: addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); ip_rt_put(rt); bond_arp_send(slave, ARPOP_REQUEST, targets[i], addr, tags); kfree(tags); } } static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { int i; if (!sip || !bond_has_this_ip(bond, tip)) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 tip %pI4 not found\n", __func__, &sip, &tip); return; } i = bond_get_targets_ip(bond->params.arp_targets, sip); if (i == -1) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 not found in targets\n", __func__, &sip); return; } slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; unsigned int alen; alen = arp_hdr_len(bond->dev); if (alen > skb_headlen(skb)) { arp = kmalloc(alen, GFP_ATOMIC); if (!arp) goto out_unlock; if (skb_copy_bits(skb, 0, arp, alen) < 0) goto out_unlock; } if (arp->ar_hln != bond->dev->addr_len || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK || arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_pln != 4) goto out_unlock; arp_ptr = (unsigned char *)(arp + 1); arp_ptr += bond->dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4 + bond->dev->addr_len; memcpy(&tip, arp_ptr, 4); slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI4 tip %pI4\n", __func__, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), &sip, &tip); curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); /* We 'trust' the received ARP enough to validate it if: * * (a) the slave receiving the ARP is active (which includes the * current ARP slave, if any), or * * (b) the receiving slave isn't active, but there is a currently * active slave and it received valid arp reply(s) after it became * the currently active slave, or * * (c) there is an ARP slave that sent an ARP during the prior ARP * interval, and we receive an ARP reply on any slave. We accept * these because switch FDB update delays may deliver the ARP * reply to a slave other than the sender of the ARP request. * * Note: for (b), backup slaves are receiving the broadcast ARP * request, not a reply. This request passes from the sending * slave through the L2 switch(es) to the receiving slave. Since * this is checking the request, sip/tip are swapped for * validation. * * This is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_arp(bond, slave, sip, tip); out_unlock: if (arp != (struct arphdr *)skb->data) kfree(arp); return RX_HANDLER_ANOTHER; } #if IS_ENABLED(CONFIG_IPV6) static void bond_ns_send(struct slave *slave, const struct in6_addr *daddr, const struct in6_addr *saddr, struct bond_vlan_tag *tags) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct in6_addr mcaddr; struct sk_buff *skb; slave_dbg(bond_dev, slave_dev, "NS on slave: dst %pI6c src %pI6c\n", daddr, saddr); skb = ndisc_ns_create(slave_dev, daddr, saddr, 0); if (!skb) { net_err_ratelimited("NS packet allocation failed\n"); return; } addrconf_addr_solict_mult(daddr, &mcaddr); if (bond_handle_vlan(slave, tags, skb)) { slave_update_last_tx(slave); ndisc_send_skb(skb, &mcaddr, saddr); } } static void bond_ns_send_all(struct bonding *bond, struct slave *slave) { struct in6_addr *targets = bond->params.ns_targets; struct bond_vlan_tag *tags; struct dst_entry *dst; struct in6_addr saddr; struct flowi6 fl6; int i; for (i = 0; i < BOND_MAX_NS_TARGETS && !ipv6_addr_any(&targets[i]); i++) { slave_dbg(bond->dev, slave->dev, "%s: target %pI6c\n", __func__, &targets[i]); tags = NULL; /* Find out through which dev should the packet go */ memset(&fl6, 0, sizeof(struct flowi6)); fl6.daddr = targets[i]; fl6.flowi6_oif = bond->dev->ifindex; dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6); if (dst->error) { dst_release(dst); /* there's no route to target - try to send arp * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) pr_warn_once("%s: no route to ns_ip6_target %pI6c and arp_validate is set\n", bond->dev->name, &targets[i]); bond_ns_send(slave, &targets[i], &in6addr_any, tags); continue; } /* bond device itself */ if (dst->dev == bond->dev) goto found; rcu_read_lock(); tags = bond_verify_device_path(bond->dev, dst->dev, 0); rcu_read_unlock(); if (!IS_ERR_OR_NULL(tags)) goto found; /* Not our device - skip */ slave_dbg(bond->dev, slave->dev, "no path to ns_ip6_target %pI6c via dst->dev %s\n", &targets[i], dst->dev ? dst->dev->name : "NULL"); dst_release(dst); continue; found: if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr)) bond_ns_send(slave, &targets[i], &saddr, tags); else bond_ns_send(slave, &targets[i], &in6addr_any, tags); dst_release(dst); kfree(tags); } } static int bond_confirm_addr6(struct net_device *dev, struct netdev_nested_priv *priv) { struct in6_addr *addr = (struct in6_addr *)priv->data; return ipv6_chk_addr(dev_net(dev), addr, dev, 0); } static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr) { struct netdev_nested_priv priv = { .data = addr, }; int ret = false; if (bond_confirm_addr6(bond->dev, &priv)) return true; rcu_read_lock(); if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_confirm_addr6, &priv)) ret = true; rcu_read_unlock(); return ret; } static void bond_validate_na(struct bonding *bond, struct slave *slave, struct in6_addr *saddr, struct in6_addr *daddr) { int i; /* Ignore NAs that: * 1. Source address is unspecified address. * 2. Dest address is neither all-nodes multicast address nor * exist on bond interface. */ if (ipv6_addr_any(saddr) || (!ipv6_addr_equal(daddr, &in6addr_linklocal_allnodes) && !bond_has_this_ip6(bond, daddr))) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n", __func__, saddr, daddr); return; } i = bond_get_targets_ip6(bond->params.ns_targets, saddr); if (i == -1) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c not found in targets\n", __func__, saddr); return; } slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct slave *curr_active_slave, *curr_arp_slave; struct in6_addr *saddr, *daddr; struct { struct ipv6hdr ip6; struct icmp6hdr icmp6; } *combined, _combined; if (skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK) goto out; combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || (combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) goto out; saddr = &combined->ip6.saddr; daddr = &combined->ip6.daddr; slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n", __func__, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), saddr, daddr); curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); /* We 'trust' the received ARP enough to validate it if: * see bond_arp_rcv(). */ if (bond_is_active_slave(slave)) bond_validate_na(bond, slave, saddr, daddr); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_na(bond, slave, daddr, saddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_na(bond, slave, saddr, daddr); out: return RX_HANDLER_ANOTHER; } #endif int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { #if IS_ENABLED(CONFIG_IPV6) bool is_ipv6 = skb->protocol == __cpu_to_be16(ETH_P_IPV6); #endif bool is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n", __func__, skb->dev->name); /* Use arp validate logic for both ARP and NS */ if (!slave_do_arp_validate(bond, slave)) { if ((slave_do_arp_validate_only(bond) && is_arp) || #if IS_ENABLED(CONFIG_IPV6) (slave_do_arp_validate_only(bond) && is_ipv6) || #endif !slave_do_arp_validate_only(bond)) slave->last_rx = jiffies; return RX_HANDLER_ANOTHER; } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); #if IS_ENABLED(CONFIG_IPV6) } else if (is_ipv6) { return bond_na_rcv(skb, bond, slave); #endif } else { return RX_HANDLER_ANOTHER; } } static void bond_send_validate(struct bonding *bond, struct slave *slave) { bond_arp_send_all(bond, slave); #if IS_ENABLED(CONFIG_IPV6) bond_ns_send_all(bond, slave); #endif } /* function to verify if we're in the arp_interval timeslice, returns true if * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval + * arp_interval/2) . the arp_interval/2 is needed for really fast networks. */ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod) { int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); return time_in_range(jiffies, last_act - delta_in_ticks, last_act + mod * delta_in_ticks + delta_in_ticks/2); } /* This function is called regularly to monitor each slave's link * ensuring that traffic is being sent and received when arp monitoring * is used in load-balancing mode. if the adapter has been dormant, then an * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ static void bond_loadbalance_arp_mon(struct bonding *bond) { struct slave *slave, *oldcurrent; struct list_head *iter; int do_failover = 0, slave_state_changed = 0; if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); oldcurrent = rcu_dereference(bond->curr_active_slave); /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into * the picture unless it is null. also, slave->last_link_up is not * needed here because we send an arp on each slave and give a slave * as long as it needs to get the tx/rx within the delta. * TODO: what about up/down delay in arp mode? it wasn't here before * so it can wait */ bond_for_each_slave_rcu(bond, slave, iter) { unsigned long last_tx = slave_last_tx(slave); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_tx, 1) && bond_time_in_interval(bond, slave->last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; /* primary_slave has no meaning in round-robin * mode. the window of a slave being up and * curr_active_slave being null after enslaving * is closed. */ if (!oldcurrent) { slave_info(bond->dev, slave->dev, "link status definitely up\n"); do_failover = 1; } else { slave_info(bond->dev, slave->dev, "interface is now up\n"); } } } else { /* slave->link == BOND_LINK_UP */ /* not all switches will respond to an arp request * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) { bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; slave_info(bond->dev, slave->dev, "interface is now down\n"); if (slave == oldcurrent) do_failover = 1; } } /* note: if switch is in round-robin mode, all links * must tx arp to ensure all links rx an arp - otherwise * links may oscillate or not come up at all; if switch is * in something like xor mode, there is nothing we can * do - all replies will be rx'ed on same link causing slaves * to be unstable during low/no traffic periods */ if (bond_slave_is_up(slave)) bond_send_validate(bond, slave); } rcu_read_unlock(); if (do_failover || slave_state_changed) { if (!rtnl_trylock()) goto re_arm; bond_for_each_slave(bond, slave, iter) { if (slave->link_new_state != BOND_LINK_NOCHANGE) slave->link = slave->link_new_state; } if (slave_state_changed) { bond_slave_state_change(bond); if (BOND_MODE(bond) == BOND_MODE_XOR) bond_update_slave_arr(bond, NULL); } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } rtnl_unlock(); } re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, msecs_to_jiffies(bond->params.arp_interval)); } /* Called to inspect slaves for active-backup mode ARP monitor link state * changes. Sets proposed link state in slaves to specify what action * should take place for the slave. Returns 0 if no changes are found, >0 * if changes to link states must be committed. * * Called with rcu_read_lock held. */ static int bond_ab_arp_inspect(struct bonding *bond) { unsigned long last_tx, last_rx; struct list_head *iter; struct slave *slave; int commit = 0; bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; } else if (slave->link == BOND_LINK_BACK) { bond_propose_link_state(slave, BOND_LINK_FAIL); commit++; } continue; } /* Give slaves 2*delta after being enslaved or made * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ if (bond_time_in_interval(bond, slave->last_link_up, 2)) continue; /* Backup slave is down if: * - No current_arp_slave AND * - more than (missed_max+1)*delta since last receive AND * - the bond has an IP address * * Note: a non-null current_arp_slave indicates * the curr_active_slave went down and we are * searching for a new one; under this condition * we only take the curr_active_slave down - this * gives each slave a chance to tx/rx traffic * before being taken out */ if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && !bond_time_in_interval(bond, last_rx, bond->params.missed_max + 1)) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } /* Active slave is down if: * - more than missed_max*delta since transmitting OR * - (more than missed_max*delta since receive AND * the bond has an IP address) */ last_tx = slave_last_tx(slave); if (bond_is_active_slave(slave) && (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, last_rx, bond->params.missed_max))) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } } return commit; } /* Called to commit link state changes noted by inspection step of * active-backup mode ARP monitor. * * Called with RTNL hold. */ static void bond_ab_arp_commit(struct bonding *bond) { bool do_failover = false; struct list_head *iter; unsigned long last_tx; struct slave *slave; bond_for_each_slave(bond, slave, iter) { switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: continue; case BOND_LINK_UP: last_tx = slave_last_tx(slave); if (rtnl_dereference(bond->curr_active_slave) != slave || (!rtnl_dereference(bond->curr_active_slave) && bond_time_in_interval(bond, last_tx, 1))) { struct slave *current_arp_slave; current_arp_slave = rtnl_dereference(bond->current_arp_slave); bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); if (current_arp_slave) { bond_set_slave_inactive_flags( current_arp_slave, BOND_SLAVE_NOTIFY_NOW); RCU_INIT_POINTER(bond->current_arp_slave, NULL); } slave_info(bond->dev, slave->dev, "link status definitely up\n"); if (!rtnl_dereference(bond->curr_active_slave) || slave == rtnl_dereference(bond->primary_slave) || slave->prio > rtnl_dereference(bond->curr_active_slave)->prio) do_failover = true; } continue; case BOND_LINK_DOWN: if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n"); if (slave == rtnl_dereference(bond->curr_active_slave)) { RCU_INIT_POINTER(bond->current_arp_slave, NULL); do_failover = true; } continue; case BOND_LINK_FAIL: bond_set_slave_link_state(slave, BOND_LINK_FAIL, BOND_SLAVE_NOTIFY_NOW); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); /* A slave has just been enslaved and has become * the current active slave. */ if (rtnl_dereference(bond->curr_active_slave)) RCU_INIT_POINTER(bond->current_arp_slave, NULL); continue; default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", slave->link_new_state); continue; } } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } bond_set_carrier(bond); } /* Send ARP probes for active-backup mode ARP monitor. * * Called with rcu_read_lock held. */ static bool bond_ab_arp_probe(struct bonding *bond) { struct slave *slave, *before = NULL, *new_slave = NULL, *curr_arp_slave = rcu_dereference(bond->current_arp_slave), *curr_active_slave = rcu_dereference(bond->curr_active_slave); struct list_head *iter; bool found = false; bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; if (curr_arp_slave && curr_active_slave) netdev_info(bond->dev, "PROBE: c_arp %s && cas %s BAD\n", curr_arp_slave->dev->name, curr_active_slave->dev->name); if (curr_active_slave) { bond_send_validate(bond, curr_active_slave); return should_notify_rtnl; } /* if we don't have a curr_active_slave, search for the next available * backup slave from the current_arp_slave and make it the candidate * for becoming the curr_active_slave */ if (!curr_arp_slave) { curr_arp_slave = bond_first_slave_rcu(bond); if (!curr_arp_slave) return should_notify_rtnl; } bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; if (found && !new_slave && bond_slave_is_up(slave)) new_slave = slave; /* if the link state is up at this point, we * mark it down - this can happen if we have * simultaneous link failures and * reselect_active_interface doesn't make this * one the current slave so it is still marked * up when it is actually down */ if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_LATER); if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_LATER); slave_info(bond->dev, slave->dev, "backup interface is now down\n"); } if (slave == curr_arp_slave) found = true; } if (!new_slave && before) new_slave = before; if (!new_slave) goto check_state; bond_set_slave_link_state(new_slave, BOND_LINK_BACK, BOND_SLAVE_NOTIFY_LATER); bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); bond_send_validate(bond, new_slave); new_slave->last_link_up = jiffies; rcu_assign_pointer(bond->current_arp_slave, new_slave); check_state: bond_for_each_slave_rcu(bond, slave, iter) { if (slave->should_notify || slave->should_notify_link) { should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; break; } } return should_notify_rtnl; } static void bond_activebackup_arp_mon(struct bonding *bond) { bool should_notify_peers = false; bool should_notify_rtnl = false; int delta_in_ticks; delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); if (bond_ab_arp_inspect(bond)) { rcu_read_unlock(); /* Race avoidance with bond_close flush of workqueue */ if (!rtnl_trylock()) { delta_in_ticks = 1; should_notify_peers = false; goto re_arm; } bond_ab_arp_commit(bond); rtnl_unlock(); rcu_read_lock(); } should_notify_rtnl = bond_ab_arp_probe(bond); rcu_read_unlock(); re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); if (should_notify_peers || should_notify_rtnl) { if (!rtnl_trylock()) return; if (should_notify_peers) { bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } if (should_notify_rtnl) { bond_slave_state_notify(bond); bond_slave_link_notify(bond); } rtnl_unlock(); } } static void bond_arp_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_activebackup_arp_mon(bond); else bond_loadbalance_arp_mon(bond); } /*-------------------------- netdev event handling --------------------------*/ /* Change device name */ static int bond_event_changename(struct bonding *bond) { bond_remove_proc_entry(bond); bond_create_proc_entry(bond); bond_debug_reregister(bond); return NOTIFY_DONE; } static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev) { struct bonding *event_bond = netdev_priv(bond_dev); netdev_dbg(bond_dev, "%s called\n", __func__); switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); case NETDEV_UNREGISTER: bond_remove_proc_entry(event_bond); #ifdef CONFIG_XFRM_OFFLOAD xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true); #endif /* CONFIG_XFRM_OFFLOAD */ break; case NETDEV_REGISTER: bond_create_proc_entry(event_bond); break; default: break; } return NOTIFY_DONE; } static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev), *primary; struct bonding *bond; struct net_device *bond_dev; /* A netdev event can be generated while enslaving a device * before netdev_rx_handler_register is called in which case * slave will be NULL */ if (!slave) { netdev_dbg(slave_dev, "%s called on NULL slave\n", __func__); return NOTIFY_DONE; } bond_dev = slave->bond->dev; bond = slave->bond; primary = rtnl_dereference(bond->primary_slave); slave_dbg(bond_dev, slave_dev, "%s called\n", __func__); switch (event) { case NETDEV_UNREGISTER: if (bond_dev->type != ARPHRD_ETHER) bond_release_and_destroy(bond_dev, slave_dev); else __bond_release_one(bond_dev, slave_dev, false, true); break; case NETDEV_UP: case NETDEV_CHANGE: /* For 802.3ad mode only: * Getting invalid Speed/Duplex values here will put slave * in weird state. Mark it as link-fail if the link was * previously up or link-down if it hasn't yet come up, and * let link-monitoring (miimon) set it right when correct * speeds/duplex are available. */ if (bond_update_speed_duplex(slave) && BOND_MODE(bond) == BOND_MODE_8023AD) { if (slave->last_link_up) slave->link = BOND_LINK_FAIL; else slave->link = BOND_LINK_DOWN; } if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); fallthrough; case NETDEV_DOWN: /* Refresh slave-array if applicable! * If the setup does not use miimon or arpmon (mode-specific!), * then these events will not cause the slave-array to be * refreshed. This will cause xmit to use a slave that is not * usable. Avoid such situation by refeshing the array at these * events. If these (miimon/arpmon) parameters are configured * then array gets refreshed twice and that should be fine! */ if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); break; case NETDEV_CHANGEMTU: /* TODO: Should slaves be allowed to * independently alter their MTU? For * an active-backup bond, slaves need * not be the same type of device, so * MTUs may vary. For other modes, * slaves arguably should have the * same MTUs. To do this, we'd need to * take over the slave's change_mtu * function for the duration of their * servitude. */ break; case NETDEV_CHANGENAME: /* we don't care if we don't have primary set */ if (!bond_uses_primary(bond) || !bond->params.primary[0]) break; if (slave == primary) { /* slave's name changed - he's no longer primary */ RCU_INIT_POINTER(bond->primary_slave, NULL); } else if (!strcmp(slave_dev->name, bond->params.primary)) { /* we have a new primary slave */ rcu_assign_pointer(bond->primary_slave, slave); } else { /* we didn't change primary - exit */ break; } netdev_info(bond->dev, "Primary slave changed to %s, reselecting active slave\n", primary ? slave_dev->name : "none"); block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: if (!bond->notifier_ctx) { bond->notifier_ctx = true; bond_compute_features(bond); bond->notifier_ctx = false; } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, slave->bond->dev); break; case NETDEV_XDP_FEAT_CHANGE: bond_xdp_set_features(bond_dev); break; default: break; } return NOTIFY_DONE; } /* bond_netdev_event: handle netdev notifier chain events. * * This function receives events for the netdev chain. The caller (an * ioctl handler calling blocking_notifier_call_chain) holds the necessary * locks for us to safely manipulate the slave devices (RTNL lock, * dev_probe_lock). */ static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); netdev_dbg(event_dev, "%s received %s\n", __func__, netdev_cmd_to_name(event)); if (!(event_dev->priv_flags & IFF_BONDING)) return NOTIFY_DONE; if (event_dev->flags & IFF_MASTER) { int ret; ret = bond_master_netdev_event(event, event_dev); if (ret != NOTIFY_DONE) return ret; } if (event_dev->flags & IFF_SLAVE) return bond_slave_netdev_event(event, event_dev); return NOTIFY_DONE; } static struct notifier_block bond_netdev_notifier = { .notifier_call = bond_netdev_event, }; /*---------------------------- Hashing Policies -----------------------------*/ /* Helper to access data in a packet, with or without a backing skb. * If skb is given the data is linearized if necessary via pskb_may_pull. */ static inline const void *bond_pull_data(struct sk_buff *skb, const void *data, int hlen, int n) { if (likely(n <= hlen)) return data; else if (skb && likely(pskb_may_pull(skb, n))) return skb->data; return NULL; } /* L2 hash helper */ static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { struct ethhdr *ep; data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); if (!data) return 0; ep = (struct ethhdr *)(data + mhoff); return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto); } static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data, int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34) { const struct ipv6hdr *iph6; const struct iphdr *iph; if (l2_proto == htons(ETH_P_IP)) { data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph)); if (!data) return false; iph = (const struct iphdr *)(data + *nhoff); iph_to_flow_copy_v4addrs(fk, iph); *nhoff += iph->ihl << 2; if (!ip_is_fragment(iph)) *ip_proto = iph->protocol; } else if (l2_proto == htons(ETH_P_IPV6)) { data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6)); if (!data) return false; iph6 = (const struct ipv6hdr *)(data + *nhoff); iph_to_flow_copy_v6addrs(fk, iph6); *nhoff += sizeof(*iph6); *ip_proto = iph6->nexthdr; } else { return false; } if (l34 && *ip_proto >= 0) fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen); return true; } static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { u32 srcmac_vendor = 0, srcmac_dev = 0; struct ethhdr *mac_hdr; u16 vlan = 0; int i; data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); if (!data) return 0; mac_hdr = (struct ethhdr *)(data + mhoff); for (i = 0; i < 3; i++) srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i]; for (i = 3; i < ETH_ALEN; i++) srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i]; if (skb && skb_vlan_tag_present(skb)) vlan = skb_vlan_tag_get(skb); return vlan ^ srcmac_vendor ^ srcmac_dev; } /* Extract the appropriate headers based on bond's xmit policy */ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data, __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk) { bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; int ip_proto = -1; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, fk, data, l2_proto, nhoff, hlen, 0); default: break; } fk->ports.ports = 0; memset(&fk->icmp, 0, sizeof(fk->icmp)); if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34)) return false; /* ICMP error packets contains at least 8 bytes of the header * of the packet which generated the error. Use this information * to correlate ICMP error packets within the same flow which * generated the error. */ if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) { skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen); if (ip_proto == IPPROTO_ICMP) { if (!icmp_is_err(fk->icmp.type)) return true; nhoff += sizeof(struct icmphdr); } else if (ip_proto == IPPROTO_ICMPV6) { if (!icmpv6_is_err(fk->icmp.type)) return true; nhoff += sizeof(struct icmp6hdr); } return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34); } return true; } static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); /* discard lowest hash bit to deal with the common even ports pattern */ if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || xmit_policy == BOND_XMIT_POLICY_ENCAP34) return hash >> 1; return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize * the data as required, but this function can be used without it if the data is * known to be linear (e.g. with xdp_buff). */ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const void *data, __be16 l2_proto, int mhoff, int nhoff, int hlen) { struct flow_keys flow; u32 hash; if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC) return bond_vlan_srcmac_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow)) return bond_eth_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) { hash = bond_eth_hash(skb, data, mhoff, hlen); } else { if (flow.icmp.id) memcpy(&hash, &flow.icmp, sizeof(hash)); else memcpy(&hash, &flow.ports.ports, sizeof(hash)); } return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** * bond_xmit_hash - generate a hash value based on the xmit policy * @bond: bonding device * @skb: buffer to use for headers * * This function will extract the necessary headers from the skb buffer and use * them to generate a hash based on the xmit_policy set in the bonding device */ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) { if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && skb->l4_hash) return skb->hash; return __bond_xmit_hash(bond, skb, skb->data, skb->protocol, 0, skb_network_offset(skb), skb_headlen(skb)); } /** * bond_xmit_hash_xdp - generate a hash value based on the xmit policy * @bond: bonding device * @xdp: buffer to use for headers * * The XDP variant of bond_xmit_hash. */ static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp) { struct ethhdr *eth; if (xdp->data + sizeof(struct ethhdr) > xdp->data_end) return 0; eth = (struct ethhdr *)xdp->data; return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0, sizeof(struct ethhdr), xdp->data_end - xdp->data); } /*-------------------------- Device entry points ----------------------------*/ void bond_work_init_all(struct bonding *bond) { INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor); INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } static void bond_work_cancel_all(struct bonding *bond) { cancel_delayed_work_sync(&bond->mii_work); cancel_delayed_work_sync(&bond->arp_work); cancel_delayed_work_sync(&bond->alb_work); cancel_delayed_work_sync(&bond->ad_work); cancel_delayed_work_sync(&bond->mcast_work); cancel_delayed_work_sync(&bond->slave_arr_work); } static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) { bond->rr_tx_counter = alloc_percpu(u32); if (!bond->rr_tx_counter) return -ENOMEM; } /* reset slave->backup and slave->inactive */ if (bond_has_slaves(bond)) { bond_for_each_slave(bond, slave, iter) { if (bond_uses_primary(bond) && slave != rcu_access_pointer(bond->curr_active_slave)) { bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); } else if (BOND_MODE(bond) != BOND_MODE_8023AD) { bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_NOW); } } } if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. */ if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB))) return -ENOMEM; if (bond->params.tlb_dynamic_lb || BOND_MODE(bond) == BOND_MODE_ALB) queue_delayed_work(bond->wq, &bond->alb_work, 0); } if (bond->params.miimon) /* link check interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->mii_work, 0); if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); bond->recv_probe = bond_rcv_validate; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond->recv_probe = bond_3ad_lacpdu_recv; bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) dev_mc_add(slave->dev, lacpdu_mcast_addr); } if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); return 0; } static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; bond_work_cancel_all(bond); bond->send_peer_notif = 0; if (bond_is_lb(bond)) bond_alb_deinitialize(bond); bond->recv_probe = NULL; if (bond_uses_primary(bond)) { rcu_read_lock(); slave = rcu_dereference(bond->curr_active_slave); if (slave) bond_hw_addr_flush(bond_dev, slave->dev); rcu_read_unlock(); } else { struct list_head *iter; bond_for_each_slave(bond, slave, iter) bond_hw_addr_flush(bond_dev, slave->dev); } return 0; } /* fold stats, assuming all rtnl_link_stats64 fields are u64, but * that some drivers can provide 32bit values only. */ static void bond_fold_stats(struct rtnl_link_stats64 *_res, const struct rtnl_link_stats64 *_new, const struct rtnl_link_stats64 *_old) { const u64 *new = (const u64 *)_new; const u64 *old = (const u64 *)_old; u64 *res = (u64 *)_res; int i; for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) { u64 nv = new[i]; u64 ov = old[i]; s64 delta = nv - ov; /* detects if this particular field is 32bit only */ if (((nv | ov) >> 32) == 0) delta = (s64)(s32)((u32)nv - (u32)ov); /* filter anomalies, some drivers reset their stats * at down/up events. */ if (delta > 0) res[i] += delta; } } #ifdef CONFIG_LOCKDEP static int bond_get_lowest_level_rcu(struct net_device *dev) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int cur = 0, max = 0; now = dev; iter = &dev->adj_list.lower; while (1) { next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; if (max <= cur) max = cur; break; } if (!next) { if (!cur) return max; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return max; } #endif static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { struct bonding *bond = netdev_priv(bond_dev); struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; int nest_level = 0; rcu_read_lock(); #ifdef CONFIG_LOCKDEP nest_level = bond_get_lowest_level_rcu(bond_dev); #endif spin_lock_nested(&bond->stats_lock, nest_level); memcpy(stats, &bond->bond_stats, sizeof(*stats)); bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); bond_fold_stats(stats, new, &slave->slave_stats); /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); rcu_read_unlock(); } static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); struct mii_ioctl_data *mii = NULL; netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCGMIIPHY: mii = if_mii(ifr); if (!mii) return -EINVAL; mii->phy_id = 0; fallthrough; case SIOCGMIIREG: /* We do this again just in case we were called by SIOCGMIIREG * instead of SIOCGMIIPHY. */ mii = if_mii(ifr); if (!mii) return -EINVAL; if (mii->reg_num == 1) { mii->val_out = 0; if (netif_carrier_ok(bond->dev)) mii->val_out = BMSR_LSTATUS; } break; default: return -EOPNOTSUPP; } return 0; } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); struct net_device *slave_dev = NULL; struct ifbond k_binfo; struct ifbond __user *u_binfo = NULL; struct ifslave k_sinfo; struct ifslave __user *u_sinfo = NULL; struct bond_opt_value newval; struct net *net; int res = 0; netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) return -EFAULT; bond_info_query(bond_dev, &k_binfo); if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) return -EFAULT; return 0; case SIOCBONDSLAVEINFOQUERY: u_sinfo = (struct ifslave __user *)ifr->ifr_data; if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) return -EFAULT; res = bond_slave_info_query(bond_dev, &k_sinfo); if (res == 0 && copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) return -EFAULT; return res; default: break; } net = dev_net(bond_dev); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; slave_dev = __dev_get_by_name(net, ifr->ifr_slave); slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev); if (!slave_dev) return -ENODEV; switch (cmd) { case SIOCBONDENSLAVE: res = bond_enslave(bond_dev, slave_dev, NULL); break; case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); break; case SIOCBONDSETHWADDR: res = bond_set_dev_addr(bond_dev, slave_dev); break; case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, &newval); break; default: res = -EOPNOTSUPP; } return res; } static int bond_siocdevprivate(struct net_device *bond_dev, struct ifreq *ifr, void __user *data, int cmd) { struct ifreq ifrdata = { .ifr_data = data }; switch (cmd) { case BOND_INFO_QUERY_OLD: return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDINFOQUERY); case BOND_SLAVE_INFO_QUERY_OLD: return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDSLAVEINFOQUERY); case BOND_ENSLAVE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDENSLAVE); case BOND_RELEASE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDRELEASE); case BOND_SETHWADDR_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDSETHWADDR); case BOND_CHANGE_ACTIVE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDCHANGEACTIVE); } return -EOPNOTSUPP; } static void bond_change_rx_flags(struct net_device *bond_dev, int change) { struct bonding *bond = netdev_priv(bond_dev); if (change & IFF_PROMISC) bond_set_promiscuity(bond, bond_dev->flags & IFF_PROMISC ? 1 : -1); if (change & IFF_ALLMULTI) bond_set_allmulti(bond, bond_dev->flags & IFF_ALLMULTI ? 1 : -1); } static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; rcu_read_lock(); if (bond_uses_primary(bond)) { slave = rcu_dereference(bond->curr_active_slave); if (slave) { dev_uc_sync(slave->dev, bond_dev); dev_mc_sync(slave->dev, bond_dev); } } else { bond_for_each_slave_rcu(bond, slave, iter) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } } rcu_read_unlock(); } static int bond_neigh_init(struct neighbour *n) { struct bonding *bond = netdev_priv(n->dev); const struct net_device_ops *slave_ops; struct neigh_parms parms; struct slave *slave; int ret = 0; rcu_read_lock(); slave = bond_first_slave_rcu(bond); if (!slave) goto out; slave_ops = slave->dev->netdev_ops; if (!slave_ops->ndo_neigh_setup) goto out; /* TODO: find another way [1] to implement this. * Passing a zeroed structure is fragile, * but at least we do not pass garbage. * * [1] One way would be that ndo_neigh_setup() never touch * struct neigh_parms, but propagate the new neigh_setup() * back to ___neigh_create() / neigh_parms_alloc() */ memset(&parms, 0, sizeof(parms)); ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); if (ret) goto out; if (parms.neigh_setup) ret = parms.neigh_setup(n); out: rcu_read_unlock(); return ret; } /* The bonding ndo_neigh_setup is called at init time beofre any * slave exists. So we must declare proxy setup function which will * be used at run time to resolve the actual slave neigh param setup. * * It's also called by master devices (such as vlans) to setup their * underlying devices. In that case - do nothing, we're already set up from * our init. */ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) { /* modify only our neigh_parms */ if (parms->dev == dev) parms->neigh_setup = bond_neigh_init; return 0; } /* Change the MTU of all of a master's slaves to match the master */ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct list_head *iter; int res = 0; netdev_dbg(bond_dev, "bond=%p, new_mtu=%d\n", bond, new_mtu); bond_for_each_slave(bond, slave, iter) { slave_dbg(bond_dev, slave->dev, "s %p c_m %p\n", slave, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); if (res) { /* If we failed to set the slave's mtu to the new value * we must abort the operation even in ACTIVE_BACKUP * mode, because if we allow the backup slaves to have * different mtu values than the active slave we'll * need to change their mtu when doing a failover. That * means changing their mtu from timer context, which * is probably not a good idea. */ slave_dbg(bond_dev, slave->dev, "err %d setting mtu to %d\n", res, new_mtu); goto unwind; } } WRITE_ONCE(bond_dev->mtu, new_mtu); return 0; unwind: /* unwind from head to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; if (rollback_slave == slave) break; tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); if (tmp_res) slave_dbg(bond_dev, rollback_slave->dev, "unwind err %d\n", tmp_res); } return res; } /* Change HW address * * Note that many devices must be down to change the HW address, and * downing the master releases all slaves. We can make bonds full of * bonding devices to test this, however. */ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct sockaddr_storage *ss = addr, tmp_ss; struct list_head *iter; int res = 0; if (BOND_MODE(bond) == BOND_MODE_ALB) return bond_alb_set_mac_address(bond_dev, addr); netdev_dbg(bond_dev, "%s: bond=%p\n", __func__, bond); /* If fail_over_mac is enabled, do nothing and return success. * Returning an error causes ifenslave to fail. */ if (bond->params.fail_over_mac && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) return 0; if (!is_valid_ether_addr(ss->__data)) return -EADDRNOTAVAIL; bond_for_each_slave(bond, slave, iter) { slave_dbg(bond_dev, slave->dev, "%s: slave=%p\n", __func__, slave); res = dev_set_mac_address(slave->dev, addr, NULL); if (res) { /* TODO: consider downing the slave * and retry ? * User should expect communications * breakage anyway until ARP finish * updating, so... */ slave_dbg(bond_dev, slave->dev, "%s: err %d\n", __func__, res); goto unwind; } } /* success */ dev_addr_set(bond_dev, ss->__data); return 0; unwind: memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len); tmp_ss.ss_family = bond_dev->type; /* unwind from head to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; if (rollback_slave == slave) break; tmp_res = dev_set_mac_address(rollback_slave->dev, (struct sockaddr *)&tmp_ss, NULL); if (tmp_res) { slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n", __func__, tmp_res); } } return res; } /** * bond_get_slave_by_id - get xmit slave with slave_id * @bond: bonding device that is transmitting * @slave_id: slave id up to slave_cnt-1 through which to transmit * * This function tries to get slave with slave_id but in case * it fails, it tries to find the first available slave for transmission. */ static struct slave *bond_get_slave_by_id(struct bonding *bond, int slave_id) { struct list_head *iter; struct slave *slave; int i = slave_id; /* Here we start from the slave with slave_id */ bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) { if (bond_slave_can_tx(slave)) return slave; } } /* Here we start from the first slave up to slave_id */ i = slave_id; bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) break; if (bond_slave_can_tx(slave)) return slave; } /* no slave that can tx has been found */ return NULL; } /** * bond_rr_gen_slave_id - generate slave id based on packets_per_slave * @bond: bonding device to use * * Based on the value of the bonding device's packets_per_slave parameter * this function generates a slave id, which is usually used as the next * slave to transmit through. */ static u32 bond_rr_gen_slave_id(struct bonding *bond) { u32 slave_id; struct reciprocal_value reciprocal_packets_per_slave; int packets_per_slave = bond->params.packets_per_slave; switch (packets_per_slave) { case 0: slave_id = get_random_u32(); break; case 1: slave_id = this_cpu_inc_return(*bond->rr_tx_counter); break; default: reciprocal_packets_per_slave = bond->params.reciprocal_packets_per_slave; slave_id = this_cpu_inc_return(*bond->rr_tx_counter); slave_id = reciprocal_divide(slave_id, reciprocal_packets_per_slave); break; } return slave_id; } static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond, struct sk_buff *skb) { struct slave *slave; int slave_cnt; u32 slave_id; /* Start with the curr_active_slave that joined the bond as the * default for sending IGMP traffic. For failover purposes one * needs to maintain some consistency for the interface that will * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ if (skb->protocol == htons(ETH_P_IP)) { int noff = skb_network_offset(skb); struct iphdr *iph; if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) goto non_igmp; iph = ip_hdr(skb); if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) return slave; return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; return bond_get_slave_by_id(bond, slave_id); } return NULL; } static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond, struct xdp_buff *xdp) { struct slave *slave; int slave_cnt; u32 slave_id; const struct ethhdr *eth; void *data = xdp->data; if (data + sizeof(struct ethhdr) > xdp->data_end) goto non_igmp; eth = (struct ethhdr *)data; data += sizeof(struct ethhdr); /* See comment on IGMP in bond_xmit_roundrobin_slave_get() */ if (eth->h_proto == htons(ETH_P_IP)) { const struct iphdr *iph; if (data + sizeof(struct iphdr) > xdp->data_end) goto non_igmp; iph = (struct iphdr *)data; if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) return slave; return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; return bond_get_slave_by_id(bond, slave_id); } return NULL; } static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; slave = bond_xmit_roundrobin_slave_get(bond, skb); if (likely(slave)) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(bond_dev, skb); } static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond) { return rcu_dereference(bond->curr_active_slave); } /* In active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. */ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; slave = bond_xmit_activebackup_slave_get(bond); if (slave) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(bond_dev, skb); } /* Use this to update slave_array when (a) it's not appropriate to update * slave_array right away (note that update_slave_array() may sleep) * and / or (b) RTNL is not held. */ void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay) { queue_delayed_work(bond->wq, &bond->slave_arr_work, delay); } /* Slave array work handler. Holds only RTNL */ static void bond_slave_arr_handler(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, slave_arr_work.work); int ret; if (!rtnl_trylock()) goto err; ret = bond_update_slave_arr(bond, NULL); rtnl_unlock(); if (ret) { pr_warn_ratelimited("Failed to update slave array from WT\n"); goto err; } return; err: bond_slave_arr_work_rearm(bond, 1); } static void bond_skip_slave(struct bond_up_slave *slaves, struct slave *skipslave) { int idx; /* Rare situation where caller has asked to skip a specific * slave but allocation failed (most likely!). BTW this is * only possible when the call is initiated from * __bond_release_one(). In this situation; overwrite the * skipslave entry in the array with the last entry from the * array to avoid a situation where the xmit path may choose * this to-be-skipped slave to send a packet out. */ for (idx = 0; slaves && idx < slaves->count; idx++) { if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; slaves->count--; break; } } } static void bond_set_slave_arr(struct bonding *bond, struct bond_up_slave *usable_slaves, struct bond_up_slave *all_slaves) { struct bond_up_slave *usable, *all; usable = rtnl_dereference(bond->usable_slaves); rcu_assign_pointer(bond->usable_slaves, usable_slaves); kfree_rcu(usable, rcu); all = rtnl_dereference(bond->all_slaves); rcu_assign_pointer(bond->all_slaves, all_slaves); kfree_rcu(all, rcu); } static void bond_reset_slave_arr(struct bonding *bond) { bond_set_slave_arr(bond, NULL, NULL); } /* Build the usable slaves array in control path for modes that use xmit-hash * to determine the slave interface - * (a) BOND_MODE_8023AD * (b) BOND_MODE_XOR * (c) (BOND_MODE_TLB || BOND_MODE_ALB) && tlb_dynamic_lb == 0 * * The caller is expected to hold RTNL only and NO other lock! */ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) { struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL; struct slave *slave; struct list_head *iter; int agg_id = 0; int ret = 0; might_sleep(); usable_slaves = kzalloc(struct_size(usable_slaves, arr, bond->slave_cnt), GFP_KERNEL); all_slaves = kzalloc(struct_size(all_slaves, arr, bond->slave_cnt), GFP_KERNEL); if (!usable_slaves || !all_slaves) { ret = -ENOMEM; goto out; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; spin_lock_bh(&bond->mode_lock); if (bond_3ad_get_active_agg_info(bond, &ad_info)) { spin_unlock_bh(&bond->mode_lock); pr_debug("bond_3ad_get_active_agg_info failed\n"); /* No active aggragator means it's not safe to use * the previous array. */ bond_reset_slave_arr(bond); goto out; } spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg; agg = SLAVE_AD_INFO(slave)->port.aggregator; if (!agg || agg->aggregator_identifier != agg_id) continue; } if (!bond_slave_can_tx(slave)) continue; slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n", usable_slaves->count); usable_slaves->arr[usable_slaves->count++] = slave; } bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; out: if (ret != 0 && skipslave) { bond_skip_slave(rtnl_dereference(bond->all_slaves), skipslave); bond_skip_slave(rtnl_dereference(bond->usable_slaves), skipslave); } kfree_rcu(all_slaves, rcu); kfree_rcu(usable_slaves, rcu); return ret; } static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond, struct sk_buff *skb, struct bond_up_slave *slaves) { struct slave *slave; unsigned int count; u32 hash; hash = bond_xmit_hash(bond, skb); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; slave = slaves->arr[hash % count]; return slave; } static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond, struct xdp_buff *xdp) { struct bond_up_slave *slaves; unsigned int count; u32 hash; hash = bond_xmit_hash_xdp(bond, xdp); slaves = rcu_dereference(bond->usable_slaves); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; return slaves->arr[hash % count]; } /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. */ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct bond_up_slave *slaves; struct slave *slave; slaves = rcu_dereference(bond->usable_slaves); slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); if (likely(slave)) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(dev, skb); } /* in broadcast mode, we send everything to all usable interfaces. */ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; struct list_head *iter; bool xmit_suc = false; bool skb_used = false; bond_for_each_slave_rcu(bond, slave, iter) { struct sk_buff *skb2; if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)) continue; if (bond_is_last_slave(bond, slave)) { skb2 = skb; skb_used = true; } else { skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { net_err_ratelimited("%s: Error: %s: skb_clone() failed\n", bond_dev->name, __func__); continue; } } if (bond_dev_queue_xmit(bond, skb2, slave->dev) == NETDEV_TX_OK) xmit_suc = true; } if (!skb_used) dev_kfree_skb_any(skb); if (xmit_suc) return NETDEV_TX_OK; dev_core_stats_tx_dropped_inc(bond_dev); return NET_XMIT_DROP; } /*------------------------- Device initialization ---------------------------*/ /* Lookup the slave that corresponds to a qid */ static inline int bond_slave_override(struct bonding *bond, struct sk_buff *skb) { struct slave *slave = NULL; struct list_head *iter; if (!skb_rx_queue_recorded(skb)) return 1; /* Find out if any slaves have the same mapping as this skb. */ bond_for_each_slave_rcu(bond, slave, iter) { if (READ_ONCE(slave->queue_id) == skb_get_queue_mapping(skb)) { if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_dev_queue_xmit(bond, skb, slave->dev); return 0; } /* If the slave isn't UP, use default transmit policy. */ break; } } return 1; } static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to * skb_tx_hash and will put the skbs in the queue we expect on their * way down to the bonding driver. */ u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb_get_queue_mapping(skb); if (unlikely(txq >= dev->real_num_tx_queues)) { do { txq -= dev->real_num_tx_queues; } while (txq >= dev->real_num_tx_queues); } return txq; } static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, struct sk_buff *skb, bool all_slaves) { struct bonding *bond = netdev_priv(master_dev); struct bond_up_slave *slaves; struct slave *slave = NULL; switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: slave = bond_xmit_roundrobin_slave_get(bond, skb); break; case BOND_MODE_ACTIVEBACKUP: slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: if (all_slaves) slaves = rcu_dereference(bond->all_slaves); else slaves = rcu_dereference(bond->usable_slaves); slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); break; case BOND_MODE_BROADCAST: break; case BOND_MODE_ALB: slave = bond_xmit_alb_slave_get(bond, skb); break; case BOND_MODE_TLB: slave = bond_xmit_tlb_slave_get(bond, skb); break; default: /* Should never happen, mode already checked */ WARN_ONCE(true, "Unknown bonding mode"); break; } if (slave) return slave->dev; return NULL; } static void bond_sk_to_flow(struct sock *sk, struct flow_keys *flow) { switch (sk->sk_family) { #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (ipv6_only_sock(sk) || ipv6_addr_type(&sk->sk_v6_daddr) != IPV6_ADDR_MAPPED) { flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; flow->addrs.v6addrs.src = inet6_sk(sk)->saddr; flow->addrs.v6addrs.dst = sk->sk_v6_daddr; break; } fallthrough; #endif default: /* AF_INET */ flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; flow->addrs.v4addrs.src = inet_sk(sk)->inet_rcv_saddr; flow->addrs.v4addrs.dst = inet_sk(sk)->inet_daddr; break; } flow->ports.src = inet_sk(sk)->inet_sport; flow->ports.dst = inet_sk(sk)->inet_dport; } /** * bond_sk_hash_l34 - generate a hash value based on the socket's L3 and L4 fields * @sk: socket to use for headers * * This function will extract the necessary field from the socket and use * them to generate a hash based on the LAYER34 xmit_policy. * Assumes that sk is a TCP or UDP socket. */ static u32 bond_sk_hash_l34(struct sock *sk) { struct flow_keys flow; u32 hash; bond_sk_to_flow(sk, &flow); /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, struct sock *sk) { struct bond_up_slave *slaves; struct slave *slave; unsigned int count; u32 hash; slaves = rcu_dereference(bond->usable_slaves); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; hash = bond_sk_hash_l34(sk); slave = slaves->arr[hash % count]; return slave->dev; } static struct net_device *bond_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { struct bonding *bond = netdev_priv(dev); struct net_device *lower = NULL; rcu_read_lock(); if (bond_sk_check(bond)) lower = __bond_sk_get_lower_dev(bond, sk); rcu_read_unlock(); return lower; } #if IS_ENABLED(CONFIG_TLS_DEVICE) static netdev_tx_t bond_tls_device_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *dev) { struct net_device *tls_netdev = rcu_dereference(tls_get_ctx(skb->sk)->netdev); /* tls_netdev might become NULL, even if tls_is_skb_tx_device_offloaded * was true, if tls_device_down is running in parallel, but it's OK, * because bond_get_slave_by_dev has a NULL check. */ if (likely(bond_get_slave_by_dev(bond, tls_netdev))) return bond_dev_queue_xmit(bond, skb, tls_netdev); return bond_tx_drop(dev, skb); } #endif static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); if (bond_should_override_tx_queue(bond) && !bond_slave_override(bond, skb)) return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_TLS_DEVICE) if (tls_is_skb_tx_device_offloaded(skb)) return bond_tls_device_xmit(bond, skb, dev); #endif switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return bond_xmit_roundrobin(skb, dev); case BOND_MODE_ACTIVEBACKUP: return bond_xmit_activebackup(skb, dev); case BOND_MODE_8023AD: case BOND_MODE_XOR: return bond_3ad_xor_xmit(skb, dev); case BOND_MODE_BROADCAST: return bond_xmit_broadcast(skb, dev); case BOND_MODE_ALB: return bond_alb_xmit(skb, dev); case BOND_MODE_TLB: return bond_tlb_xmit(skb, dev); default: /* Should never happen, mode already checked */ netdev_err(dev, "Unknown bonding mode %d\n", BOND_MODE(bond)); WARN_ON_ONCE(1); return bond_tx_drop(dev, skb); } } static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); netdev_tx_t ret = NETDEV_TX_OK; /* If we risk deadlock from transmitting this in the * netpoll path, tell netpoll to queue the frame for later tx */ if (unlikely(is_netpoll_tx_blocked(dev))) return NETDEV_TX_BUSY; rcu_read_lock(); if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else ret = bond_tx_drop(dev, skb); rcu_read_unlock(); return ret; } static struct net_device * bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; /* Caller needs to hold rcu_read_lock() */ switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp); break; case BOND_MODE_ACTIVEBACKUP: slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp); break; default: if (net_ratelimit()) netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond)); return NULL; } if (slave) return slave->dev; return NULL; } static int bond_xdp_xmit(struct net_device *bond_dev, int n, struct xdp_frame **frames, u32 flags) { int nxmit, err = -ENXIO; rcu_read_lock(); for (nxmit = 0; nxmit < n; nxmit++) { struct xdp_frame *frame = frames[nxmit]; struct xdp_frame *frames1[] = {frame}; struct net_device *slave_dev; struct xdp_buff xdp; xdp_convert_frame_to_buff(frame, &xdp); slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp); if (!slave_dev) { err = -ENXIO; break; } err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags); if (err < 1) break; } rcu_read_unlock(); /* If error happened on the first frame then we can pass the error up, otherwise * report the number of frames that were xmitted. */ if (err < 0) return (nxmit == 0 ? err : nxmit); return nxmit; } static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; struct slave *slave, *rollback_slave; struct bpf_prog *old_prog; struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = prog, .extack = extack, }; int err; ASSERT_RTNL(); if (!bond_xdp_check(bond, BOND_MODE(bond))) { BOND_NL_ERR(dev, extack, "No native XDP support for the current bonding mode"); return -EOPNOTSUPP; } old_prog = bond->xdp_prog; bond->xdp_prog = prog; bond_for_each_slave(bond, slave, iter) { struct net_device *slave_dev = slave->dev; if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { SLAVE_NL_ERR(dev, slave_dev, extack, "Slave device does not support XDP"); err = -EOPNOTSUPP; goto err; } if (dev_xdp_prog_count(slave_dev) > 0) { SLAVE_NL_ERR(dev, slave_dev, extack, "Slave has XDP program loaded, please unload before enslaving"); err = -EOPNOTSUPP; goto err; } err = dev_xdp_propagate(slave_dev, &xdp); if (err < 0) { /* ndo_bpf() sets extack error message */ slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); goto err; } if (prog) bpf_prog_inc(prog); } if (prog) { static_branch_inc(&bpf_master_redirect_enabled_key); } else if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&bpf_master_redirect_enabled_key); } return 0; err: /* unwind the program changes */ bond->xdp_prog = old_prog; xdp.prog = old_prog; xdp.extack = NULL; /* do not overwrite original error */ bond_for_each_slave(bond, rollback_slave, iter) { struct net_device *slave_dev = rollback_slave->dev; int err_unwind; if (slave == rollback_slave) break; err_unwind = dev_xdp_propagate(slave_dev, &xdp); if (err_unwind < 0) slave_err(dev, slave_dev, "Error %d when unwinding XDP program change\n", err_unwind); else if (xdp.prog) bpf_prog_inc(xdp.prog); } return err; } static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return bond_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) { if (speed == 0 || speed == SPEED_UNKNOWN) speed = slave->speed; else speed = min(speed, slave->speed); return speed; } /* Set the BOND_PHC_INDEX flag to notify user space */ static int bond_set_phc_index_flag(struct kernel_hwtstamp_config *kernel_cfg) { struct ifreq *ifr = kernel_cfg->ifr; struct hwtstamp_config cfg; if (kernel_cfg->copied_to_user) { /* Lower device has a legacy implementation */ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; cfg.flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX; if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) return -EFAULT; } else { kernel_cfg->flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX; } return 0; } static int bond_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct bonding *bond = netdev_priv(dev); struct net_device *real_dev; int err; real_dev = bond_option_active_slave_get_rcu(bond); if (!real_dev) return -EOPNOTSUPP; err = generic_hwtstamp_get_lower(real_dev, cfg); if (err) return err; return bond_set_phc_index_flag(cfg); } static int bond_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(dev); struct net_device *real_dev; int err; if (!(cfg->flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX)) return -EOPNOTSUPP; real_dev = bond_option_active_slave_get_rcu(bond); if (!real_dev) return -EOPNOTSUPP; err = generic_hwtstamp_set_lower(real_dev, cfg, extack); if (err) return err; return bond_set_phc_index_flag(cfg); } static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; /* Since bond_slave_can_tx returns false for all inactive or down slaves, we * do not need to check mode. Though link speed might not represent * the true receive or transmit bandwidth (not all modes are symmetric) * this is an accurate maximum. */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { bond_update_speed_duplex(slave); if (slave->speed != SPEED_UNKNOWN) { if (BOND_MODE(bond) == BOND_MODE_BROADCAST) speed = bond_mode_bcast_speed(slave, speed); else speed += slave->speed; } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; } } cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; } static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", BOND_ABI_VERSION); } static int bond_ethtool_get_ts_info(struct net_device *bond_dev, struct kernel_ethtool_ts_info *info) { struct bonding *bond = netdev_priv(bond_dev); struct kernel_ethtool_ts_info ts_info; struct net_device *real_dev; bool sw_tx_support = false; struct list_head *iter; struct slave *slave; int ret = 0; rcu_read_lock(); real_dev = bond_option_active_slave_get_rcu(bond); dev_hold(real_dev); rcu_read_unlock(); if (real_dev) { ret = ethtool_get_ts_info_by_layer(real_dev, info); } else { /* Check if all slaves support software tx timestamping */ rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { ret = ethtool_get_ts_info_by_layer(slave->dev, &ts_info); if (!ret && (ts_info.so_timestamping & SOF_TIMESTAMPING_TX_SOFTWARE)) { sw_tx_support = true; continue; } sw_tx_support = false; break; } rcu_read_unlock(); } if (sw_tx_support) info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE; dev_put(real_dev); return ret; } static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = bond_ethtool_get_link_ksettings, .get_ts_info = bond_ethtool_get_ts_info, }; static const struct net_device_ops bond_netdev_ops = { .ndo_init = bond_init, .ndo_uninit = bond_uninit, .ndo_open = bond_open, .ndo_stop = bond_close, .ndo_start_xmit = bond_start_xmit, .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, .ndo_eth_ioctl = bond_eth_ioctl, .ndo_siocbond = bond_do_ioctl, .ndo_siocdevprivate = bond_siocdevprivate, .ndo_change_rx_flags = bond_change_rx_flags, .ndo_set_rx_mode = bond_set_rx_mode, .ndo_change_mtu = bond_change_mtu, .ndo_set_mac_address = bond_set_mac_address, .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, .ndo_poll_controller = bond_poll_controller, #endif .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, .ndo_features_check = passthru_features_check, .ndo_get_xmit_slave = bond_xmit_get_slave, .ndo_sk_get_lower_dev = bond_sk_get_lower_dev, .ndo_bpf = bond_xdp, .ndo_xdp_xmit = bond_xdp_xmit, .ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave, .ndo_hwtstamp_get = bond_hwtstamp_get, .ndo_hwtstamp_set = bond_hwtstamp_set, }; static const struct device_type bond_type = { .name = "bond", }; static void bond_destructor(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); if (bond->wq) destroy_workqueue(bond->wq); free_percpu(bond->rr_tx_counter); } void bond_setup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); spin_lock_init(&bond->mode_lock); bond->params = bonding_defaults; /* Initialize pointers */ bond->dev = bond_dev; /* Initialize the device entry points */ ether_setup(bond_dev); bond_dev->max_mtu = ETH_MAX_MTU; bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; bond_dev->needs_free_netdev = true; bond_dev->priv_destructor = bond_destructor; SET_NETDEV_DEVTYPE(bond_dev, &bond_type); /* Initialize the device options */ bond_dev->flags |= IFF_MASTER; bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT | IFF_NO_QUEUE; bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); #ifdef CONFIG_XFRM_OFFLOAD /* set up xfrm device ops (only supported in active-backup right now) */ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; INIT_LIST_HEAD(&bond->ipsec_list); mutex_init(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ bond_dev->lltx = true; /* Don't allow bond devices to change network namespaces. */ bond_dev->netns_immutable = true; /* By default, we declare the bond to be fully * VLAN hardware accelerated capable. Special * care is taken in the various xmit functions * when there are slaves that are not hw accel * capable */ bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; bond_dev->features |= NETIF_F_GSO_PARTIAL; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_features |= BOND_XFRM_FEATURES; /* Only enable XFRM features if this is an active-backup config */ if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ } /* Destroy a bonding device. * Must be under rtnl_lock when this function is called. */ static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ bond_for_each_slave(bond, slave, iter) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); #ifdef CONFIG_XFRM_OFFLOAD mutex_destroy(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ bond_set_slave_arr(bond, NULL, NULL); list_del_rcu(&bond->bond_list); bond_debug_unregister(bond); } /*------------------------- Module initialization ---------------------------*/ static int __init bond_check_params(struct bond_params *params) { int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; struct bond_opt_value newval; const struct bond_opt_value *valptr; int arp_all_targets_value = 0; u16 ad_actor_sys_prio = 0; u16 ad_user_port_key = 0; __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0 }; int arp_ip_count; int bond_mode = BOND_MODE_ROUNDROBIN; int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; int lacp_fast = 0; int tlb_dynamic_lb; /* Convert string parameters. */ if (mode) { bond_opt_initstr(&newval, mode); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval); if (!valptr) { pr_err("Error: Invalid bonding mode \"%s\"\n", mode); return -EINVAL; } bond_mode = valptr->value; } if (xmit_hash_policy) { if (bond_mode == BOND_MODE_ROUNDROBIN || bond_mode == BOND_MODE_ACTIVEBACKUP || bond_mode == BOND_MODE_BROADCAST) { pr_info("xmit_hash_policy param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, xmit_hash_policy); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH), &newval); if (!valptr) { pr_err("Error: Invalid xmit_hash_policy \"%s\"\n", xmit_hash_policy); return -EINVAL; } xmit_hashtype = valptr->value; } } if (lacp_rate) { if (bond_mode != BOND_MODE_8023AD) { pr_info("lacp_rate param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, lacp_rate); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE), &newval); if (!valptr) { pr_err("Error: Invalid lacp rate \"%s\"\n", lacp_rate); return -EINVAL; } lacp_fast = valptr->value; } } if (ad_select) { bond_opt_initstr(&newval, ad_select); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT), &newval); if (!valptr) { pr_err("Error: Invalid ad_select \"%s\"\n", ad_select); return -EINVAL; } params->ad_select = valptr->value; if (bond_mode != BOND_MODE_8023AD) pr_warn("ad_select param only affects 802.3ad mode\n"); } else { params->ad_select = BOND_AD_STABLE; } if (max_bonds < 0) { pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); max_bonds = BOND_DEFAULT_MAX_BONDS; } if (miimon < 0) { pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", miimon, INT_MAX); miimon = 0; } if (updelay < 0) { pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", updelay, INT_MAX); updelay = 0; } if (downdelay < 0) { pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", downdelay, INT_MAX); downdelay = 0; } if ((use_carrier != 0) && (use_carrier != 1)) { pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", use_carrier); use_carrier = 1; } if (num_peer_notif < 0 || num_peer_notif > 255) { pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", num_peer_notif); num_peer_notif = 1; } /* reset values for 802.3ad/TLB/ALB */ if (!bond_mode_uses_arp(bond_mode)) { if (!miimon) { pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); pr_warn("Forcing miimon to 100msec\n"); miimon = BOND_DEFAULT_MIIMON; } } if (tx_queues < 1 || tx_queues > 255) { pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n", tx_queues, BOND_DEFAULT_TX_QUEUES); tx_queues = BOND_DEFAULT_TX_QUEUES; } if ((all_slaves_active != 0) && (all_slaves_active != 1)) { pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n", all_slaves_active); all_slaves_active = 0; } if (resend_igmp < 0 || resend_igmp > 255) { pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n", resend_igmp, BOND_DEFAULT_RESEND_IGMP); resend_igmp = BOND_DEFAULT_RESEND_IGMP; } bond_opt_initval(&newval, packets_per_slave); if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) { pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n", packets_per_slave, USHRT_MAX); packets_per_slave = 1; } if (bond_mode == BOND_MODE_ALB) { pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n", updelay); } if (!miimon) { if (updelay || downdelay) { /* just warn the user the up/down delay will have * no effect since miimon is zero... */ pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", updelay, downdelay); } } else { /* don't allow arp monitoring */ if (arp_interval) { pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", miimon, arp_interval); arp_interval = 0; } if ((updelay % miimon) != 0) { pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", updelay, miimon, (updelay / miimon) * miimon); } updelay /= miimon; if ((downdelay % miimon) != 0) { pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", downdelay, miimon, (downdelay / miimon) * miimon); } downdelay /= miimon; } if (arp_interval < 0) { pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n", arp_interval, INT_MAX); arp_interval = 0; } for (arp_ip_count = 0, i = 0; (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) { __be32 ip; /* not a complete check, but good enough to catch mistakes */ if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || !bond_is_ip_target_ok(ip)) { pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", arp_ip_target[i]); arp_interval = 0; } else { if (bond_get_targets_ip(arp_target, ip) == -1) arp_target[arp_ip_count++] = ip; else pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", &ip); } } if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", arp_interval); arp_interval = 0; } if (arp_validate) { if (!arp_interval) { pr_err("arp_validate requires arp_interval\n"); return -EINVAL; } bond_opt_initstr(&newval, arp_validate); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE), &newval); if (!valptr) { pr_err("Error: invalid arp_validate \"%s\"\n", arp_validate); return -EINVAL; } arp_validate_value = valptr->value; } else { arp_validate_value = 0; } if (arp_all_targets) { bond_opt_initstr(&newval, arp_all_targets); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS), &newval); if (!valptr) { pr_err("Error: invalid arp_all_targets_value \"%s\"\n", arp_all_targets); arp_all_targets_value = 0; } else { arp_all_targets_value = valptr->value; } } if (miimon) { pr_info("MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, arp_validate_value); pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):", arp_interval, valptr->string, arp_ip_count); for (i = 0; i < arp_ip_count; i++) pr_cont(" %s", arp_ip_target[i]); pr_cont("\n"); } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n"); } if (primary && !bond_mode_uses_primary(bond_mode)) { /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ pr_warn("Warning: %s primary device specified but has no effect in %s mode\n", primary, bond_mode_name(bond_mode)); primary = NULL; } if (primary && primary_reselect) { bond_opt_initstr(&newval, primary_reselect); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT), &newval); if (!valptr) { pr_err("Error: Invalid primary_reselect \"%s\"\n", primary_reselect); return -EINVAL; } primary_reselect_value = valptr->value; } else { primary_reselect_value = BOND_PRI_RESELECT_ALWAYS; } if (fail_over_mac) { bond_opt_initstr(&newval, fail_over_mac); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC), &newval); if (!valptr) { pr_err("Error: invalid fail_over_mac \"%s\"\n", fail_over_mac); return -EINVAL; } fail_over_mac_value = valptr->value; if (bond_mode != BOND_MODE_ACTIVEBACKUP) pr_warn("Warning: fail_over_mac only affects active-backup mode\n"); } else { fail_over_mac_value = BOND_FOM_NONE; } bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse( bond_opt_get(BOND_OPT_AD_ACTOR_SYS_PRIO), &newval); if (!valptr) { pr_err("Error: No ad_actor_sys_prio default value"); return -EINVAL; } ad_actor_sys_prio = valptr->value; valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_USER_PORT_KEY), &newval); if (!valptr) { pr_err("Error: No ad_user_port_key default value"); return -EINVAL; } ad_user_port_key = valptr->value; bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval); if (!valptr) { pr_err("Error: No tlb_dynamic_lb default value"); return -EINVAL; } tlb_dynamic_lb = valptr->value; if (lp_interval == 0) { pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; } /* fill params struct with the proper values */ params->mode = bond_mode; params->xmit_policy = xmit_hashtype; params->miimon = miimon; params->num_peer_notif = num_peer_notif; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->arp_all_targets = arp_all_targets_value; params->missed_max = 2; params->updelay = updelay; params->downdelay = downdelay; params->peer_notif_delay = 0; params->use_carrier = use_carrier; params->lacp_active = 1; params->lacp_fast = lacp_fast; params->primary[0] = 0; params->primary_reselect = primary_reselect_value; params->fail_over_mac = fail_over_mac_value; params->tx_queues = tx_queues; params->all_slaves_active = all_slaves_active; params->resend_igmp = resend_igmp; params->min_links = min_links; params->lp_interval = lp_interval; params->packets_per_slave = packets_per_slave; params->tlb_dynamic_lb = tlb_dynamic_lb; params->ad_actor_sys_prio = ad_actor_sys_prio; eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; params->coupled_control = 1; if (packets_per_slave > 0) { params->reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); } else { /* reciprocal_packets_per_slave is unused if * packets_per_slave is 0 or 1, just initialize it */ params->reciprocal_packets_per_slave = (struct reciprocal_value) { 0 }; } if (primary) strscpy_pad(params->primary, primary, sizeof(params->primary)); memcpy(params->arp_targets, arp_target, sizeof(arp_target)); #if IS_ENABLED(CONFIG_IPV6) memset(params->ns_targets, 0, sizeof(struct in6_addr) * BOND_MAX_NS_TARGETS); #endif return 0; } /* Called from registration process */ static int bond_init(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); netdev_dbg(bond_dev, "Begin bond_init\n"); bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, bond_dev->name); if (!bond->wq) return -ENOMEM; bond->notifier_ctx = false; spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); list_add_tail_rcu(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); bond_debug_register(bond); /* Ensure valid dev_addr */ if (is_zero_ether_addr(bond_dev->dev_addr) && bond_dev->addr_assign_type == NET_ADDR_PERM) eth_hw_addr_random(bond_dev); return 0; } unsigned int bond_get_num_tx_queues(void) { return tx_queues; } /* Create a new bond based on the specified name and bonding parameters. * If name is NULL, obtain a suitable "bond%d" name for us. * Caller must NOT hold rtnl_lock; we need to release it here before we * set up our sysfs entries. */ int bond_create(struct net *net, const char *name) { struct net_device *bond_dev; struct bonding *bond; int res = -ENOMEM; rtnl_lock(); bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "bond%d", NET_NAME_UNKNOWN, bond_setup, tx_queues); if (!bond_dev) goto out; bond = netdev_priv(bond_dev); dev_net_set(bond_dev, net); bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); if (res < 0) { free_netdev(bond_dev); goto out; } netif_carrier_off(bond_dev); bond_work_init_all(bond); out: rtnl_unlock(); return res; } static int __net_init bond_net_init(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); bn->net = net; INIT_LIST_HEAD(&bn->dev_list); bond_create_proc_dir(bn); bond_create_sysfs(bn); return 0; } /* According to commit 69b0216ac255 ("bonding: fix bonding_masters * race condition in bond unloading") we need to remove sysfs files * before we remove our devices (done later in bond_net_exit_batch_rtnl()) */ static void __net_exit bond_net_pre_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); bond_destroy_sysfs(bn); } static void __net_exit bond_net_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_kill_list) { struct bond_net *bn; struct net *net; /* Kill off any bonds created after unregistering bond rtnl ops */ list_for_each_entry(net, net_list, exit_list) { struct bonding *bond, *tmp_bond; bn = net_generic(net, bond_net_id); list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) unregister_netdevice_queue(bond->dev, dev_kill_list); } } /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory * only after all bonds are gone") bond_destroy_proc_dir() is called * after bond_net_exit_batch_rtnl() has completed. */ static void __net_exit bond_net_exit_batch(struct list_head *net_list) { struct bond_net *bn; struct net *net; list_for_each_entry(net, net_list, exit_list) { bn = net_generic(net, bond_net_id); bond_destroy_proc_dir(bn); } } static struct pernet_operations bond_net_ops = { .init = bond_net_init, .pre_exit = bond_net_pre_exit, .exit_batch_rtnl = bond_net_exit_batch_rtnl, .exit_batch = bond_net_exit_batch, .id = &bond_net_id, .size = sizeof(struct bond_net), }; static int __init bonding_init(void) { int i; int res; res = bond_check_params(&bonding_defaults); if (res) goto out; bond_create_debugfs(); res = register_pernet_subsys(&bond_net_ops); if (res) goto err_net_ops; res = bond_netlink_init(); if (res) goto err_link; for (i = 0; i < max_bonds; i++) { res = bond_create(&init_net, NULL); if (res) goto err; } skb_flow_dissector_init(&flow_keys_bonding, flow_keys_bonding_keys, ARRAY_SIZE(flow_keys_bonding_keys)); register_netdevice_notifier(&bond_netdev_notifier); out: return res; err: bond_netlink_fini(); err_link: unregister_pernet_subsys(&bond_net_ops); err_net_ops: bond_destroy_debugfs(); goto out; } static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); bond_netlink_fini(); unregister_pernet_subsys(&bond_net_ops); bond_destroy_debugfs(); #ifdef CONFIG_NET_POLL_CONTROLLER /* Make sure we don't have an imbalance on our netpoll blocking */ WARN_ON(atomic_read(&netpoll_block_tx)); #endif } module_init(bonding_init); module_exit(bonding_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); |
| 458 273 177 178 178 177 178 178 1958 1725 231 1726 1728 1726 3013 3010 27 458 748 295 457 458 458 457 295 295 295 130 105 104 105 26 1 1 1 17 17 17 91 91 91 7 5 3 353 353 353 353 353 313 232 8 162 30 30 18 18 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* net/core/xdp.c * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/bug.h> #include <net/page_pool/helpers.h> #include <net/hotdata.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> #include <net/xdp_sock_drv.h> #define REG_STATE_NEW 0x0 #define REG_STATE_REGISTERED 0x1 #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 static DEFINE_IDA(mem_id_pool); static DEFINE_MUTEX(mem_id_lock); #define MEM_ID_MAX 0xFFFE #define MEM_ID_MIN 1 static int mem_id_next = MEM_ID_MIN; static bool mem_id_init; /* false */ static struct rhashtable *mem_id_ht; static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) { const u32 *k = data; const u32 key = *k; BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xdp_mem_allocator *xa = ptr; u32 mem_id = *(u32 *)arg->key; return xa->mem.id != mem_id; } static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, .hashfn = xdp_mem_id_hashfn, .obj_cmpfn = xdp_mem_id_cmp, }; static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) { struct xdp_mem_allocator *xa; xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ ida_free(&mem_id_pool, xa->mem.id); kfree(xa); } static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); } static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; struct rhashtable_iter iter; mutex_lock(&mem_id_lock); rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { if (xa->allocator == allocator) mem_xa_remove(xa); } rhashtable_walk_stop(&iter); } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); } void xdp_unreg_mem_model(struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; int type = mem->type; int id = mem->id; /* Reset mem info to defaults */ mem->id = 0; mem->type = 0; if (id == 0) return; if (type == MEM_TYPE_PAGE_POOL) { xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; } xdp_unreg_mem_model(&xdp_rxq->mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ if (xdp_rxq->reg_state == REG_STATE_UNUSED) return; xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) { memset(xdp_rxq, 0, sizeof(*xdp_rxq)); } /* Returns 0 on success, negative on failure */ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size) { if (!dev) { WARN(1, "Missing net_device from driver"); return -ENODEV; } if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); return -EINVAL; } if (xdp_rxq->reg_state == REG_STATE_REGISTERED) { WARN(1, "Missing unregister, handled but fix driver"); xdp_rxq_info_unreg(xdp_rxq); } /* State either UNREGISTERED or NEW */ xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->reg_state = REG_STATE_UNUSED; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unused); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) { return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); static int __mem_id_init_hash_table(void) { struct rhashtable *rht; int ret; if (unlikely(mem_id_init)) return 0; rht = kzalloc(sizeof(*rht), GFP_KERNEL); if (!rht) return -ENOMEM; ret = rhashtable_init(rht, &mem_id_rht_params); if (ret < 0) { kfree(rht); return ret; } mem_id_ht = rht; smp_mb(); /* mutex lock should provide enough pairing */ mem_id_init = true; return 0; } /* Allocate a cyclic ID that maps to allocator pointer. * See: https://www.kernel.org/doc/html/latest/core-api/idr.html * * Caller must lock mem_id_lock. */ static int __mem_id_cyclic_get(gfp_t gfp) { int retries = 1; int id; again: id = ida_alloc_range(&mem_id_pool, mem_id_next, MEM_ID_MAX - 1, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ if (retries--) { mem_id_next = MEM_ID_MIN; goto again; } } return id; /* errno */ } mem_id_next = id + 1; return id; } static bool __is_supported_mem_type(enum xdp_mem_type type) { if (type == MEM_TYPE_PAGE_POOL) return is_page_pool_compiled_in(); if (type >= MEM_TYPE_MAX) return false; return true; } static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; if (!__is_supported_mem_type(type)) return ERR_PTR(-EOPNOTSUPP); mem->type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) return ERR_PTR(-EINVAL); /* Setup time check page_pool req */ return NULL; } /* Delay init of rhashtable to save memory if feature isn't used */ if (!mem_id_init) { mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); if (ret < 0) return ERR_PTR(ret); } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) return ERR_PTR(-ENOMEM); mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); if (id < 0) { errno = id; goto err; } mem->id = id; xdp_alloc->mem = *mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { ida_free(&mem_id_pool, mem->id); mem->id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) page_pool_use_xdp_mem(allocator, mem_allocator_disconnect, mem); mutex_unlock(&mem_id_lock); return xdp_alloc; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); return ERR_PTR(errno); } int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; xdp_alloc = __xdp_reg_mem_model(mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); return 0; } EXPORT_SYMBOL_GPL(xdp_reg_mem_model); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return -EFAULT; } xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator); if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); if (type == MEM_TYPE_XSK_BUFF_POOL && allocator) xsk_pool_set_rxq_info(allocator, xdp_rxq); if (trace_mem_connect_enabled() && xdp_alloc) trace_mem_connect(xdp_alloc, xdp_rxq); return 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /** * xdp_reg_page_pool - register &page_pool as a memory provider for XDP * @pool: &page_pool to register * * Can be used to register pools manually without connecting to any XDP RxQ * info, so that the XDP layer will be aware of them. Then, they can be * attached to an RxQ info manually via xdp_rxq_info_attach_page_pool(). * * Return: %0 on success, -errno on error. */ int xdp_reg_page_pool(struct page_pool *pool) { struct xdp_mem_info mem; return xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pool); } EXPORT_SYMBOL_GPL(xdp_reg_page_pool); /** * xdp_unreg_page_pool - unregister &page_pool from the memory providers list * @pool: &page_pool to unregister * * A shorthand for manual unregistering page pools. If the pool was previously * attached to an RxQ info, it must be detached first. */ void xdp_unreg_page_pool(const struct page_pool *pool) { struct xdp_mem_info mem = { .type = MEM_TYPE_PAGE_POOL, .id = pool->xdp_mem_id, }; xdp_unreg_mem_model(&mem); } EXPORT_SYMBOL_GPL(xdp_unreg_page_pool); /** * xdp_rxq_info_attach_page_pool - attach registered pool to RxQ info * @xdp_rxq: XDP RxQ info to attach the pool to * @pool: pool to attach * * If the pool was registered manually, this function must be called instead * of xdp_rxq_info_reg_mem_model() to connect it to the RxQ info. */ void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, const struct page_pool *pool) { struct xdp_mem_info mem = { .type = MEM_TYPE_PAGE_POOL, .id = pool->xdp_mem_id, }; xdp_rxq_info_attach_mem_model(xdp_rxq, &mem); } EXPORT_SYMBOL_GPL(xdp_rxq_info_attach_page_pool); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, bool napi_direct, struct xdp_buff *xdp) { switch (mem_type) { case MEM_TYPE_PAGE_POOL: netmem = netmem_compound_head(netmem); if (napi_direct && xdp_return_frame_no_direct()) napi_direct = false; /* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE) * as mem->type knows this a page_pool page */ page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, napi_direct); break; case MEM_TYPE_PAGE_SHARED: page_frag_free(__netmem_address(netmem)); break; case MEM_TYPE_PAGE_ORDER0: put_page(__netmem_to_page(netmem)); break; case MEM_TYPE_XSK_BUFF_POOL: /* NB! Only valid from an xdp_buff! */ xsk_buff_free(xdp); break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem_type); break; } } void xdp_return_frame(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, false, NULL); out: __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdpf->mem_type, true, NULL); out: __xdp_return(virt_to_netmem(xdpf->data), xdpf->mem_type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); /* XDP bulk APIs introduce a defer/flush mechanism to return * pages belonging to the same xdp_mem_allocator object * (identified via the mem.id field) in bulk to optimize * I-cache and D-cache. * The bulk queue size is set to 16 to be aligned to how * XDP_REDIRECT bulking works. The bulk is flushed when * it is full or when mem.id changes. * xdp_frame_bulk is usually stored/allocated on the function * call-stack to avoid locking penalties. */ /* Must be called with rcu_read_lock held */ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq) { if (xdpf->mem_type != MEM_TYPE_PAGE_POOL) { xdp_return_frame(xdpf); return; } if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); if (unlikely(xdp_frame_has_frags(xdpf))) { struct skb_shared_info *sinfo; int i; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { skb_frag_t *frag = &sinfo->frags[i]; bq->q[bq->count++] = skb_frag_netmem(frag); if (bq->count == XDP_BULK_QUEUE_SIZE) xdp_flush_frame_bulk(bq); } } bq->q[bq->count++] = virt_to_netmem(xdpf->data); } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); /** * xdp_return_frag -- free one XDP frag or decrement its refcount * @netmem: network memory reference to release * @xdp: &xdp_buff to release the frag for */ void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp) { __xdp_return(netmem, xdp->rxq->mem.type, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frag); void xdp_return_buff(struct xdp_buff *xdp) { struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); for (u32 i = 0; i < sinfo->nr_frags; i++) __xdp_return(skb_frag_netmem(&sinfo->frags[i]), xdp->rxq->mem.type, true, xdp); out: __xdp_return(virt_to_netmem(xdp->data), xdp->rxq->mem.type, true, xdp); } EXPORT_SYMBOL_GPL(xdp_return_buff); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog) bpf_prog_put(info->prog); info->prog = bpf->prog; info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) { unsigned int metasize, totsize; void *addr, *data_to_copy; struct xdp_frame *xdpf; struct page *page; /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ metasize = xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; if (sizeof(*xdpf) + totsize > PAGE_SIZE) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); xdpf = addr; memset(xdpf, 0, sizeof(*xdpf)); addr += sizeof(*xdpf); data_to_copy = metasize ? xdp->data_meta : xdp->data; memcpy(addr, data_to_copy, totsize); xdpf->data = addr + metasize; xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; xdpf->mem_type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); return xdpf; } EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); /* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */ void xdp_warn(const char *msg, const char *func, const int line) { WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); /** * xdp_build_skb_from_buff - create an skb from &xdp_buff * @xdp: &xdp_buff to convert to an skb * * Perform common operations to create a new skb to pass up the stack from * &xdp_buff: allocate an skb head from the NAPI percpu cache, initialize * skb data pointers and offsets, set the recycle bit if the buff is * PP-backed, Rx queue index, protocol and update frags info. * * Return: new &sk_buff on success, %NULL on error. */ struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp) { const struct xdp_rxq_info *rxq = xdp->rxq; const struct skb_shared_info *sinfo; struct sk_buff *skb; u32 nr_frags = 0; int metalen; if (unlikely(xdp_buff_has_frags(xdp))) { sinfo = xdp_get_shared_info_from_buff(xdp); nr_frags = sinfo->nr_frags; } skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); metalen = xdp->data - xdp->data_meta; if (metalen > 0) skb_metadata_set(skb, metalen); if (rxq->mem.type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); skb_record_rx_queue(skb, rxq->queue_index); if (unlikely(nr_frags)) { u32 tsize; tsize = sinfo->xdp_frags_truesize ? : nr_frags * xdp->frame_sz; xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, tsize, xdp_buff_is_frag_pfmemalloc(xdp)); } skb->protocol = eth_type_trans(skb, rxq->dev); return skb; } EXPORT_SYMBOL_GPL(xdp_build_skb_from_buff); /** * xdp_copy_frags_from_zc - copy frags from XSk buff to skb * @skb: skb to copy frags to * @xdp: XSk &xdp_buff from which the frags will be copied * @pp: &page_pool backing page allocation, if available * * Copy all frags from XSk &xdp_buff to the skb to pass it up the stack. * Allocate a new buffer for each frag, copy it and attach to the skb. * * Return: true on success, false on netmem allocation fail. */ static noinline bool xdp_copy_frags_from_zc(struct sk_buff *skb, const struct xdp_buff *xdp, struct page_pool *pp) { struct skb_shared_info *sinfo = skb_shinfo(skb); const struct skb_shared_info *xinfo; u32 nr_frags, tsize = 0; bool pfmemalloc = false; xinfo = xdp_get_shared_info_from_buff(xdp); nr_frags = xinfo->nr_frags; for (u32 i = 0; i < nr_frags; i++) { u32 len = skb_frag_size(&xinfo->frags[i]); u32 offset, truesize = len; netmem_ref netmem; netmem = page_pool_dev_alloc_netmem(pp, &offset, &truesize); if (unlikely(!netmem)) { sinfo->nr_frags = i; return false; } memcpy(__netmem_address(netmem), __netmem_address(xinfo->frags[i].netmem), LARGEST_ALIGN(len)); __skb_fill_netmem_desc_noacc(sinfo, i, netmem, offset, len); tsize += truesize; pfmemalloc |= netmem_is_pfmemalloc(netmem); } xdp_update_skb_shared_info(skb, nr_frags, xinfo->xdp_frags_size, tsize, pfmemalloc); return true; } /** * xdp_build_skb_from_zc - create an skb from XSk &xdp_buff * @xdp: source XSk buff * * Similar to xdp_build_skb_from_buff(), but for XSk frames. Allocate an skb * head, new buffer for the head, copy the data and initialize the skb fields. * If there are frags, allocate new buffers for them and copy. * Buffers are allocated from the system percpu pools to try recycling them. * If new skb was built successfully, @xdp is returned to XSk pool's freelist. * On error, it remains untouched and the caller must take care of this. * * Return: new &sk_buff on success, %NULL on error. */ struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp) { struct page_pool *pp = this_cpu_read(system_page_pool); const struct xdp_rxq_info *rxq = xdp->rxq; u32 len = xdp->data_end - xdp->data_meta; u32 truesize = xdp->frame_sz; struct sk_buff *skb; int metalen; void *data; if (!IS_ENABLED(CONFIG_PAGE_POOL)) return NULL; data = page_pool_dev_alloc_va(pp, &truesize); if (unlikely(!data)) return NULL; skb = napi_build_skb(data, truesize); if (unlikely(!skb)) { page_pool_free_va(pp, data, true); return NULL; } skb_mark_for_recycle(skb); skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); memcpy(__skb_put(skb, len), xdp->data_meta, LARGEST_ALIGN(len)); metalen = xdp->data - xdp->data_meta; if (metalen > 0) { skb_metadata_set(skb, metalen); __skb_pull(skb, metalen); } skb_record_rx_queue(skb, rxq->queue_index); if (unlikely(xdp_buff_has_frags(xdp)) && unlikely(!xdp_copy_frags_from_zc(skb, xdp, pp))) { napi_consume_skb(skb, true); return NULL; } xsk_buff_free(xdp); skb->protocol = eth_type_trans(skb, rxq->dev); return skb; } EXPORT_SYMBOL_GPL(xdp_build_skb_from_zc); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); unsigned int headroom, frame_size; void *hard_start; u8 nr_frags; /* xdp frags frame */ if (unlikely(xdp_frame_has_frags(xdpf))) nr_frags = sinfo->nr_frags; /* Part of headroom was reserved to xdpf */ headroom = sizeof(*xdpf) + xdpf->headroom; /* Memory size backing xdp_frame data already have reserved * room for build_skb to place skb_shared_info in tailroom. */ frame_size = xdpf->frame_sz; hard_start = xdpf->data - headroom; skb = build_skb_around(skb, hard_start, frame_size); if (unlikely(!skb)) return NULL; skb_reserve(skb, headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); if (unlikely(xdp_frame_has_frags(xdpf))) xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, nr_frags * xdpf->frame_sz, xdp_frame_is_frag_pfmemalloc(xdpf)); /* Essential SKB info: protocol and skb->dev */ skb->protocol = eth_type_trans(skb, dev); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) * - HW RX hash (skb_set_hash) * - RX ring dev queue index (skb_record_rx_queue) */ if (xdpf->mem_type == MEM_TYPE_PAGE_POOL) skb_mark_for_recycle(skb); /* Allow SKB to reuse area used by xdp_frame */ xdp_scrub_frame(xdpf); return skb; } EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) { unsigned int headroom, totalsize; struct xdp_frame *nxdpf; struct page *page; void *addr; headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; if (unlikely(totalsize > PAGE_SIZE)) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); memcpy(addr, xdpf, totalsize); nxdpf = addr; nxdpf->data = addr + headroom; nxdpf->frame_sz = PAGE_SIZE; nxdpf->mem_type = MEM_TYPE_PAGE_ORDER0; return nxdpf; } __bpf_kfunc_start_defs(); /** * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp. * @ctx: XDP context pointer. * @timestamp: Return value pointer. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc * * ``-ENODATA`` : means no RX-timestamp available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. * @rss_type: Return value pointer for RSS type. * * The RSS hash type (@rss_type) specifies what portion of packet headers NIC * hardware used when calculating RSS hash value. The RSS type can be decoded * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } /** * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag * @ctx: XDP context pointer. * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) * * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** * and should be used as follows: * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` * * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. * Driver is expected to provide those in **host byte order (usually LE)**, * so the bpf program should not perform byte conversion. * According to 802.1Q standard, *VLAN TCI (Tag control information)* * is a bit field that contains: * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, * *Drop eligible indicator (DEI)* - 1 bit, * *Priority code point (PCP)* - 3 bits. * For detailed meaning of DEI and PCP, please refer to other sources. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc * * ``-ENODATA`` : VLAN tag was not stripped or is not available */ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { return -EOPNOTSUPP; } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(xdp_metadata_kfunc_ids) #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC BTF_KFUNCS_END(xdp_metadata_kfunc_ids) static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { .owner = THIS_MODULE, .set = &xdp_metadata_kfunc_ids, }; BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted) #define XDP_METADATA_KFUNC(name, _, str, __) BTF_ID(func, str) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC u32 bpf_xdp_metadata_kfunc_id(int id) { /* xdp_metadata_kfunc_ids is sorted and can't be used */ return xdp_metadata_kfunc_ids_unsorted[id]; } bool bpf_dev_bound_kfunc_id(u32 btf_id) { return btf_id_set8_contains(&xdp_metadata_kfunc_ids, btf_id); } static int __init xdp_metadata_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { val &= NETDEV_XDP_ACT_MASK; if (dev->xdp_features == val) return; dev->xdp_features = val; if (dev->reg_state == NETREG_REGISTERED) call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); } EXPORT_SYMBOL_GPL(xdp_set_features_flag); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT); if (support_sg) val |= NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); void xdp_features_clear_redirect_target(struct net_device *dev) { xdp_features_t val = dev->xdp_features; val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG); xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); |
| 13 2 3 2 3 114 111 11 112 14 9 14 8 111 123 9 9 1 1 125 1 112 16 9 3 10 20 10 20 126 125 131 131 130 2 62 69 87 44 86 117 57 3 114 116 68 55 117 116 62 62 117 131 6 1 103 55 117 30 124 5 2 105 53 119 30 130 131 1 1 1 1 1 3 1 1 1 3 3 3 108 16 2 3 1 3 3 1 2 129 128 62 62 68 68 131 2 129 130 130 128 131 2 131 131 129 131 4 4 126 124 2 2 108 48 131 5 5 5 131 129 1 129 3 131 53 117 8 119 1 1 104 49 130 3 3 101 127 1 101 101 101 98 131 127 125 5 110 58 53 58 17 15 17 126 124 25 22 3 19 19 28 28 126 115 40 40 40 1 1 98 92 9 9 36 126 126 125 124 2 123 109 45 125 1 51 50 45 22 5 3 3 6 6 5 5 5 5 42 42 42 60 5 3 6 5 42 61 4 35 21 61 1 56 4 37 21 41 19 56 3 1 59 1 57 3 57 3 58 2 58 2 58 2 58 2 56 3 1 56 3 1 54 6 55 5 53 3 4 53 7 59 4 4 33 61 1 60 59 60 60 60 76 3 75 75 76 76 1 3 7 7 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 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* COMMON Applications Kept Enhanced (CAKE) discipline * * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com> * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk> * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com> * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de> * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au> * * The CAKE Principles: * (or, how to have your cake and eat it too) * * This is a combination of several shaping, AQM and FQ techniques into one * easy-to-use package: * * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE * equipment and bloated MACs. This operates in deficit mode (as in sch_fq), * eliminating the need for any sort of burst parameter (eg. token bucket * depth). Burst support is limited to that necessary to overcome scheduling * latency. * * - A Diffserv-aware priority queue, giving more priority to certain classes, * up to a specified fraction of bandwidth. Above that bandwidth threshold, * the priority is reduced to avoid starving other tins. * * - Each priority tin has a separate Flow Queue system, to isolate traffic * flows from each other. This prevents a burst on one flow from increasing * the delay to another. Flows are distributed to queues using a * set-associative hash function. * * - Each queue is actively managed by Cobalt, which is a combination of the * Codel and Blue AQM algorithms. This serves flows fairly, and signals * congestion early via ECN (if available) and/or packet drops, to keep * latency low. The codel parameters are auto-tuned based on the bandwidth * setting, as is necessary at low bandwidths. * * The configuration parameters are kept deliberately simple for ease of use. * Everything has sane defaults. Complete generality of configuration is *not* * a goal. * * The priority queue operates according to a weighted DRR scheme, combined with * a bandwidth tracker which reuses the shaper logic to detect which side of the * bandwidth sharing threshold the tin is operating. This determines whether a * priority-based weight (high) or a bandwidth-based weight (low) is used for * that tin in the current pass. * * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly * granted us permission to leverage. */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> #include <linux/if_vlan.h> #include <net/gso.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/flow_dissector.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #endif #define CAKE_SET_WAYS (8) #define CAKE_MAX_TINS (8) #define CAKE_QUEUES (1024) #define CAKE_FLOW_MASK 63 #define CAKE_FLOW_NAT_FLAG 64 /* struct cobalt_params - contains codel and blue parameters * @interval: codel initial drop rate * @target: maximum persistent sojourn time & blue update rate * @mtu_time: serialisation delay of maximum-size packet * @p_inc: increment of blue drop probability (0.32 fxp) * @p_dec: decrement of blue drop probability (0.32 fxp) */ struct cobalt_params { u64 interval; u64 target; u64 mtu_time; u32 p_inc; u32 p_dec; }; /* struct cobalt_vars - contains codel and blue variables * @count: codel dropping frequency * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 * @drop_next: time to drop next packet, or when we dropped last * @blue_timer: Blue time to next drop * @p_drop: BLUE drop probability (0.32 fxp) * @dropping: set if in dropping state * @ecn_marked: set if marked */ struct cobalt_vars { u32 count; u32 rec_inv_sqrt; ktime_t drop_next; ktime_t blue_timer; u32 p_drop; bool dropping; bool ecn_marked; }; enum { CAKE_SET_NONE = 0, CAKE_SET_SPARSE, CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */ CAKE_SET_BULK, CAKE_SET_DECAYING }; struct cake_flow { /* this stuff is all needed per-flow at dequeue time */ struct sk_buff *head; struct sk_buff *tail; struct list_head flowchain; s32 deficit; u32 dropped; struct cobalt_vars cvars; u16 srchost; /* index into cake_host table */ u16 dsthost; u8 set; }; /* please try to keep this structure <= 64 bytes */ struct cake_host { u32 srchost_tag; u32 dsthost_tag; u16 srchost_bulk_flow_count; u16 dsthost_bulk_flow_count; }; struct cake_heap_entry { u16 t:3, b:10; }; struct cake_tin_data { struct cake_flow flows[CAKE_QUEUES]; u32 backlogs[CAKE_QUEUES]; u32 tags[CAKE_QUEUES]; /* for set association */ u16 overflow_idx[CAKE_QUEUES]; struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */ u16 flow_quantum; struct cobalt_params cparams; u32 drop_overlimit; u16 bulk_flow_count; u16 sparse_flow_count; u16 decaying_flow_count; u16 unresponsive_flow_count; u32 max_skblen; struct list_head new_flows; struct list_head old_flows; struct list_head decaying_flows; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ ktime_t time_next_packet; u64 tin_rate_ns; u64 tin_rate_bps; u16 tin_rate_shft; u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; u32 tin_ecn_mark; u32 packets; u64 bytes; u32 ack_drops; /* moving averages */ u64 avge_delay; u64 peak_delay; u64 base_delay; /* hash function stats */ u32 way_directs; u32 way_hits; u32 way_misses; u32 way_collisions; }; /* number of tins is small, so size of this struct doesn't matter much */ struct cake_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ struct tcf_block *block; struct cake_tin_data *tins; struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS]; u16 overflow_timeout; u16 tin_cnt; u8 tin_mode; u8 flow_mode; u8 ack_filter; u8 atm_mode; u32 fwmark_mask; u16 fwmark_shft; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ u16 rate_shft; ktime_t time_next_packet; ktime_t failsafe_next_packet; u64 rate_ns; u64 rate_bps; u16 rate_flags; s16 rate_overhead; u16 rate_mpu; u64 interval; u64 target; /* resource tracking */ u32 buffer_used; u32 buffer_max_used; u32 buffer_limit; u32 buffer_config_limit; /* indices for dequeue */ u16 cur_tin; u16 cur_flow; struct qdisc_watchdog watchdog; const u8 *tin_index; const u8 *tin_order; /* bandwidth capacity estimate */ ktime_t last_packet_time; ktime_t avg_window_begin; u64 avg_packet_interval; u64 avg_window_bytes; u64 avg_peak_bandwidth; ktime_t last_reconfig_time; /* packet length stats */ u32 avg_netoff; u16 max_netlen; u16 max_adjlen; u16 min_netlen; u16 min_adjlen; }; enum { CAKE_FLAG_OVERHEAD = BIT(0), CAKE_FLAG_AUTORATE_INGRESS = BIT(1), CAKE_FLAG_INGRESS = BIT(2), CAKE_FLAG_WASH = BIT(3), CAKE_FLAG_SPLIT_GSO = BIT(4) }; /* COBALT operates the Codel and BLUE algorithms in parallel, in order to * obtain the best features of each. Codel is excellent on flows which * respond to congestion signals in a TCP-like way. BLUE is more effective on * unresponsive flows. */ struct cobalt_skb_cb { ktime_t enqueue_time; u32 adjusted_len; }; static u64 us_to_ns(u64 us) { return us * NSEC_PER_USEC; } static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb)); return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data; } static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb) { return get_cobalt_cb(skb)->enqueue_time; } static void cobalt_set_enqueue_time(struct sk_buff *skb, ktime_t now) { get_cobalt_cb(skb)->enqueue_time = now; } static u16 quantum_div[CAKE_QUEUES + 1] = {0}; /* Diffserv lookup tables */ static const u8 precedence[] = { 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, }; static const u8 diffserv8[] = { 2, 0, 1, 2, 4, 2, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 5, 2, 4, 2, 4, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 6, 2, 3, 2, 3, 2, 3, 2, 6, 2, 2, 2, 6, 2, 6, 2, 7, 2, 2, 2, 2, 2, 2, 2, 7, 2, 2, 2, 2, 2, 2, 2, }; static const u8 diffserv4[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 3, 0, 2, 0, 2, 0, 2, 0, 3, 0, 0, 0, 3, 0, 3, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, }; static const u8 diffserv3[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, }; static const u8 besteffort[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, }; /* tin priority order for |