| 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the ICMP module. * * Version: @(#)icmp.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _ICMP_H #define _ICMP_H #include <linux/icmp.h> #include <net/inet_sock.h> #include <net/snmp.h> #include <net/ip.h> struct icmp_err { int errno; unsigned int fatal:1; }; extern const struct icmp_err icmp_err_convert[]; #define ICMP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define __ICMP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.icmp_statistics, field) #define ICMPMSGOUT_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256) #define ICMPMSGIN_INC_STATS(net, field) SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field) struct dst_entry; struct net_proto_family; struct sk_buff; struct net; void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, const struct inet_skb_parm *parm); static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { __icmp_send(skb_in, type, code, info, IPCB(skb_in)); } #if IS_ENABLED(CONFIG_NF_NAT) void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); #else static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct inet_skb_parm parm; memset(&parm, 0, sizeof(parm)); __icmp_send(skb_in, type, code, info, &parm); } #endif int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr); #endif /* _ICMP_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2023 Bootlin * */ #include "common.h" #include "netlink.h" #include <linux/phy.h> #include <linux/phy_link_topology.h> #include <linux/sfp.h> #include <net/netdev_lock.h> struct phy_req_info { struct ethnl_req_info base; }; struct phy_reply_data { struct ethnl_reply_data base; u32 phyindex; char *drvname; char *name; unsigned int upstream_type; char *upstream_sfp_name; unsigned int upstream_index; char *downstream_sfp_name; }; #define PHY_REPDATA(__reply_base) \ container_of(__reply_base, struct phy_reply_data, base) const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int phy_reply_size(const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data) { struct phy_reply_data *rep_data = PHY_REPDATA(reply_data); size_t size = 0; /* ETHTOOL_A_PHY_INDEX */ size += nla_total_size(sizeof(u32)); /* ETHTOOL_A_DRVNAME */ if (rep_data->drvname) size += nla_total_size(strlen(rep_data->drvname) + 1); /* ETHTOOL_A_NAME */ size += nla_total_size(strlen(rep_data->name) + 1); /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ size += nla_total_size(sizeof(u32)); /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ if (rep_data->upstream_sfp_name) size += nla_total_size(strlen(rep_data->upstream_sfp_name) + 1); /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ if (rep_data->upstream_index) size += nla_total_size(sizeof(u32)); /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ if (rep_data->downstream_sfp_name) size += nla_total_size(strlen(rep_data->downstream_sfp_name) + 1); return size; } static int phy_prepare_data(const struct ethnl_req_info *req_info, struct ethnl_reply_data *reply_data, const struct genl_info *info) { struct phy_link_topology *topo = reply_data->dev->link_topo; struct phy_reply_data *rep_data = PHY_REPDATA(reply_data); struct nlattr **tb = info->attrs; struct phy_device_node *pdn; struct phy_device *phydev; /* RTNL is held by the caller */ phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER, info->extack); if (IS_ERR_OR_NULL(phydev)) return -EOPNOTSUPP; pdn = xa_load(&topo->phys, phydev->phyindex); if (!pdn) return -EOPNOTSUPP; rep_data->phyindex = phydev->phyindex; rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL); rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); rep_data->upstream_type = pdn->upstream_type; if (pdn->upstream_type == PHY_UPSTREAM_PHY) { struct phy_device *upstream = pdn->upstream.phydev; rep_data->upstream_index = upstream->phyindex; } if (pdn->parent_sfp_bus) rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus), GFP_KERNEL); if (phydev->sfp_bus) rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus), GFP_KERNEL); return 0; } static int phy_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data) { struct phy_reply_data *rep_data = PHY_REPDATA(reply_data); if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, rep_data->phyindex) || nla_put_string(skb, ETHTOOL_A_PHY_NAME, rep_data->name) || nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, rep_data->upstream_type)) return -EMSGSIZE; if (rep_data->drvname && nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, rep_data->drvname)) return -EMSGSIZE; if (rep_data->upstream_index && nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, rep_data->upstream_index)) return -EMSGSIZE; if (rep_data->upstream_sfp_name && nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, rep_data->upstream_sfp_name)) return -EMSGSIZE; if (rep_data->downstream_sfp_name && nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, rep_data->downstream_sfp_name)) return -EMSGSIZE; return 0; } static void phy_cleanup_data(struct ethnl_reply_data *reply_data) { struct phy_reply_data *rep_data = PHY_REPDATA(reply_data); kfree(rep_data->drvname); kfree(rep_data->name); kfree(rep_data->upstream_sfp_name); kfree(rep_data->downstream_sfp_name); } const struct ethnl_request_ops ethnl_phy_request_ops = { .request_cmd = ETHTOOL_MSG_PHY_GET, .reply_cmd = ETHTOOL_MSG_PHY_GET_REPLY, .hdr_attr = ETHTOOL_A_PHY_HEADER, .req_info_size = sizeof(struct phy_req_info), .reply_data_size = sizeof(struct phy_reply_data), .prepare_data = phy_prepare_data, .reply_size = phy_reply_size, .fill_reply = phy_fill_reply, .cleanup_data = phy_cleanup_data, }; |
| 562 561 561 4 4 4 565 567 559 567 565 566 565 565 564 564 566 562 540 24 562 564 567 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * umh - the kernel usermode helper */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <linux/initrd.h> #include <linux/freezer.h> #include <trace/events/module.h> static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; static DEFINE_SPINLOCK(umh_sysctl_lock); static DECLARE_RWSEM(umhelper_sem); static void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) (*info->cleanup)(info); kfree(info); } static void umh_complete(struct subprocess_info *sub_info) { struct completion *comp = xchg(&sub_info->complete, NULL); /* * See call_usermodehelper_exec(). If xchg() returns NULL * we own sub_info, the UMH_KILLABLE caller has gone away * or the caller used UMH_NO_WAIT. */ if (comp) complete(comp); else call_usermodehelper_freeinfo(sub_info); } /* * This is the task which runs the usermode application */ static int call_usermodehelper_exec_async(void *data) { struct subprocess_info *sub_info = data; struct cred *new; int retval; spin_lock_irq(¤t->sighand->siglock); flush_signal_handlers(current, 1); spin_unlock_irq(¤t->sighand->siglock); /* * Initial kernel threads share ther FS with init, in order to * get the init root directory. But we've now created a new * thread that is going to execve a user process and has its own * 'struct fs_struct'. Reset umask to the default. */ current->fs->umask = 0022; /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ set_user_nice(current, 0); retval = -ENOMEM; new = prepare_kernel_cred(current); if (!new) goto out; spin_lock(&umh_sysctl_lock); new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); new->cap_inheritable = cap_intersect(usermodehelper_inheritable, new->cap_inheritable); spin_unlock(&umh_sysctl_lock); if (sub_info->init) { retval = sub_info->init(sub_info, new); if (retval) { abort_creds(new); goto out; } } commit_creds(new); wait_for_initramfs(); retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); out: sub_info->retval = retval; /* * call_usermodehelper_exec_sync() will call umh_complete * if UHM_WAIT_PROC. */ if (!(sub_info->wait & UMH_WAIT_PROC)) umh_complete(sub_info); if (!retval) return 0; do_exit(0); } /* Handles UMH_WAIT_PROC. */ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info) { pid_t pid; /* If SIGCLD is ignored do_wait won't populate the status. */ kernel_sigaction(SIGCHLD, SIG_DFL); pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD); if (pid < 0) sub_info->retval = pid; else kernel_wait(pid, &sub_info->retval); /* Restore default kernel sig handler */ kernel_sigaction(SIGCHLD, SIG_IGN); umh_complete(sub_info); } /* * We need to create the usermodehelper kernel thread from a task that is affine * to an optimized set of CPUs (or nohz housekeeping ones) such that they * inherit a widest affinity irrespective of call_usermodehelper() callers with * possibly reduced affinity (eg: per-cpu workqueues). We don't want * usermodehelper targets to contend a busy CPU. * * Unbound workqueues provide such wide affinity and allow to block on * UMH_WAIT_PROC requests without blocking pending request (up to some limit). * * Besides, workqueues provide the privilege level that caller might not have * to perform the usermodehelper request. * */ static void call_usermodehelper_exec_work(struct work_struct *work) { struct subprocess_info *sub_info = container_of(work, struct subprocess_info, work); if (sub_info->wait & UMH_WAIT_PROC) { call_usermodehelper_exec_sync(sub_info); } else { pid_t pid; /* * Use CLONE_PARENT to reparent it to kthreadd; we do not * want to pollute current->children, and we need a parent * that always ignores SIGCHLD to ensure auto-reaping. */ pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); } } } /* * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user * land has been frozen during a system-wide hibernation or suspend operation). * Should always be manipulated under umhelper_sem acquired for write. */ static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED; /* Number of helpers running */ static atomic_t running_helpers = ATOMIC_INIT(0); /* * Wait queue head used by usermodehelper_disable() to wait for all running * helpers to finish. */ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq); /* * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled * to become 'false'. */ static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq); /* * Time to wait for running_helpers to become zero before the setting of * usermodehelper_disabled in usermodehelper_disable() fails */ #define RUNNING_HELPERS_TIMEOUT (5 * HZ) int usermodehelper_read_trylock(void) { DEFINE_WAIT(wait); int ret = 0; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_INTERRUPTIBLE); if (!usermodehelper_disabled) break; if (usermodehelper_disabled == UMH_DISABLED) ret = -EAGAIN; up_read(&umhelper_sem); if (ret) break; schedule(); try_to_freeze(); down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return ret; } EXPORT_SYMBOL_GPL(usermodehelper_read_trylock); long usermodehelper_read_lock_wait(long timeout) { DEFINE_WAIT(wait); if (timeout < 0) return -EINVAL; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_UNINTERRUPTIBLE); if (!usermodehelper_disabled) break; up_read(&umhelper_sem); timeout = schedule_timeout(timeout); if (!timeout) break; down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return timeout; } EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait); void usermodehelper_read_unlock(void) { up_read(&umhelper_sem); } EXPORT_SYMBOL_GPL(usermodehelper_read_unlock); /** * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled. * @depth: New value to assign to usermodehelper_disabled. * * Change the value of usermodehelper_disabled (under umhelper_sem locked for * writing) and wakeup tasks waiting for it to change. */ void __usermodehelper_set_disable_depth(enum umh_disable_depth depth) { down_write(&umhelper_sem); usermodehelper_disabled = depth; wake_up(&usermodehelper_disabled_waitq); up_write(&umhelper_sem); } /** * __usermodehelper_disable - Prevent new helpers from being started. * @depth: New value to assign to usermodehelper_disabled. * * Set usermodehelper_disabled to @depth and wait for running helpers to exit. */ int __usermodehelper_disable(enum umh_disable_depth depth) { long retval; if (!depth) return -EINVAL; down_write(&umhelper_sem); usermodehelper_disabled = depth; up_write(&umhelper_sem); /* * From now on call_usermodehelper_exec() won't start any new * helpers, so it is sufficient if running_helpers turns out to * be zero at one point (it may be increased later, but that * doesn't matter). */ retval = wait_event_timeout(running_helpers_waitq, atomic_read(&running_helpers) == 0, RUNNING_HELPERS_TIMEOUT); if (retval) return 0; __usermodehelper_set_disable_depth(UMH_ENABLED); return -EAGAIN; } static void helper_lock(void) { atomic_inc(&running_helpers); smp_mb__after_atomic(); } static void helper_unlock(void) { if (atomic_dec_and_test(&running_helpers)) wake_up(&running_helpers_waitq); } /** * call_usermodehelper_setup - prepare to call a usermode helper * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @gfp_mask: gfp mask for memory allocation * @init: an init function * @cleanup: a cleanup function * @data: arbitrary context sensitive data * * Returns either %NULL on allocation failure, or a subprocess_info * structure. This should be passed to call_usermodehelper_exec to * exec the process and free the structure. * * The init function is used to customize the helper process prior to * exec. A non-zero return code causes the process to error out, exit, * and return the failure to the calling process * * The cleanup function is just before the subprocess_info is about to * be freed. This can be used for freeing the argv and envp. The * Function must be runnable in either a process context or the * context in which call_usermodehelper_exec is called. */ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv, char **envp, gfp_t gfp_mask, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *info), void *data) { struct subprocess_info *sub_info; sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask); if (!sub_info) goto out; INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); #ifdef CONFIG_STATIC_USERMODEHELPER sub_info->path = CONFIG_STATIC_USERMODEHELPER_PATH; #else sub_info->path = path; #endif sub_info->argv = argv; sub_info->envp = envp; sub_info->cleanup = cleanup; sub_info->init = init; sub_info->data = data; out: return sub_info; } EXPORT_SYMBOL(call_usermodehelper_setup); /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocess * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). * * Note: successful return value does not guarantee the helper was called at * all. You can't rely on sub_info->{init,cleanup} being called even for * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { unsigned int state = TASK_UNINTERRUPTIBLE; DECLARE_COMPLETION_ONSTACK(done); int retval = 0; if (!sub_info->path) { call_usermodehelper_freeinfo(sub_info); return -EINVAL; } helper_lock(); if (usermodehelper_disabled) { retval = -EBUSY; goto out; } /* * If there is no binary for us to call, then just return and get out of * here. This allows us to set STATIC_USERMODEHELPER_PATH to "" and * disable all call_usermodehelper() calls. */ if (strlen(sub_info->path) == 0) goto out; /* * Set the completion pointer only if there is a waiter. * This makes it possible to use umh_complete to free * the data structure in case of UMH_NO_WAIT. */ sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done; sub_info->wait = wait; queue_work(system_unbound_wq, &sub_info->work); if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; if (wait & UMH_KILLABLE) { retval = wait_for_completion_state(&done, state | TASK_KILLABLE); if (!retval) goto wait_done; /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; /* * fallthrough; in case of -ERESTARTSYS now do uninterruptible * wait_for_completion_state(). Since umh_complete() shall call * complete() in a moment if xchg() above returned NULL, this * uninterruptible wait_for_completion_state() will not block * SIGKILL'ed processes for long. */ } wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; out: call_usermodehelper_freeinfo(sub_info); unlock: helper_unlock(); return retval; } EXPORT_SYMBOL(call_usermodehelper_exec); /** * call_usermodehelper() - prepare and start a usermode application * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * This function is the equivalent to use call_usermodehelper_setup() and * call_usermodehelper_exec(). */ int call_usermodehelper(const char *path, char **argv, char **envp, int wait) { struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; info = call_usermodehelper_setup(path, argv, envp, gfp_mask, NULL, NULL, NULL); if (info == NULL) return -ENOMEM; return call_usermodehelper_exec(info, wait); } EXPORT_SYMBOL(call_usermodehelper); #if defined(CONFIG_SYSCTL) static int proc_cap_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; unsigned long cap_array[2]; kernel_cap_t new_cap, *cap; int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) return -EPERM; /* * convert from the global kernel_cap_t to the ulong array to print to * userspace if this is a read. * * Legacy format: capabilities are exposed as two 32-bit values */ cap = table->data; spin_lock(&umh_sysctl_lock); cap_array[0] = (u32) cap->val; cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; t.data = &cap_array; /* * actually read or write and array of ulongs from userspace. Remember * these are least significant 32 bits first */ err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; new_cap.val = (u32)cap_array[0]; new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } return 0; } static const struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", .data = &usermodehelper_inheritable, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, }; static int __init init_umh_sysctls(void) { register_sysctl_init("kernel/usermodehelper", usermodehelper_table); return 0; } early_initcall(init_umh_sysctls); #endif /* CONFIG_SYSCTL */ |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 | // SPDX-License-Identifier: GPL-2.0-only /* * misc.c * * PURPOSE * Miscellaneous routines for the OSTA-UDF(tm) filesystem. * * COPYRIGHT * (C) 1998 Dave Boynton * (C) 1998-2004 Ben Fennema * (C) 1999-2000 Stelias Computing Inc * * HISTORY * * 04/19/99 blf partial support for reading/writing specific EA's */ #include "udfdecl.h" #include <linux/fs.h> #include <linux/string.h> #include <linux/crc-itu-t.h> #include "udf_i.h" #include "udf_sb.h" struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size, uint32_t type, uint8_t loc) { uint8_t *ea = NULL, *ad = NULL; int offset; uint16_t crclen; struct udf_inode_info *iinfo = UDF_I(inode); ea = iinfo->i_data; if (iinfo->i_lenEAttr) { ad = iinfo->i_data + iinfo->i_lenEAttr; } else { ad = ea; size += sizeof(struct extendedAttrHeaderDesc); } offset = inode->i_sb->s_blocksize - udf_file_entry_alloc_offset(inode) - iinfo->i_lenAlloc; /* TODO - Check for FreeEASpace */ if (loc & 0x01 && offset >= size) { struct extendedAttrHeaderDesc *eahd; eahd = (struct extendedAttrHeaderDesc *)ea; if (iinfo->i_lenAlloc) memmove(&ad[size], ad, iinfo->i_lenAlloc); if (iinfo->i_lenEAttr) { /* check checksum/crc */ if (eahd->descTag.tagIdent != cpu_to_le16(TAG_IDENT_EAHD) || le32_to_cpu(eahd->descTag.tagLocation) != iinfo->i_location.logicalBlockNum) return NULL; } else { struct udf_sb_info *sbi = UDF_SB(inode->i_sb); size -= sizeof(struct extendedAttrHeaderDesc); iinfo->i_lenEAttr += sizeof(struct extendedAttrHeaderDesc); eahd->descTag.tagIdent = cpu_to_le16(TAG_IDENT_EAHD); if (sbi->s_udfrev >= 0x0200) eahd->descTag.descVersion = cpu_to_le16(3); else eahd->descTag.descVersion = cpu_to_le16(2); eahd->descTag.tagSerialNum = cpu_to_le16(sbi->s_serial_number); eahd->descTag.tagLocation = cpu_to_le32( iinfo->i_location.logicalBlockNum); eahd->impAttrLocation = cpu_to_le32(0xFFFFFFFF); eahd->appAttrLocation = cpu_to_le32(0xFFFFFFFF); } offset = iinfo->i_lenEAttr; if (type < 2048) { if (le32_to_cpu(eahd->appAttrLocation) < iinfo->i_lenEAttr) { uint32_t aal = le32_to_cpu(eahd->appAttrLocation); memmove(&ea[offset - aal + size], &ea[aal], offset - aal); offset -= aal; eahd->appAttrLocation = cpu_to_le32(aal + size); } if (le32_to_cpu(eahd->impAttrLocation) < iinfo->i_lenEAttr) { uint32_t ial = le32_to_cpu(eahd->impAttrLocation); memmove(&ea[offset - ial + size], &ea[ial], offset - ial); offset -= ial; eahd->impAttrLocation = cpu_to_le32(ial + size); } } else if (type < 65536) { if (le32_to_cpu(eahd->appAttrLocation) < iinfo->i_lenEAttr) { uint32_t aal = le32_to_cpu(eahd->appAttrLocation); memmove(&ea[offset - aal + size], &ea[aal], offset - aal); offset -= aal; eahd->appAttrLocation = cpu_to_le32(aal + size); } } /* rewrite CRC + checksum of eahd */ crclen = sizeof(struct extendedAttrHeaderDesc) - sizeof(struct tag); eahd->descTag.descCRCLength = cpu_to_le16(crclen); eahd->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)eahd + sizeof(struct tag), crclen)); eahd->descTag.tagChecksum = udf_tag_checksum(&eahd->descTag); iinfo->i_lenEAttr += size; return (struct genericFormat *)&ea[offset]; } return NULL; } struct genericFormat *udf_get_extendedattr(struct inode *inode, uint32_t type, uint8_t subtype) { struct genericFormat *gaf; uint8_t *ea = NULL; uint32_t offset; struct udf_inode_info *iinfo = UDF_I(inode); ea = iinfo->i_data; if (iinfo->i_lenEAttr) { struct extendedAttrHeaderDesc *eahd; eahd = (struct extendedAttrHeaderDesc *)ea; /* check checksum/crc */ if (eahd->descTag.tagIdent != cpu_to_le16(TAG_IDENT_EAHD) || le32_to_cpu(eahd->descTag.tagLocation) != iinfo->i_location.logicalBlockNum) return NULL; if (type < 2048) offset = sizeof(struct extendedAttrHeaderDesc); else if (type < 65536) offset = le32_to_cpu(eahd->impAttrLocation); else offset = le32_to_cpu(eahd->appAttrLocation); while (offset + sizeof(*gaf) < iinfo->i_lenEAttr) { uint32_t attrLength; gaf = (struct genericFormat *)&ea[offset]; attrLength = le32_to_cpu(gaf->attrLength); /* Detect undersized elements and buffer overflows */ if ((attrLength < sizeof(*gaf)) || (attrLength > (iinfo->i_lenEAttr - offset))) break; if (le32_to_cpu(gaf->attrType) == type && gaf->attrSubtype == subtype) return gaf; else offset += attrLength; } } return NULL; } /* * udf_read_tagged * * PURPOSE * Read the first block of a tagged descriptor. * * HISTORY * July 1, 1997 - Andrew E. Mileski * Written, tested, and released. */ struct buffer_head *udf_read_tagged(struct super_block *sb, uint32_t block, uint32_t location, uint16_t *ident) { struct tag *tag_p; struct buffer_head *bh = NULL; u8 checksum; /* Read the block */ if (block == 0xFFFFFFFF) return NULL; bh = sb_bread(sb, block); if (!bh) { udf_err(sb, "read failed, block=%u, location=%u\n", block, location); return NULL; } tag_p = (struct tag *)(bh->b_data); *ident = le16_to_cpu(tag_p->tagIdent); if (location != le32_to_cpu(tag_p->tagLocation)) { udf_debug("location mismatch block %u, tag %u != %u\n", block, le32_to_cpu(tag_p->tagLocation), location); goto error_out; } /* Verify the tag checksum */ checksum = udf_tag_checksum(tag_p); if (checksum != tag_p->tagChecksum) { udf_err(sb, "tag checksum failed, block %u: 0x%02x != 0x%02x\n", block, checksum, tag_p->tagChecksum); goto error_out; } /* Verify the tag version */ if (tag_p->descVersion != cpu_to_le16(0x0002U) && tag_p->descVersion != cpu_to_le16(0x0003U)) { udf_err(sb, "tag version 0x%04x != 0x0002 || 0x0003, block %u\n", le16_to_cpu(tag_p->descVersion), block); goto error_out; } /* Verify the descriptor CRC */ if (le16_to_cpu(tag_p->descCRCLength) + sizeof(struct tag) > sb->s_blocksize || le16_to_cpu(tag_p->descCRC) == crc_itu_t(0, bh->b_data + sizeof(struct tag), le16_to_cpu(tag_p->descCRCLength))) return bh; udf_debug("Crc failure block %u: crc = %u, crclen = %u\n", block, le16_to_cpu(tag_p->descCRC), le16_to_cpu(tag_p->descCRCLength)); error_out: brelse(bh); return NULL; } struct buffer_head *udf_read_ptagged(struct super_block *sb, struct kernel_lb_addr *loc, uint32_t offset, uint16_t *ident) { return udf_read_tagged(sb, udf_get_lb_pblock(sb, loc, offset), loc->logicalBlockNum + offset, ident); } void udf_update_tag(char *data, int length) { struct tag *tptr = (struct tag *)data; length -= sizeof(struct tag); tptr->descCRCLength = cpu_to_le16(length); tptr->descCRC = cpu_to_le16(crc_itu_t(0, data + sizeof(struct tag), length)); tptr->tagChecksum = udf_tag_checksum(tptr); } void udf_new_tag(char *data, uint16_t ident, uint16_t version, uint16_t snum, uint32_t loc, int length) { struct tag *tptr = (struct tag *)data; tptr->tagIdent = cpu_to_le16(ident); tptr->descVersion = cpu_to_le16(version); tptr->tagSerialNum = cpu_to_le16(snum); tptr->tagLocation = cpu_to_le32(loc); udf_update_tag(data, length); } u8 udf_tag_checksum(const struct tag *t) { u8 *data = (u8 *)t; u8 checksum = 0; int i; for (i = 0; i < sizeof(struct tag); ++i) if (i != 4) /* position of checksum */ checksum += data[i]; return checksum; } |
| 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 12 12 12 12 4 2 2 2 1 1 1 1 2 2 1 1 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 1 1 1 1 1 1 1 1 10 10 10 10 43 6 1 6 5 2 20 19 18 6 1 18 6 1 18 3 1 18 3 3 3 1 20 2 2 1 2 1 2 2 14 13 4 4 13 12 12 11 11 11 2 1 10 6 10 4 10 1 10 10 10 10 10 9 10 10 10 10 10 10 3 2 2 2 2 2 1 9 9 9 7 9 9 1 1 1 1 1 1 10 11 27 7 2 2 7 2 2 12 37 25 36 3 3 4 1 4 2 4 1 3 4 4 4 4 4 4 4 4 4 4 4 14 14 14 14 14 9 8 7 7 9 7 7 7 17 1 17 3 17 17 17 17 17 12 10 10 10 10 10 12 7 7 8 9 7 7 9 2 2 2 1 1 1 2 1 9 2 1 1 1 1 2 2 1 2 1 1 2 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2003 Patrick McHardy, <kaber@trash.net> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version 2 * of the License, or (at your option) any later version. * * 2003-10-17 - Ported from altq */ /* * Copyright (c) 1997-1999 Carnegie Mellon University. All Rights Reserved. * * Permission to use, copy, modify, and distribute this software and * its documentation is hereby granted (including for commercial or * for-profit use), provided that both the copyright notice and this * permission notice appear in all copies of the software, derivative * works, or modified versions, and any portions thereof. * * THIS SOFTWARE IS EXPERIMENTAL AND IS KNOWN TO HAVE BUGS, SOME OF * WHICH MAY HAVE SERIOUS CONSEQUENCES. CARNEGIE MELLON PROVIDES THIS * SOFTWARE IN ITS ``AS IS'' CONDITION, 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 CARNEGIE MELLON UNIVERSITY 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. * * Carnegie Mellon encourages (but does not require) users of this * software to return any improvements or extensions that they make, * and to grant Carnegie Mellon the rights to redistribute these * changes without encumbrance. */ /* * H-FSC is described in Proceedings of SIGCOMM'97, * "A Hierarchical Fair Service Curve Algorithm for Link-Sharing, * Real-Time and Priority Service" * by Ion Stoica, Hui Zhang, and T. S. Eugene Ng. * * Oleg Cherevko <olwi@aq.ml.com.ua> added the upperlimit for link-sharing. * when a class has an upperlimit, the fit-time is computed from the * upperlimit service curve. the link-sharing scheduler does not schedule * a class whose fit-time exceeds the current time. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <asm/div64.h> /* * kernel internal service curve representation: * coordinates are given by 64 bit unsigned integers. * x-axis: unit is clock count. * y-axis: unit is byte. * * The service curve parameters are converted to the internal * representation. The slope values are scaled to avoid overflow. * the inverse slope values as well as the y-projection of the 1st * segment are kept in order to avoid 64-bit divide operations * that are expensive on 32-bit architectures. */ struct internal_sc { u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ u64 dy; /* the y-projection of the 1st segment */ u64 sm2; /* scaled slope of the 2nd segment */ u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; /* runtime service curve */ struct runtime_sc { u64 x; /* current starting position on x-axis */ u64 y; /* current starting position on y-axis */ u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ u64 dy; /* the y-projection of the 1st segment */ u64 sm2; /* scaled slope of the 2nd segment */ u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; enum hfsc_class_flags { HFSC_RSC = 0x1, HFSC_FSC = 0x2, HFSC_USC = 0x4 }; struct hfsc_class { struct Qdisc_class_common cl_common; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ struct tcf_block *block; unsigned int level; /* class level in hierarchy */ struct hfsc_sched *sched; /* scheduler data */ struct hfsc_class *cl_parent; /* parent class */ struct list_head siblings; /* sibling classes */ struct list_head children; /* child classes */ struct Qdisc *qdisc; /* leaf qdisc */ struct rb_node el_node; /* qdisc's eligible tree member */ struct rb_root vt_tree; /* active children sorted by cl_vt */ struct rb_node vt_node; /* parent's vt_tree member */ struct rb_root cf_tree; /* active children sorted by cl_f */ struct rb_node cf_node; /* parent's cf_heap member */ u64 cl_total; /* total work in bytes */ u64 cl_cumul; /* cumulative work in bytes done by real-time criteria */ u64 cl_d; /* deadline*/ u64 cl_e; /* eligible time */ u64 cl_vt; /* virtual time */ u64 cl_f; /* time when this class will fit for link-sharing, max(myf, cfmin) */ u64 cl_myf; /* my fit-time (calculated from this class's own upperlimit curve) */ u64 cl_cfmin; /* earliest children's fit-time (used with cl_myf to obtain cl_f) */ u64 cl_cvtmin; /* minimal virtual time among the children fit for link-sharing (monotonic within a period) */ u64 cl_vtadj; /* intra-period cumulative vt adjustment */ u64 cl_cvtoff; /* largest virtual time seen among the children */ struct internal_sc cl_rsc; /* internal real-time service curve */ struct internal_sc cl_fsc; /* internal fair service curve */ struct internal_sc cl_usc; /* internal upperlimit service curve */ struct runtime_sc cl_deadline; /* deadline curve */ struct runtime_sc cl_eligible; /* eligible curve */ struct runtime_sc cl_virtual; /* virtual curve */ struct runtime_sc cl_ulimit; /* upperlimit curve */ u8 cl_flags; /* which curves are valid */ u32 cl_vtperiod; /* vt period sequence number */ u32 cl_parentperiod;/* parent's vt period sequence number*/ u32 cl_nactive; /* number of active children */ }; struct hfsc_sched { u16 defcls; /* default class id */ struct hfsc_class root; /* root class */ struct Qdisc_class_hash clhash; /* class hash */ struct rb_root eligible; /* eligible tree */ struct qdisc_watchdog watchdog; /* watchdog timer */ }; #define HT_INFINITY 0xffffffffffffffffULL /* infinite time value */ static bool cl_in_el_or_vttree(struct hfsc_class *cl) { return ((cl->cl_flags & HFSC_FSC) && cl->cl_nactive) || ((cl->cl_flags & HFSC_RSC) && !RB_EMPTY_NODE(&cl->el_node)); } /* * eligible tree holds backlogged classes being sorted by their eligible times. * there is one eligible tree per hfsc instance. */ static void eltree_insert(struct hfsc_class *cl) { struct rb_node **p = &cl->sched->eligible.rb_node; struct rb_node *parent = NULL; struct hfsc_class *cl1; while (*p != NULL) { parent = *p; cl1 = rb_entry(parent, struct hfsc_class, el_node); if (cl->cl_e >= cl1->cl_e) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&cl->el_node, parent, p); rb_insert_color(&cl->el_node, &cl->sched->eligible); } static inline void eltree_remove(struct hfsc_class *cl) { if (!RB_EMPTY_NODE(&cl->el_node)) { rb_erase(&cl->el_node, &cl->sched->eligible); RB_CLEAR_NODE(&cl->el_node); } } static inline void eltree_update(struct hfsc_class *cl) { eltree_remove(cl); eltree_insert(cl); } /* find the class with the minimum deadline among the eligible classes */ static inline struct hfsc_class * eltree_get_mindl(struct hfsc_sched *q, u64 cur_time) { struct hfsc_class *p, *cl = NULL; struct rb_node *n; for (n = rb_first(&q->eligible); n != NULL; n = rb_next(n)) { p = rb_entry(n, struct hfsc_class, el_node); if (p->cl_e > cur_time) break; if (cl == NULL || p->cl_d < cl->cl_d) cl = p; } return cl; } /* find the class with minimum eligible time among the eligible classes */ static inline struct hfsc_class * eltree_get_minel(struct hfsc_sched *q) { struct rb_node *n; n = rb_first(&q->eligible); if (n == NULL) return NULL; return rb_entry(n, struct hfsc_class, el_node); } /* * vttree holds holds backlogged child classes being sorted by their virtual * time. each intermediate class has one vttree. */ static void vttree_insert(struct hfsc_class *cl) { struct rb_node **p = &cl->cl_parent->vt_tree.rb_node; struct rb_node *parent = NULL; struct hfsc_class *cl1; while (*p != NULL) { parent = *p; cl1 = rb_entry(parent, struct hfsc_class, vt_node); if (cl->cl_vt >= cl1->cl_vt) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&cl->vt_node, parent, p); rb_insert_color(&cl->vt_node, &cl->cl_parent->vt_tree); } static inline void vttree_remove(struct hfsc_class *cl) { rb_erase(&cl->vt_node, &cl->cl_parent->vt_tree); } static inline void vttree_update(struct hfsc_class *cl) { vttree_remove(cl); vttree_insert(cl); } static inline struct hfsc_class * vttree_firstfit(struct hfsc_class *cl, u64 cur_time) { struct hfsc_class *p; struct rb_node *n; for (n = rb_first(&cl->vt_tree); n != NULL; n = rb_next(n)) { p = rb_entry(n, struct hfsc_class, vt_node); if (p->cl_f <= cur_time) return p; } return NULL; } /* * get the leaf class with the minimum vt in the hierarchy */ static struct hfsc_class * vttree_get_minvt(struct hfsc_class *cl, u64 cur_time) { /* if root-class's cfmin is bigger than cur_time nothing to do */ if (cl->cl_cfmin > cur_time) return NULL; while (cl->level > 0) { cl = vttree_firstfit(cl, cur_time); if (cl == NULL) return NULL; /* * update parent's cl_cvtmin. */ if (cl->cl_parent->cl_cvtmin < cl->cl_vt) cl->cl_parent->cl_cvtmin = cl->cl_vt; } return cl; } static void cftree_insert(struct hfsc_class *cl) { struct rb_node **p = &cl->cl_parent->cf_tree.rb_node; struct rb_node *parent = NULL; struct hfsc_class *cl1; while (*p != NULL) { parent = *p; cl1 = rb_entry(parent, struct hfsc_class, cf_node); if (cl->cl_f >= cl1->cl_f) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&cl->cf_node, parent, p); rb_insert_color(&cl->cf_node, &cl->cl_parent->cf_tree); } static inline void cftree_remove(struct hfsc_class *cl) { rb_erase(&cl->cf_node, &cl->cl_parent->cf_tree); } static inline void cftree_update(struct hfsc_class *cl) { cftree_remove(cl); cftree_insert(cl); } /* * service curve support functions * * external service curve parameters * m: bps * d: us * internal service curve parameters * sm: (bytes/psched_us) << SM_SHIFT * ism: (psched_us/byte) << ISM_SHIFT * dx: psched_us * * The clock source resolution with ktime and PSCHED_SHIFT 10 is 1.024us. * * sm and ism are scaled in order to keep effective digits. * SM_SHIFT and ISM_SHIFT are selected to keep at least 4 effective * digits in decimal using the following table. * * bits/sec 100Kbps 1Mbps 10Mbps 100Mbps 1Gbps * ------------+------------------------------------------------------- * bytes/1.024us 12.8e-3 128e-3 1280e-3 12800e-3 128000e-3 * * 1.024us/byte 78.125 7.8125 0.78125 0.078125 0.0078125 * * So, for PSCHED_SHIFT 10 we need: SM_SHIFT 20, ISM_SHIFT 18. */ #define SM_SHIFT (30 - PSCHED_SHIFT) #define ISM_SHIFT (8 + PSCHED_SHIFT) #define SM_MASK ((1ULL << SM_SHIFT) - 1) #define ISM_MASK ((1ULL << ISM_SHIFT) - 1) static inline u64 seg_x2y(u64 x, u64 sm) { u64 y; /* * compute * y = x * sm >> SM_SHIFT * but divide it for the upper and lower bits to avoid overflow */ y = (x >> SM_SHIFT) * sm + (((x & SM_MASK) * sm) >> SM_SHIFT); return y; } static inline u64 seg_y2x(u64 y, u64 ism) { u64 x; if (y == 0) x = 0; else if (ism == HT_INFINITY) x = HT_INFINITY; else { x = (y >> ISM_SHIFT) * ism + (((y & ISM_MASK) * ism) >> ISM_SHIFT); } return x; } /* Convert m (bps) into sm (bytes/psched us) */ static u64 m2sm(u32 m) { u64 sm; sm = ((u64)m << SM_SHIFT); sm += PSCHED_TICKS_PER_SEC - 1; do_div(sm, PSCHED_TICKS_PER_SEC); return sm; } /* convert m (bps) into ism (psched us/byte) */ static u64 m2ism(u32 m) { u64 ism; if (m == 0) ism = HT_INFINITY; else { ism = ((u64)PSCHED_TICKS_PER_SEC << ISM_SHIFT); ism += m - 1; do_div(ism, m); } return ism; } /* convert d (us) into dx (psched us) */ static u64 d2dx(u32 d) { u64 dx; dx = ((u64)d * PSCHED_TICKS_PER_SEC); dx += USEC_PER_SEC - 1; do_div(dx, USEC_PER_SEC); return dx; } /* convert sm (bytes/psched us) into m (bps) */ static u32 sm2m(u64 sm) { u64 m; m = (sm * PSCHED_TICKS_PER_SEC) >> SM_SHIFT; return (u32)m; } /* convert dx (psched us) into d (us) */ static u32 dx2d(u64 dx) { u64 d; d = dx * USEC_PER_SEC; do_div(d, PSCHED_TICKS_PER_SEC); return (u32)d; } static void sc2isc(struct tc_service_curve *sc, struct internal_sc *isc) { isc->sm1 = m2sm(sc->m1); isc->ism1 = m2ism(sc->m1); isc->dx = d2dx(sc->d); isc->dy = seg_x2y(isc->dx, isc->sm1); isc->sm2 = m2sm(sc->m2); isc->ism2 = m2ism(sc->m2); } /* * initialize the runtime service curve with the given internal * service curve starting at (x, y). */ static void rtsc_init(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y) { rtsc->x = x; rtsc->y = y; rtsc->sm1 = isc->sm1; rtsc->ism1 = isc->ism1; rtsc->dx = isc->dx; rtsc->dy = isc->dy; rtsc->sm2 = isc->sm2; rtsc->ism2 = isc->ism2; } /* * calculate the y-projection of the runtime service curve by the * given x-projection value */ static u64 rtsc_y2x(struct runtime_sc *rtsc, u64 y) { u64 x; if (y < rtsc->y) x = rtsc->x; else if (y <= rtsc->y + rtsc->dy) { /* x belongs to the 1st segment */ if (rtsc->dy == 0) x = rtsc->x + rtsc->dx; else x = rtsc->x + seg_y2x(y - rtsc->y, rtsc->ism1); } else { /* x belongs to the 2nd segment */ x = rtsc->x + rtsc->dx + seg_y2x(y - rtsc->y - rtsc->dy, rtsc->ism2); } return x; } static u64 rtsc_x2y(struct runtime_sc *rtsc, u64 x) { u64 y; if (x <= rtsc->x) y = rtsc->y; else if (x <= rtsc->x + rtsc->dx) /* y belongs to the 1st segment */ y = rtsc->y + seg_x2y(x - rtsc->x, rtsc->sm1); else /* y belongs to the 2nd segment */ y = rtsc->y + rtsc->dy + seg_x2y(x - rtsc->x - rtsc->dx, rtsc->sm2); return y; } /* * update the runtime service curve by taking the minimum of the current * runtime service curve and the service curve starting at (x, y). */ static void rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y) { u64 y1, y2, dx, dy; u32 dsm; if (isc->sm1 <= isc->sm2) { /* service curve is convex */ y1 = rtsc_x2y(rtsc, x); if (y1 < y) /* the current rtsc is smaller */ return; rtsc->x = x; rtsc->y = y; return; } /* * service curve is concave * compute the two y values of the current rtsc * y1: at x * y2: at (x + dx) */ y1 = rtsc_x2y(rtsc, x); if (y1 <= y) { /* rtsc is below isc, no change to rtsc */ return; } y2 = rtsc_x2y(rtsc, x + isc->dx); if (y2 >= y + isc->dy) { /* rtsc is above isc, replace rtsc by isc */ rtsc->x = x; rtsc->y = y; rtsc->dx = isc->dx; rtsc->dy = isc->dy; return; } /* * the two curves intersect * compute the offsets (dx, dy) using the reverse * function of seg_x2y() * seg_x2y(dx, sm1) == seg_x2y(dx, sm2) + (y1 - y) */ dx = (y1 - y) << SM_SHIFT; dsm = isc->sm1 - isc->sm2; do_div(dx, dsm); /* * check if (x, y1) belongs to the 1st segment of rtsc. * if so, add the offset. */ if (rtsc->x + rtsc->dx > x) dx += rtsc->x + rtsc->dx - x; dy = seg_x2y(dx, isc->sm1); rtsc->x = x; rtsc->y = y; rtsc->dx = dx; rtsc->dy = dy; } static void init_ed(struct hfsc_class *cl, unsigned int next_len) { u64 cur_time = psched_get_time(); /* update the deadline curve */ rtsc_min(&cl->cl_deadline, &cl->cl_rsc, cur_time, cl->cl_cumul); /* * update the eligible curve. * for concave, it is equal to the deadline curve. * for convex, it is a linear curve with slope m2. */ cl->cl_eligible = cl->cl_deadline; if (cl->cl_rsc.sm1 <= cl->cl_rsc.sm2) { cl->cl_eligible.dx = 0; cl->cl_eligible.dy = 0; } /* compute e and d */ cl->cl_e = rtsc_y2x(&cl->cl_eligible, cl->cl_cumul); cl->cl_d = rtsc_y2x(&cl->cl_deadline, cl->cl_cumul + next_len); eltree_insert(cl); } static void update_ed(struct hfsc_class *cl, unsigned int next_len) { cl->cl_e = rtsc_y2x(&cl->cl_eligible, cl->cl_cumul); cl->cl_d = rtsc_y2x(&cl->cl_deadline, cl->cl_cumul + next_len); eltree_update(cl); } static inline void update_d(struct hfsc_class *cl, unsigned int next_len) { cl->cl_d = rtsc_y2x(&cl->cl_deadline, cl->cl_cumul + next_len); } static inline void update_cfmin(struct hfsc_class *cl) { struct rb_node *n = rb_first(&cl->cf_tree); struct hfsc_class *p; if (n == NULL) { cl->cl_cfmin = 0; return; } p = rb_entry(n, struct hfsc_class, cf_node); cl->cl_cfmin = p->cl_f; } static void init_vf(struct hfsc_class *cl, unsigned int len) { struct hfsc_class *max_cl; struct rb_node *n; u64 vt, f, cur_time; int go_active; cur_time = 0; go_active = 1; for (; cl->cl_parent != NULL; cl = cl->cl_parent) { if (go_active && cl->cl_nactive++ == 0) go_active = 1; else go_active = 0; if (go_active) { n = rb_last(&cl->cl_parent->vt_tree); if (n != NULL) { max_cl = rb_entry(n, struct hfsc_class, vt_node); /* * set vt to the average of the min and max * classes. if the parent's period didn't * change, don't decrease vt of the class. */ vt = max_cl->cl_vt; if (cl->cl_parent->cl_cvtmin != 0) vt = (cl->cl_parent->cl_cvtmin + vt)/2; if (cl->cl_parent->cl_vtperiod != cl->cl_parentperiod || vt > cl->cl_vt) cl->cl_vt = vt; } else { /* * first child for a new parent backlog period. * initialize cl_vt to the highest value seen * among the siblings. this is analogous to * what cur_time would provide in realtime case. */ cl->cl_vt = cl->cl_parent->cl_cvtoff; cl->cl_parent->cl_cvtmin = 0; } /* update the virtual curve */ rtsc_min(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); cl->cl_vtadj = 0; cl->cl_vtperiod++; /* increment vt period */ cl->cl_parentperiod = cl->cl_parent->cl_vtperiod; if (cl->cl_parent->cl_nactive == 0) cl->cl_parentperiod++; cl->cl_f = 0; vttree_insert(cl); cftree_insert(cl); if (cl->cl_flags & HFSC_USC) { /* class has upper limit curve */ if (cur_time == 0) cur_time = psched_get_time(); /* update the ulimit curve */ rtsc_min(&cl->cl_ulimit, &cl->cl_usc, cur_time, cl->cl_total); /* compute myf */ cl->cl_myf = rtsc_y2x(&cl->cl_ulimit, cl->cl_total); } } f = max(cl->cl_myf, cl->cl_cfmin); if (f != cl->cl_f) { cl->cl_f = f; cftree_update(cl); } update_cfmin(cl->cl_parent); } } static void update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time) { u64 f; /* , myf_bound, delta; */ int go_passive = 0; if (cl->qdisc->q.qlen == 0 && cl->cl_flags & HFSC_FSC) go_passive = 1; for (; cl->cl_parent != NULL; cl = cl->cl_parent) { cl->cl_total += len; if (!(cl->cl_flags & HFSC_FSC) || cl->cl_nactive == 0) continue; if (go_passive && --cl->cl_nactive == 0) go_passive = 1; else go_passive = 0; /* update vt */ cl->cl_vt = rtsc_y2x(&cl->cl_virtual, cl->cl_total) + cl->cl_vtadj; /* * if vt of the class is smaller than cvtmin, * the class was skipped in the past due to non-fit. * if so, we need to adjust vtadj. */ if (cl->cl_vt < cl->cl_parent->cl_cvtmin) { cl->cl_vtadj += cl->cl_parent->cl_cvtmin - cl->cl_vt; cl->cl_vt = cl->cl_parent->cl_cvtmin; } if (go_passive) { /* no more active child, going passive */ /* update cvtoff of the parent class */ if (cl->cl_vt > cl->cl_parent->cl_cvtoff) cl->cl_parent->cl_cvtoff = cl->cl_vt; /* remove this class from the vt tree */ vttree_remove(cl); cftree_remove(cl); update_cfmin(cl->cl_parent); continue; } /* update the vt tree */ vttree_update(cl); /* update f */ if (cl->cl_flags & HFSC_USC) { cl->cl_myf = rtsc_y2x(&cl->cl_ulimit, cl->cl_total); #if 0 cl->cl_myf = cl->cl_myfadj + rtsc_y2x(&cl->cl_ulimit, cl->cl_total); /* * This code causes classes to stay way under their * limit when multiple classes are used at gigabit * speed. needs investigation. -kaber */ /* * if myf lags behind by more than one clock tick * from the current time, adjust myfadj to prevent * a rate-limited class from going greedy. * in a steady state under rate-limiting, myf * fluctuates within one clock tick. */ myf_bound = cur_time - PSCHED_JIFFIE2US(1); if (cl->cl_myf < myf_bound) { delta = cur_time - cl->cl_myf; cl->cl_myfadj += delta; cl->cl_myf += delta; } #endif } f = max(cl->cl_myf, cl->cl_cfmin); if (f != cl->cl_f) { cl->cl_f = f; cftree_update(cl); update_cfmin(cl->cl_parent); } } } static void hfsc_adjust_levels(struct hfsc_class *cl) { struct hfsc_class *p; unsigned int level; do { level = 0; list_for_each_entry(p, &cl->children, siblings) { if (p->level >= level) level = p->level + 1; } cl->level = level; } while ((cl = cl->cl_parent) != NULL); } static inline struct hfsc_class * hfsc_find_class(u32 classid, struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct Qdisc_class_common *clc; clc = qdisc_class_find(&q->clhash, classid); if (clc == NULL) return NULL; return container_of(clc, struct hfsc_class, cl_common); } static void hfsc_change_rsc(struct hfsc_class *cl, struct tc_service_curve *rsc, u64 cur_time) { sc2isc(rsc, &cl->cl_rsc); rtsc_init(&cl->cl_deadline, &cl->cl_rsc, cur_time, cl->cl_cumul); cl->cl_eligible = cl->cl_deadline; if (cl->cl_rsc.sm1 <= cl->cl_rsc.sm2) { cl->cl_eligible.dx = 0; cl->cl_eligible.dy = 0; } cl->cl_flags |= HFSC_RSC; } static void hfsc_change_fsc(struct hfsc_class *cl, struct tc_service_curve *fsc) { sc2isc(fsc, &cl->cl_fsc); rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); cl->cl_flags |= HFSC_FSC; } static void hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, u64 cur_time) { sc2isc(usc, &cl->cl_usc); rtsc_init(&cl->cl_ulimit, &cl->cl_usc, cur_time, cl->cl_total); cl->cl_flags |= HFSC_USC; } static void hfsc_upgrade_rt(struct hfsc_class *cl) { cl->cl_fsc = cl->cl_rsc; rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); cl->cl_flags |= HFSC_FSC; } static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_USC] = { .len = sizeof(struct tc_service_curve) }, }; static int hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)*arg; struct hfsc_class *parent = NULL; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HFSC_MAX + 1]; struct tc_service_curve *rsc = NULL, *fsc = NULL, *usc = NULL; u64 cur_time; int err; if (opt == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_HFSC_MAX, opt, hfsc_policy, NULL); if (err < 0) return err; if (tb[TCA_HFSC_RSC]) { rsc = nla_data(tb[TCA_HFSC_RSC]); if (rsc->m1 == 0 && rsc->m2 == 0) rsc = NULL; } if (tb[TCA_HFSC_FSC]) { fsc = nla_data(tb[TCA_HFSC_FSC]); if (fsc->m1 == 0 && fsc->m2 == 0) fsc = NULL; } if (tb[TCA_HFSC_USC]) { usc = nla_data(tb[TCA_HFSC_USC]); if (usc->m1 == 0 && usc->m2 == 0) usc = NULL; } if (cl != NULL) { int old_flags; int len = 0; if (parentid) { if (cl->cl_parent && cl->cl_parent->cl_common.classid != parentid) return -EINVAL; if (cl->cl_parent == NULL && parentid != TC_H_ROOT) return -EINVAL; } cur_time = psched_get_time(); if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, true, tca[TCA_RATE]); if (err) return err; } sch_tree_lock(sch); old_flags = cl->cl_flags; if (rsc != NULL) hfsc_change_rsc(cl, rsc, cur_time); if (fsc != NULL) hfsc_change_fsc(cl, fsc); if (usc != NULL) hfsc_change_usc(cl, usc, cur_time); if (cl->qdisc->q.qlen != 0) len = qdisc_peek_len(cl->qdisc); /* Check queue length again since some qdisc implementations * (e.g., netem/codel) might empty the queue during the peek * operation. */ if (cl->qdisc->q.qlen != 0) { if (cl->cl_flags & HFSC_RSC) { if (old_flags & HFSC_RSC) update_ed(cl, len); else init_ed(cl, len); } if (cl->cl_flags & HFSC_FSC) { if (old_flags & HFSC_FSC) update_vf(cl, 0, cur_time); else init_vf(cl, len); } } sch_tree_unlock(sch); return 0; } if (parentid == TC_H_ROOT) return -EEXIST; parent = &q->root; if (parentid) { parent = hfsc_find_class(parentid, sch); if (parent == NULL) return -ENOENT; } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; if (hfsc_find_class(classid, sch)) return -EEXIST; if (rsc == NULL && fsc == NULL) return -EINVAL; cl = kzalloc(sizeof(struct hfsc_class), GFP_KERNEL); if (cl == NULL) return -ENOBUFS; RB_CLEAR_NODE(&cl->el_node); err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); return err; } if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, true, tca[TCA_RATE]); if (err) { tcf_block_put(cl->block); kfree(cl); return err; } } if (rsc != NULL) hfsc_change_rsc(cl, rsc, 0); if (fsc != NULL) hfsc_change_fsc(cl, fsc); if (usc != NULL) hfsc_change_usc(cl, usc, 0); cl->cl_common.classid = classid; cl->sched = q; cl->cl_parent = parent; cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; else qdisc_hash_add(cl->qdisc, true); INIT_LIST_HEAD(&cl->children); cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; sch_tree_lock(sch); /* Check if the inner class is a misconfigured 'rt' */ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { NL_SET_ERR_MSG(extack, "Forced curve change on parent 'rt' to 'sc'"); hfsc_upgrade_rt(parent); } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) qdisc_purge_queue(parent->qdisc); hfsc_adjust_levels(parent); sch_tree_unlock(sch); qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; } static void hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) { struct hfsc_sched *q = qdisc_priv(sch); tcf_block_put(cl->block); qdisc_put(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) kfree(cl); } static int hfsc_delete_class(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) || cl == &q->root) { NL_SET_ERR_MSG(extack, "HFSC class in use"); return -EBUSY; } sch_tree_lock(sch); list_del(&cl->siblings); hfsc_adjust_levels(cl->cl_parent); qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->cl_common); sch_tree_unlock(sch); hfsc_destroy_class(sch, cl); return 0; } static struct hfsc_class * hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *head, *cl; struct tcf_result res; struct tcf_proto *tcf; int result; if (TC_H_MAJ(skb->priority ^ sch->handle) == 0 && (cl = hfsc_find_class(skb->priority, sch)) != NULL) if (cl->level == 0) return cl; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return NULL; } #endif cl = (struct hfsc_class *)res.class; if (!cl) { cl = hfsc_find_class(res.classid, sch); if (!cl) break; /* filter selected invalid classid */ if (cl->level >= head->level) break; /* filter may only point downwards */ } if (cl->level == 0) return cl; /* hit leaf class */ /* apply inner filter chain */ tcf = rcu_dereference_bh(cl->filter_list); head = cl; } /* classification failed, try default class */ cl = hfsc_find_class(TC_H_MAKE(TC_H_MAJ(sch->handle), READ_ONCE(q->defcls)), sch); if (cl == NULL || cl->level > 0) return NULL; return cl; } static int hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl->level > 0) return -EINVAL; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->cl_common.classid, NULL); if (new == NULL) new = &noop_qdisc; } *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } static struct Qdisc * hfsc_class_leaf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl->level == 0) return cl->qdisc; return NULL; } static void hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; /* vttree is now handled in update_vf() so that update_vf(cl, 0, 0) * needs to be called explicitly to remove a class from vttree. */ if (cl->cl_nactive) update_vf(cl, 0, 0); if (cl->cl_flags & HFSC_RSC) eltree_remove(cl); } static unsigned long hfsc_search_class(struct Qdisc *sch, u32 classid) { return (unsigned long)hfsc_find_class(classid, sch); } static unsigned long hfsc_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid) { struct hfsc_class *p = (struct hfsc_class *)parent; struct hfsc_class *cl = hfsc_find_class(classid, sch); if (cl != NULL) { if (p != NULL && p->level <= cl->level) return 0; qdisc_class_get(&cl->cl_common); } return (unsigned long)cl; } static void hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; qdisc_class_put(&cl->cl_common); } static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl == NULL) cl = &q->root; return cl->block; } static int hfsc_dump_sc(struct sk_buff *skb, int attr, struct internal_sc *sc) { struct tc_service_curve tsc; tsc.m1 = sm2m(sc->sm1); tsc.d = dx2d(sc->dx); tsc.m2 = sm2m(sc->sm2); if (nla_put(skb, attr, sizeof(tsc), &tsc)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int hfsc_dump_curves(struct sk_buff *skb, struct hfsc_class *cl) { if ((cl->cl_flags & HFSC_RSC) && (hfsc_dump_sc(skb, TCA_HFSC_RSC, &cl->cl_rsc) < 0)) goto nla_put_failure; if ((cl->cl_flags & HFSC_FSC) && (hfsc_dump_sc(skb, TCA_HFSC_FSC, &cl->cl_fsc) < 0)) goto nla_put_failure; if ((cl->cl_flags & HFSC_USC) && (hfsc_dump_sc(skb, TCA_HFSC_USC, &cl->cl_usc) < 0)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct hfsc_class *cl = (struct hfsc_class *)arg; struct nlattr *nest; tcm->tcm_parent = cl->cl_parent ? cl->cl_parent->cl_common.classid : TC_H_ROOT; tcm->tcm_handle = cl->cl_common.classid; if (cl->level == 0) tcm->tcm_info = cl->qdisc->handle; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (hfsc_dump_curves(skb, cl) < 0) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct hfsc_class *cl = (struct hfsc_class *)arg; struct tc_hfsc_stats xstats; __u32 qlen; qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog); xstats.level = cl->level; xstats.period = cl->cl_vtperiod; xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); } static void hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; } } } static void hfsc_schedule_watchdog(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; u64 next_time = 0; cl = eltree_get_minel(q); if (cl) next_time = cl->cl_e; if (q->root.cl_cfmin != 0) { if (next_time == 0 || next_time > q->root.cl_cfmin) next_time = q->root.cl_cfmin; } if (next_time) qdisc_watchdog_schedule(&q->watchdog, next_time); } static int hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; int err; qdisc_watchdog_init(&q->watchdog, sch); if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); q->defcls = qopt->defcls; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; q->eligible = RB_ROOT; err = tcf_block_get(&q->root.block, &q->root.filter_list, sch, extack); if (err) return err; gnet_stats_basic_sync_init(&q->root.bstats); q->root.cl_common.classid = sch->handle; q->root.sched = q; q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, NULL); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; else qdisc_hash_add(q->root.qdisc, true); INIT_LIST_HEAD(&q->root.children); q->root.vt_tree = RB_ROOT; q->root.cf_tree = RB_ROOT; qdisc_class_hash_insert(&q->clhash, &q->root.cl_common); qdisc_class_hash_grow(sch, &q->clhash); return 0; } static int hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; if (nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); WRITE_ONCE(q->defcls, qopt->defcls); return 0; } static void hfsc_reset_class(struct hfsc_class *cl) { cl->cl_total = 0; cl->cl_cumul = 0; cl->cl_d = 0; cl->cl_e = 0; cl->cl_vt = 0; cl->cl_vtadj = 0; cl->cl_cvtmin = 0; cl->cl_cvtoff = 0; cl->cl_vtperiod = 0; cl->cl_parentperiod = 0; cl->cl_f = 0; cl->cl_myf = 0; cl->cl_cfmin = 0; cl->cl_nactive = 0; cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; qdisc_reset(cl->qdisc); if (cl->cl_flags & HFSC_RSC) rtsc_init(&cl->cl_deadline, &cl->cl_rsc, 0, 0); if (cl->cl_flags & HFSC_FSC) rtsc_init(&cl->cl_virtual, &cl->cl_fsc, 0, 0); if (cl->cl_flags & HFSC_USC) rtsc_init(&cl->cl_ulimit, &cl->cl_usc, 0, 0); } static void hfsc_reset_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) hfsc_reset_class(cl); } q->eligible = RB_ROOT; qdisc_watchdog_cancel(&q->watchdog); } static void hfsc_destroy_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hlist_node *next; struct hfsc_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { tcf_block_put(cl->block); cl->block = NULL; } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], cl_common.hnode) hfsc_destroy_class(sch, cl); } qdisc_class_hash_destroy(&q->clhash); qdisc_watchdog_cancel(&q->watchdog); } static int hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) { struct hfsc_sched *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); struct tc_hfsc_qopt qopt; qopt.defcls = READ_ONCE(q->defcls); if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; return skb->len; nla_put_failure: nlmsg_trim(skb, b); return -1; } static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); struct hfsc_class *cl; int err; bool first; cl = hfsc_classify(skb, sch, &err); if (cl == NULL) { if (err & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return err; } first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { cl->qstats.drops++; qdisc_qstats_drop(sch); } return err; } sch->qstats.backlog += len; sch->q.qlen++; if (first && !cl_in_el_or_vttree(cl)) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); if (cl->cl_flags & HFSC_FSC) init_vf(cl, len); /* * If this is the first packet, isolate the head so an eventual * head drop before the first dequeue operation has no chance * to invalidate the deadline. */ if (cl->cl_flags & HFSC_RSC) cl->qdisc->ops->peek(cl->qdisc); } return NET_XMIT_SUCCESS; } static struct sk_buff * hfsc_dequeue(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; struct sk_buff *skb; u64 cur_time; unsigned int next_len; int realtime = 0; if (sch->q.qlen == 0) return NULL; cur_time = psched_get_time(); /* * if there are eligible classes, use real-time criteria. * find the class with the minimum deadline among * the eligible classes. */ cl = eltree_get_mindl(q, cur_time); if (cl) { realtime = 1; } else { /* * use link-sharing criteria * get the class with the minimum vt in the hierarchy */ cl = vttree_get_minvt(&q->root, cur_time); if (cl == NULL) { qdisc_qstats_overlimit(sch); hfsc_schedule_watchdog(sch); return NULL; } } skb = qdisc_dequeue_peeked(cl->qdisc); if (skb == NULL) { qdisc_warn_nonwc("HFSC", cl->qdisc); return NULL; } bstats_update(&cl->bstats, skb); update_vf(cl, qdisc_pkt_len(skb), cur_time); if (realtime) cl->cl_cumul += qdisc_pkt_len(skb); if (cl->cl_flags & HFSC_RSC) { if (cl->qdisc->q.qlen != 0) { /* update ed */ next_len = qdisc_peek_len(cl->qdisc); /* Check queue length again since some qdisc implementations * (e.g., netem/codel) might empty the queue during the peek * operation. */ if (cl->qdisc->q.qlen != 0) { if (realtime) update_ed(cl, next_len); else update_d(cl, next_len); } } else { /* the class becomes passive */ eltree_remove(cl); } } qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; return skb; } static const struct Qdisc_class_ops hfsc_class_ops = { .change = hfsc_change_class, .delete = hfsc_delete_class, .graft = hfsc_graft_class, .leaf = hfsc_class_leaf, .qlen_notify = hfsc_qlen_notify, .find = hfsc_search_class, .bind_tcf = hfsc_bind_tcf, .unbind_tcf = hfsc_unbind_tcf, .tcf_block = hfsc_tcf_block, .dump = hfsc_dump_class, .dump_stats = hfsc_dump_class_stats, .walk = hfsc_walk }; static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = { .id = "hfsc", .init = hfsc_init_qdisc, .change = hfsc_change_qdisc, .reset = hfsc_reset_qdisc, .destroy = hfsc_destroy_qdisc, .dump = hfsc_dump_qdisc, .enqueue = hfsc_enqueue, .dequeue = hfsc_dequeue, .peek = qdisc_peek_dequeued, .cl_ops = &hfsc_class_ops, .priv_size = sizeof(struct hfsc_sched), .owner = THIS_MODULE }; MODULE_ALIAS_NET_SCH("hfsc"); static int __init hfsc_init(void) { return register_qdisc(&hfsc_qdisc_ops); } static void __exit hfsc_cleanup(void) { unregister_qdisc(&hfsc_qdisc_ops); } MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Hierarchical Fair Service Curve scheduler"); module_init(hfsc_init); module_exit(hfsc_cleanup); |
| 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_COUNTER_H #define _LINUX_PAGE_COUNTER_H #include <linux/atomic.h> #include <linux/cache.h> #include <linux/limits.h> #include <asm/page.h> struct page_counter { /* * Make sure 'usage' does not share cacheline with any other field in * v2. The memcg->memory.usage is a hot member of struct mem_cgroup. */ atomic_long_t usage; unsigned long failcnt; /* v1-only field */ CACHELINE_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ unsigned long emin; atomic_long_t min_usage; atomic_long_t children_min_usage; /* effective memory.low and memory.low usage tracking */ unsigned long elow; atomic_long_t low_usage; atomic_long_t children_low_usage; unsigned long watermark; /* Latest cg2 reset watermark */ unsigned long local_watermark; /* Keep all the read most fields in a separete cacheline. */ CACHELINE_PADDING(_pad2_); bool protection_support; bool track_failcnt; unsigned long min; unsigned long low; unsigned long high; unsigned long max; struct page_counter *parent; } ____cacheline_internodealigned_in_smp; #if BITS_PER_LONG == 32 #define PAGE_COUNTER_MAX LONG_MAX #else #define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE) #endif /* * Protection is supported only for the first counter (with id 0). */ static inline void page_counter_init(struct page_counter *counter, struct page_counter *parent, bool protection_support) { counter->usage = (atomic_long_t)ATOMIC_LONG_INIT(0); counter->max = PAGE_COUNTER_MAX; counter->parent = parent; counter->protection_support = protection_support; counter->track_failcnt = false; } static inline unsigned long page_counter_read(struct page_counter *counter) { return atomic_long_read(&counter->usage); } void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); void page_counter_charge(struct page_counter *counter, unsigned long nr_pages); bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages); void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages); static inline void page_counter_set_high(struct page_counter *counter, unsigned long nr_pages) { WRITE_ONCE(counter->high, nr_pages); } int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages); int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages); static inline void page_counter_reset_watermark(struct page_counter *counter) { unsigned long usage = page_counter_read(counter); /* * Update local_watermark first, so it's always <= watermark * (modulo CPU/compiler re-ordering) */ counter->local_watermark = usage; counter->watermark = usage; } #if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM) void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection); #else static inline void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection) {} #endif #endif /* _LINUX_PAGE_COUNTER_H */ |
| 115 114 117 116 33 33 112 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/once.h> #include <linux/random.h> #include <linux/module.h> struct once_work { struct work_struct work; struct static_key_true *key; struct module *module; }; static void once_deferred(struct work_struct *w) { struct once_work *work; work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); module_put(work->module); kfree(work); } static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; w = kmalloc(sizeof(*w), GFP_ATOMIC); if (!w) return; INIT_WORK(&w->work, once_deferred); w->key = key; w->module = mod; __module_get(mod); schedule_work(&w->work); } static DEFINE_SPINLOCK(once_lock); bool __do_once_start(bool *done, unsigned long *flags) __acquires(once_lock) { spin_lock_irqsave(&once_lock, *flags); if (*done) { spin_unlock_irqrestore(&once_lock, *flags); /* Keep sparse happy by restoring an even lock count on * this lock. In case we return here, we don't call into * __do_once_done but return early in the DO_ONCE() macro. */ __acquire(once_lock); return false; } return true; } EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); static DEFINE_MUTEX(once_mutex); bool __do_once_sleepable_start(bool *done) __acquires(once_mutex) { mutex_lock(&once_mutex); if (*done) { mutex_unlock(&once_mutex); /* Keep sparse happy by restoring an even lock count on * this mutex. In case we return here, we don't call into * __do_once_done but return early in the DO_ONCE_SLEEPABLE() macro. */ __acquire(once_mutex); return false; } return true; } EXPORT_SYMBOL(__do_once_sleepable_start); void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, struct module *mod) __releases(once_mutex) { *done = true; mutex_unlock(&once_mutex); once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_sleepable_done); |
| 188 186 182 72 52 52 52 11 189 189 189 1 1 189 1104 1066 72 171 645 242 171 127 630 636 636 635 639 638 142 638 142 593 138 2 1 1 2 138 436 138 437 7 7 431 138 138 138 641 636 115 638 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux network device link state notification * * Author: * Stefan Rompf <sux@loplof.de> */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/if.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <linux/rtnetlink.h> #include <linux/jiffies.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/bitops.h> #include <linux/types.h> #include "dev.h" enum lw_bits { LW_URGENT = 0, }; static unsigned long linkwatch_flags; static unsigned long linkwatch_nextevent; static void linkwatch_event(struct work_struct *dummy); static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); static unsigned int default_operstate(const struct net_device *dev) { if (netif_testing(dev)) return IF_OPER_TESTING; /* Some uppers (DSA) have additional sources for being down, so * first check whether lower is indeed the source of its down state. */ if (!netif_carrier_ok(dev)) { struct net_device *peer; int iflink; /* If called from netdev_run_todo()/linkwatch_sync_dev(), * dev_net(dev) can be already freed, and RTNL is not held. */ if (dev->reg_state <= NETREG_REGISTERED) iflink = dev_get_iflink(dev); else iflink = dev->ifindex; if (iflink == dev->ifindex) return IF_OPER_DOWN; ASSERT_RTNL(); peer = __dev_get_by_index(dev_net(dev), iflink); if (!peer) return IF_OPER_DOWN; return netif_carrier_ok(peer) ? IF_OPER_DOWN : IF_OPER_LOWERLAYERDOWN; } if (netif_dormant(dev)) return IF_OPER_DORMANT; return IF_OPER_UP; } static void rfc2863_policy(struct net_device *dev) { unsigned int operstate = default_operstate(dev); if (operstate == READ_ONCE(dev->operstate)) return; switch(dev->link_mode) { case IF_LINK_MODE_TESTING: if (operstate == IF_OPER_UP) operstate = IF_OPER_TESTING; break; case IF_LINK_MODE_DORMANT: if (operstate == IF_OPER_UP) operstate = IF_OPER_DORMANT; break; case IF_LINK_MODE_DEFAULT: default: break; } WRITE_ONCE(dev->operstate, operstate); } void linkwatch_init_dev(struct net_device *dev) { /* Handle pre-registration link state changes */ if (!netif_carrier_ok(dev) || netif_dormant(dev) || netif_testing(dev)) rfc2863_policy(dev); } static bool linkwatch_urgent_event(struct net_device *dev) { if (!netif_running(dev)) return false; if (dev->ifindex != dev_get_iflink(dev)) return true; if (netif_is_lag_port(dev) || netif_is_lag_master(dev)) return true; return netif_carrier_ok(dev) && qdisc_tx_changing(dev); } static void linkwatch_add_event(struct net_device *dev) { unsigned long flags; spin_lock_irqsave(&lweventlist_lock, flags); if (list_empty(&dev->link_watch_list)) { list_add_tail(&dev->link_watch_list, &lweventlist); netdev_hold(dev, &dev->linkwatch_dev_tracker, GFP_ATOMIC); } spin_unlock_irqrestore(&lweventlist_lock, flags); } static void linkwatch_schedule_work(int urgent) { unsigned long delay = linkwatch_nextevent - jiffies; if (test_bit(LW_URGENT, &linkwatch_flags)) return; /* Minimise down-time: drop delay for up event. */ if (urgent) { if (test_and_set_bit(LW_URGENT, &linkwatch_flags)) return; delay = 0; } /* If we wrap around we'll delay it by at most HZ. */ if (delay > HZ) delay = 0; /* * If urgent, schedule immediate execution; otherwise, don't * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) mod_delayed_work(system_dfl_wq, &linkwatch_work, 0); else queue_delayed_work(system_dfl_wq, &linkwatch_work, delay); } static void linkwatch_do_dev(struct net_device *dev) { /* * Make sure the above read is complete since it can be * rewritten as soon as we clear the bit below. */ smp_mb__before_atomic(); /* We are about to handle this device, * so new events can be accepted */ clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) dev_activate(dev); else dev_deactivate(dev); netif_state_change(dev); } /* Note: our callers are responsible for calling netdev_tracker_free(). * This is the reason we use __dev_put() instead of dev_put(). */ __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) { #define MAX_DO_DEV_PER_LOOP 100 int do_dev = MAX_DO_DEV_PER_LOOP; /* Use a local list here since we add non-urgent * events back to the global one when called with * urgent_only=1. */ LIST_HEAD(wrk); /* Give urgent case more budget */ if (urgent_only) do_dev += MAX_DO_DEV_PER_LOOP; /* * Limit the number of linkwatch events to one * per second so that a runaway driver does not * cause a storm of messages on the netlink * socket. This limit does not apply to up events * while the device qdisc is down. */ if (!urgent_only) linkwatch_nextevent = jiffies + HZ; /* Limit wrap-around effect on delay. */ else if (time_after(linkwatch_nextevent, jiffies + HZ)) linkwatch_nextevent = jiffies; clear_bit(LW_URGENT, &linkwatch_flags); spin_lock_irq(&lweventlist_lock); list_splice_init(&lweventlist, &wrk); while (!list_empty(&wrk) && do_dev > 0) { struct net_device *dev; dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); if (!netif_device_present(dev) || (urgent_only && !linkwatch_urgent_event(dev))) { list_add_tail(&dev->link_watch_list, &lweventlist); continue; } /* We must free netdev tracker under * the spinlock protection. */ netdev_tracker_free(dev, &dev->linkwatch_dev_tracker); spin_unlock_irq(&lweventlist_lock); netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); do_dev--; spin_lock_irq(&lweventlist_lock); } /* Add the remaining work back to lweventlist */ list_splice_init(&wrk, &lweventlist); if (!list_empty(&lweventlist)) linkwatch_schedule_work(0); spin_unlock_irq(&lweventlist_lock); } static bool linkwatch_clean_dev(struct net_device *dev) { unsigned long flags; bool clean = false; spin_lock_irqsave(&lweventlist_lock, flags); if (!list_empty(&dev->link_watch_list)) { list_del_init(&dev->link_watch_list); clean = true; /* We must release netdev tracker under * the spinlock protection. */ netdev_tracker_free(dev, &dev->linkwatch_dev_tracker); } spin_unlock_irqrestore(&lweventlist_lock, flags); return clean; } void __linkwatch_sync_dev(struct net_device *dev) { netdev_ops_assert_locked(dev); if (linkwatch_clean_dev(dev)) linkwatch_do_dev(dev); } void linkwatch_sync_dev(struct net_device *dev) { if (linkwatch_clean_dev(dev)) { netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); } } /* Must be called with the rtnl semaphore held */ void linkwatch_run_queue(void) { __linkwatch_run_queue(0); } static void linkwatch_event(struct work_struct *dummy) { rtnl_lock(); __linkwatch_run_queue(time_after(linkwatch_nextevent, jiffies)); rtnl_unlock(); } void linkwatch_fire_event(struct net_device *dev) { bool urgent = linkwatch_urgent_event(dev); if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { linkwatch_add_event(dev); } else if (!urgent) return; linkwatch_schedule_work(urgent); } EXPORT_SYMBOL(linkwatch_fire_event); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 * * Author: Eric Biederman <ebiederm@xmision.com> */ #include <linux/export.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/random.h> #include <linux/sysctl.h> #include <linux/wait.h> #include <linux/rwsem.h> #ifdef CONFIG_PROC_SYSCTL static void *get_uts(const struct ctl_table *table) { char *which = table->data; struct uts_namespace *uts_ns; uts_ns = current->nsproxy->uts_ns; which = (which - (char *)&init_uts_ns) + (char *)uts_ns; return which; } /* * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? */ static int proc_do_uts_string(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table uts_table; int r; char tmp_data[__NEW_UTS_LEN + 1]; memcpy(&uts_table, table, sizeof(uts_table)); uts_table.data = tmp_data; /* * Buffer the value in tmp_data so that proc_dostring() can be called * without holding any locks. * We also need to read the original value in the write==1 case to * support partial writes. */ down_read(&uts_sem); memcpy(tmp_data, get_uts(table), sizeof(tmp_data)); up_read(&uts_sem); r = proc_dostring(&uts_table, write, buffer, lenp, ppos); if (write) { /* * Write back the new value. * Note that, since we dropped uts_sem, the result can * theoretically be incorrect if there are two parallel writes * at non-zero offsets to the same sysctl. */ add_device_randomness(tmp_data, sizeof(tmp_data)); down_write(&uts_sem); memcpy(get_uts(table), tmp_data, sizeof(tmp_data)); up_write(&uts_sem); proc_sys_poll_notify(table->poll); } return r; } #else #define proc_do_uts_string NULL #endif static DEFINE_CTL_TABLE_POLL(hostname_poll); static DEFINE_CTL_TABLE_POLL(domainname_poll); // Note: update 'enum uts_proc' to match any changes to this table static const struct ctl_table uts_kern_table[] = { { .procname = "arch", .data = init_uts_ns.name.machine, .maxlen = sizeof(init_uts_ns.name.machine), .mode = 0444, .proc_handler = proc_do_uts_string, }, { .procname = "ostype", .data = init_uts_ns.name.sysname, .maxlen = sizeof(init_uts_ns.name.sysname), .mode = 0444, .proc_handler = proc_do_uts_string, }, { .procname = "osrelease", .data = init_uts_ns.name.release, .maxlen = sizeof(init_uts_ns.name.release), .mode = 0444, .proc_handler = proc_do_uts_string, }, { .procname = "version", .data = init_uts_ns.name.version, .maxlen = sizeof(init_uts_ns.name.version), .mode = 0444, .proc_handler = proc_do_uts_string, }, { .procname = "hostname", .data = init_uts_ns.name.nodename, .maxlen = sizeof(init_uts_ns.name.nodename), .mode = 0644, .proc_handler = proc_do_uts_string, .poll = &hostname_poll, }, { .procname = "domainname", .data = init_uts_ns.name.domainname, .maxlen = sizeof(init_uts_ns.name.domainname), .mode = 0644, .proc_handler = proc_do_uts_string, .poll = &domainname_poll, }, }; #ifdef CONFIG_PROC_SYSCTL /* * Notify userspace about a change in a certain entry of uts_kern_table, * identified by the parameter proc. */ void uts_proc_notify(enum uts_proc proc) { const struct ctl_table *table = &uts_kern_table[proc]; proc_sys_poll_notify(table->poll); } #endif static int __init utsname_sysctl_init(void) { register_sysctl("kernel", uts_kern_table); return 0; } device_initcall(utsname_sysctl_init); |
| 4 4 4 4 4 4 4 4 4 4 4 1 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 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 1 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 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 4 25 26 17 17 17 4 4 4 4 4 4 17 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 1 1 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 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 2 2 2 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ /* * mballoc.c contains the multiblocks allocation routines */ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> #include <linux/freezer.h> #include <trace/events/ext4.h> #include <kunit/static_stub.h> /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() * - search for metadata in few groups * * TODO v4: * - normalization should take into account whether file is still open * - discard preallocations if no free space left (policy?) * - don't normalize tails * - quota * - reservation for superuser * * TODO v3: * - bitmap read-ahead (proposed by Oleg Drokin aka green) * - track min/max extents in each group for better group selection * - mb_mark_used() may allocate chunk right after splitting buddy * - tree of groups sorted by number of free blocks * - error handling */ /* * The allocation request involve request for multiple number of blocks * near to the goal(block) value specified. * * During initialization phase of the allocator we decide to use the * group preallocation or inode preallocation depending on the size of * the file. The size of the file could be the resulting file size we * would have after allocation, or the current file size, which ever * is larger. If the size is less than sbi->s_mb_stream_request we * select to use the group preallocation. The default value of * s_mb_stream_request is 16 blocks. This can also be tuned via * /sys/fs/ext4/<partition>/mb_stream_req. The value is represented in * terms of number of blocks. * * The main motivation for having small file use group preallocation is to * ensure that we have small files closer together on the disk. * * First stage the allocator looks at the inode prealloc list, * ext4_inode_info->i_prealloc_list, which contains list of prealloc * spaces for this particular inode. The inode prealloc space is * represented as: * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space * pa_len -> length for this prealloc space (in clusters) * pa_free -> free space available in this prealloc space (in clusters) * * The inode preallocation space is used looking at the _logical_ start * block. If only the logical file block falls within the range of prealloc * space we will consume the particular prealloc space. This makes sure that * we have contiguous physical blocks representing the file blocks * * The important thing to be noted in case of inode prealloc space is that * we don't modify the values associated to inode prealloc space except * pa_free. * * If we are not able to find blocks in the inode prealloc space and if we * have the group allocation flag set then we look at the locality group * prealloc space. These are per CPU prealloc list represented as * * ext4_sb_info.s_locality_groups[smp_processor_id()] * * The reason for having a per cpu locality group is to reduce the contention * between CPUs. It is possible to get scheduled at this point. * * The locality group prealloc space is used looking at whether we have * enough free space (pa_free) within the prealloc space. * * If we can't allocate blocks via inode prealloc or/and locality group * prealloc then we look at the buddy cache. The buddy cache is represented * by ext4_sb_info.s_buddy_cache (struct inode) whose file offset gets * mapped to the buddy and bitmap information regarding different * groups. The buddy information is attached to buddy cache inode so that * we can access them through the page cache. The information regarding * each group is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are stored in the * inode as: * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. So for each group we * take up 2 blocks. A page can contain blocks_per_page (PAGE_SIZE / * blocksize) blocks. So it can have information regarding groups_per_page * which is blocks_per_page/2 * * The buddy cache inode is not stored on disk. The inode is thrown * away when the filesystem is unmounted. * * We look for count number of blocks in the buddy cache. If we were able * to locate that many free blocks we return with additional information * regarding rest of the contiguous physical block available * * Before allocating blocks via buddy cache we normalize the request * blocks. This ensure we ask for more blocks that we needed. The extra * blocks that we get after allocation is added to the respective prealloc * list. In case of inode preallocation we follow a list of heuristics * based on file size. This can be found in ext4_mb_normalize_request. If * we are doing a group prealloc we try to normalize the request to * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is * dependent on the cluster size; for non-bigalloc file systems, it is * 512 blocks. This can be tuned via * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in * terms of number of blocks. If we have mounted the file system with -O * stripe=<value> option the group prealloc request is normalized to the * smallest multiple of the stripe value (sbi->s_stripe) which is * greater than the default mb_group_prealloc. * * If "mb_optimize_scan" mount option is set, we maintain in memory group info * structures in two data structures: * * 1) Array of largest free order xarrays (sbi->s_mb_largest_free_orders) * * Locking: Writers use xa_lock, readers use rcu_read_lock. * * This is an array of xarrays where the index in the array represents the * largest free order in the buddy bitmap of the participating group infos of * that xarray. So, there are exactly MB_NUM_ORDERS(sb) (which means total * number of buddy bitmap orders possible) number of xarrays. Group-infos are * placed in appropriate xarrays. * * 2) Average fragment size xarrays (sbi->s_mb_avg_fragment_size) * * Locking: Writers use xa_lock, readers use rcu_read_lock. * * This is an array of xarrays where in the i-th xarray there are groups with * average fragment size >= 2^i and < 2^(i+1). The average fragment size * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. * Note that we don't bother with a special xarray for completely empty * groups so we only have MB_NUM_ORDERS(sb) xarrays. Group-infos are placed * in appropriate xarrays. * * In xarray, the index is the block group number, the value is the block group * information, and a non-empty value indicates the block group is present in * the current xarray. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for * fulfilling an allocation request. * * At CR_POWER2_ALIGNED , we look for groups which have the largest_free_order * >= the order of the request. We directly look at the largest free order list * in the data structure (1) above where largest_free_order = order of the * request. If that list is empty, we look at remaining list in the increasing * order of largest_free_order. This allows us to perform CR_POWER2_ALIGNED * lookup in O(1) time. * * At CR_GOAL_LEN_FAST, we only consider groups where * average fragment size > request size. So, we lookup a group which has average * fragment size just above or equal to request size using our average fragment * size group lists (data structure 2) in O(1) time. * * At CR_BEST_AVAIL_LEN, we aim to optimize allocations which can't be satisfied * in CR_GOAL_LEN_FAST. The fact that we couldn't find a group in * CR_GOAL_LEN_FAST suggests that there is no BG that has avg * fragment size > goal length. So before falling to the slower * CR_GOAL_LEN_SLOW, in CR_BEST_AVAIL_LEN we proactively trim goal length and * then use the same fragment lists as CR_GOAL_LEN_FAST to find a BG with a big * enough average fragment size. This increases the chances of finding a * suitable block group in O(1) time and results in faster allocation at the * cost of reduced size of allocation. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR_POWER2_ALIGNED and * CR_GOAL_LEN_FAST phase. * * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan * /sys/fs/ext4/<partition>/mb_order2_req * /sys/fs/ext4/<partition>/mb_max_linear_groups * * The regular allocator uses buddy scan only if the request len is power of * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The * value of s_mb_order2_reqs can be tuned via * /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to * stripe size (sbi->s_stripe), we try to search for contiguous block in * stripe size. This should result in better allocation on RAID setups. If * not, we search in the specific group using bitmap for best extents. The * tunable min_to_scan and max_to_scan control the behaviour here. * min_to_scan indicate how long the mballoc __must__ look for a best * extent and max_to_scan indicates how long the mballoc __can__ look for a * best extent in the found extents. Searching for the blocks starts with * the group specified as the goal value in allocation context via * ac_g_ex. Each group is first checked based on the criteria whether it * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * * When "mb_optimize_scan" is turned on, as mentioned above, the groups may not * get traversed linearly. That may result in subsequent allocations being not * close to each other. And so, the underlying device may get filled up in a * non-linear fashion. While that may not matter on non-rotational devices, for * rotational devices that may result in higher seek times. "mb_max_linear_groups" * tells mballoc how many groups mballoc should search linearly before * performing consulting above data structures for more efficient lookups. For * non rotational devices, this value defaults to 0 and for rotational devices * this is set to MB_DEFAULT_LINEAR_LIMIT. * * Both the prealloc space are getting populated as above. So for the first * request we will hit the buddy cache which will result in this prealloc * space getting filled. The prealloc space is then later used for the * subsequent request. */ /* * mballoc operates on the following data: * - on-disk bitmap * - in-core buddy (actually includes buddy and bitmap) * - preallocation descriptors (PAs) * * there are two types of preallocations: * - inode * assiged to specific inode and can be used for this inode only. * it describes part of inode's space preallocated to specific * physical blocks. any block from that preallocated can be used * independent. the descriptor just tracks number of blocks left * unused. so, before taking some block from descriptor, one must * make sure corresponded logical block isn't allocated yet. this * also means that freeing any block within descriptor's range * must discard all preallocated blocks. * - locality group * assigned to specific locality group which does not translate to * permanent set of inodes: inode can join and leave group. space * from this type of preallocation can be used for any inode. thus * it's consumed from the beginning to the end. * * relation between them can be expressed as: * in-core buddy = on-disk bitmap + preallocation descriptors * * this mean blocks mballoc considers used are: * - allocated blocks (persistent) * - preallocated blocks (non-persistent) * * consistency in mballoc world means that at any time a block is either * free or used in ALL structures. notice: "any time" should not be read * literally -- time is discrete and delimited by locks. * * to keep it simple, we don't use block numbers, instead we count number of * blocks: how many blocks marked used/free in on-disk bitmap, buddy and PA. * * all operations can be expressed as: * - init buddy: buddy = on-disk + PAs * - new PA: buddy += N; PA = N * - use inode PA: on-disk += N; PA -= N * - discard inode PA buddy -= on-disk - PA; PA = 0 * - use locality group PA on-disk += N; PA -= N * - discard locality group PA buddy -= PA; PA = 0 * note: 'buddy -= on-disk - PA' is used to show that on-disk bitmap * is used in real operation because we can't know actual used * bits from PA, only from on-disk bitmap * * if we follow this strict logic, then all operations above should be atomic. * given some of them can block, we'd have to use something like semaphores * killing performance on high-end SMP hardware. let's try to relax it using * the following knowledge: * 1) if buddy is referenced, it's already initialized * 2) while block is used in buddy and the buddy is referenced, * nobody can re-allocate that block * 3) we work on bitmaps and '+' actually means 'set bits'. if on-disk has * bit set and PA claims same block, it's OK. IOW, one can set bit in * on-disk bitmap if buddy has same bit set or/and PA covers corresponded * block * * so, now we're building a concurrency table: * - init buddy vs. * - new PA * blocks for PA are allocated in the buddy, buddy must be referenced * until PA is linked to allocation group to avoid concurrent buddy init * - use inode PA * we need to make sure that either on-disk bitmap or PA has uptodate data * given (3) we care that PA-=N operation doesn't interfere with init * - discard inode PA * the simplest way would be to have buddy initialized by the discard * - use locality group PA * again PA-=N must be serialized with init * - discard locality group PA * the simplest way would be to have buddy initialized by the discard * - new PA vs. * - use inode PA * i_data_sem serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * some mutex should serialize them * - discard locality group PA * discard process must wait until PA isn't used by another process * - use inode PA * - use inode PA * i_data_sem or another mutex should serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * nothing wrong here -- they're different PAs covering different blocks * - discard locality group PA * discard process must wait until PA isn't used by another process * * now we're ready to make few consequences: * - PA is referenced and while it is no discard is possible * - PA is referenced until block isn't marked in on-disk bitmap * - PA changes only after on-disk bitmap * - discard must not compete with init. either init is done before * any discard or they're serialized somehow * - buddy init as sum of on-disk bitmap and PAs is done atomically * * a special case when we've used PA to emptiness. no need to modify buddy * in this case, but we should care about concurrent init * */ /* * Logic in few words: * * - allocation: * load group * find blocks * mark bits in on-disk bitmap * release group * * - use preallocation: * find proper PA (per-inode or group) * load group * mark bits in on-disk bitmap * release group * release PA * * - free: * load group * mark bits in on-disk bitmap * release group * * - discard preallocations in group: * mark PAs deleted * move them onto local list * load on-disk bitmap * load group * remove PA from object (inode or locality group) * mark free blocks in-core * * - discard inode's preallocations: */ /* * Locking rules * * Locks: * - bitlock on a group (group) * - object (inode/locality) (object) * - per-pa lock (pa) * - cr_power2_aligned lists lock (cr_power2_aligned) * - cr_goal_len_fast lists lock (cr_goal_len_fast) * * Paths: * - new pa * object * group * * - find and use pa: * pa * * - release consumed pa: * pa * group * object * * - generate in-core bitmap: * group * pa * * - discard all for given object (inode, locality group): * object * pa * group * * - discard all for given group: * group * pa * group * object * * - allocation path (ext4_mb_regular_allocator) * group * cr_power2_aligned/cr_goal_len_fast */ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_data_cachep; /* We create slab caches for groupinfo data structures based on the * superblock block size. There will be one per mounted filesystem for * each unique s_blocksize_bits */ #define NR_GRPINFO_CACHES 8 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k", "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k", "ext4_groupinfo_64k", "ext4_groupinfo_128k" }; static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); static int ext4_mb_scan_group(struct ext4_allocation_context *ac, ext4_group_t group); static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks); /* * The algorithm using this percpu seq counter goes below: * 1. We sample the percpu discard_pa_seq counter before trying for block * allocation in ext4_mb_new_blocks(). * 2. We increment this percpu discard_pa_seq counter when we either allocate * or free these blocks i.e. while marking those blocks as used/free in * mb_mark_used()/mb_free_blocks(). * 3. We also increment this percpu seq counter when we successfully identify * that the bb_prealloc_list is not empty and hence proceed for discarding * of those PAs inside ext4_mb_discard_group_preallocations(). * * Now to make sure that the regular fast path of block allocation is not * affected, as a small optimization we only sample the percpu seq counter * on that cpu. Only when the block allocation fails and when freed blocks * found were 0, that is when we sample percpu seq counter for all cpus using * below function ext4_get_discard_pa_seq_sum(). This happens after making * sure that all the PAs on grp->bb_prealloc_list got freed or if it's empty. */ static DEFINE_PER_CPU(u64, discard_pa_seq); static inline u64 ext4_get_discard_pa_seq_sum(void) { int __cpu; u64 __seq = 0; for_each_possible_cpu(__cpu) __seq += per_cpu(discard_pa_seq, __cpu); return __seq; } static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline int mb_test_bit(int bit, void *addr) { /* * ext4_test_bit on architecture like powerpc * needs unsigned long aligned address */ addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_bit(bit, addr); } static inline void mb_set_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit(bit, addr); } static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } static inline int mb_test_and_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_and_clear_bit(bit, addr); } static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_zero_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static inline int mb_find_next_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) { char *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(max == NULL); if (order > e4b->bd_blkbits + 1) { *max = 0; return NULL; } /* at order 0 we see each particular block */ if (order == 0) { *max = 1 << (e4b->bd_blkbits + 3); return e4b->bd_bitmap; } bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order]; *max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order]; return bb; } #ifdef DOUBLE_CHECK static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int i; struct super_block *sb = e4b->bd_sb; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(EXT4_SB(sb), first + i); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing block already freed " "(bit %u)", first + i); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { int i; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) { unsigned char *b1, *b2; int i; b1 = (unsigned char *) e4b->bd_info->bb_bitmap; b2 = (unsigned char *) bitmap; for (i = 0; i < e4b->bd_sb->s_blocksize; i++) { if (b1[i] != b2[i]) { ext4_msg(e4b->bd_sb, KERN_ERR, "corruption in group %u " "at byte %u(%u): %x in copy != %x " "on disk/prealloc", e4b->bd_group, i, i * 8, b1[i], b2[i]); BUG(); } } } } static void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { struct buffer_head *bh; grp->bb_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS); if (!grp->bb_bitmap) return; bh = ext4_read_block_bitmap(sb, group); if (IS_ERR_OR_NULL(bh)) { kfree(grp->bb_bitmap); grp->bb_bitmap = NULL; return; } memcpy(grp->bb_bitmap, bh->b_data, sb->s_blocksize); put_bh(bh); } static void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { kfree(grp->bb_bitmap); } #else static inline void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { return; } static inline void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { return; } static inline void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { return; } #endif #ifdef AGGRESSIVE_CHECK #define MB_CHECK_ASSERT(assert) \ do { \ if (!(assert)) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: \"%s\"\n", \ function, file, line, # assert); \ BUG(); \ } \ } while (0) static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { struct super_block *sb = e4b->bd_sb; int order = e4b->bd_blkbits + 1; int max; int max2; int i; int j; int k; int count; struct ext4_group_info *grp; int fragments = 0; int fstart; struct list_head *cur; void *buddy; void *buddy2; if (e4b->bd_info->bb_check_counter++ % 10) return; while (order > 1) { buddy = mb_find_buddy(e4b, order, &max); MB_CHECK_ASSERT(buddy); buddy2 = mb_find_buddy(e4b, order - 1, &max2); MB_CHECK_ASSERT(buddy2); MB_CHECK_ASSERT(buddy != buddy2); MB_CHECK_ASSERT(max * 2 == max2); count = 0; for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { /* only single bit in buddy2 may be 0 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); } continue; } /* both bits in buddy2 must be 1 */ MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2)); MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2)); for (j = 0; j < (1 << order); j++) { k = (i * (1 << order)) + j; MB_CHECK_ASSERT( !mb_test_bit(k, e4b->bd_bitmap)); } count++; } MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count); order--; } fstart = -1; buddy = mb_find_buddy(e4b, 0, &max); for (i = 0; i < max; i++) { if (!mb_test_bit(i, buddy)) { MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free); if (fstart == -1) { fragments++; fstart = i; } continue; } fstart = -1; /* check used bits only */ for (j = 0; j < e4b->bd_blkbits + 1; j++) { buddy2 = mb_find_buddy(e4b, j, &max2); k = i >> j; MB_CHECK_ASSERT(k < max2); MB_CHECK_ASSERT(mb_test_bit(k, buddy2)); } } MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info)); MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); if (!grp) return; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k); MB_CHECK_ASSERT(groupnr == e4b->bd_group); for (i = 0; i < pa->pa_len; i++) MB_CHECK_ASSERT(mb_test_bit(k + i, buddy)); } } #undef MB_CHECK_ASSERT #define mb_check_buddy(e4b) __mb_check_buddy(e4b, \ __FILE__, __func__, __LINE__) #else #define mb_check_buddy(e4b) #endif /* * Divide blocks started from @first with length @len into * smaller chunks with power of 2 blocks. * Clear the bits in bitmap which the blocks of the chunk(s) covered, * then increase bb_counters[] for corresponded chunk size. */ static void ext4_mb_mark_free_simple(struct super_block *sb, void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t min; ext4_grpblk_t max; ext4_grpblk_t chunk; unsigned int border; BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb)); border = 2 << sb->s_blocksize_bits; while (len > 0) { /* find how many blocks can be covered since this position */ max = ffs(first | border) - 1; /* find how many blocks of power 2 we need to mark */ min = fls(len) - 1; if (max < min) min = max; chunk = 1 << min; /* mark multiblock chunks only */ grp->bb_counters[min]++; if (min > 0) mb_clear_bit(first >> min, buddy + sbi->s_mb_offsets[min]); len -= chunk; first += chunk; } } static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { int order; /* * We don't bother with a special lists groups with only 1 block free * extents and for completely empty groups. */ order = fls(len) - 2; if (order < 0) return 0; if (order == MB_NUM_ORDERS(sb)) order--; if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb))) order = MB_NUM_ORDERS(sb) - 1; return order; } /* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int new, old; if (!test_opt2(sb, MB_OPTIMIZE_SCAN)) return; old = grp->bb_avg_fragment_size_order; new = grp->bb_fragments == 0 ? -1 : mb_avg_fragment_size_order(sb, grp->bb_free / grp->bb_fragments); if (new == old) return; if (old >= 0) xa_erase(&sbi->s_mb_avg_fragment_size[old], grp->bb_group); grp->bb_avg_fragment_size_order = new; if (new >= 0) { /* * Cannot use __GFP_NOFAIL because we hold the group lock. * Although allocation for insertion may fails, it's not fatal * as we have linear traversal to fall back on. */ int err = xa_insert(&sbi->s_mb_avg_fragment_size[new], grp->bb_group, grp, GFP_ATOMIC); if (err) mb_debug(sb, "insert group: %u to s_mb_avg_fragment_size[%d] failed, err %d", grp->bb_group, new, err); } } static int ext4_mb_scan_groups_xa_range(struct ext4_allocation_context *ac, struct xarray *xa, ext4_group_t start, ext4_group_t end) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); enum criteria cr = ac->ac_criteria; ext4_group_t ngroups = ext4_get_groups_count(sb); unsigned long group = start; struct ext4_group_info *grp; if (WARN_ON_ONCE(end > ngroups || start >= end)) return 0; xa_for_each_range(xa, group, grp, start, end - 1) { int err; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[cr]); err = ext4_mb_scan_group(ac, grp->bb_group); if (err || ac->ac_status != AC_STATUS_CONTINUE) return err; cond_resched(); } return 0; } /* * Find a suitable group of given order from the largest free orders xarray. */ static inline int ext4_mb_scan_groups_largest_free_order_range(struct ext4_allocation_context *ac, int order, ext4_group_t start, ext4_group_t end) { struct xarray *xa = &EXT4_SB(ac->ac_sb)->s_mb_largest_free_orders[order]; if (xa_empty(xa)) return 0; return ext4_mb_scan_groups_xa_range(ac, xa, start, end); } /* * Choose next group by traversing largest_free_order lists. Updates *new_cr if * cr level needs an update. */ static int ext4_mb_scan_groups_p2_aligned(struct ext4_allocation_context *ac, ext4_group_t group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int i; int ret = 0; ext4_group_t start, end; start = group; end = ext4_get_groups_count(ac->ac_sb); wrap_around: for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { ret = ext4_mb_scan_groups_largest_free_order_range(ac, i, start, end); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; } if (start) { end = start; start = 0; goto wrap_around; } if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_failed[ac->ac_criteria]); /* Increment cr and search again if no group is found */ ac->ac_criteria = CR_GOAL_LEN_FAST; return ret; } /* * Find a suitable group of given order from the average fragments xarray. */ static int ext4_mb_scan_groups_avg_frag_order_range(struct ext4_allocation_context *ac, int order, ext4_group_t start, ext4_group_t end) { struct xarray *xa = &EXT4_SB(ac->ac_sb)->s_mb_avg_fragment_size[order]; if (xa_empty(xa)) return 0; return ext4_mb_scan_groups_xa_range(ac, xa, start, end); } /* * Choose next group by traversing average fragment size list of suitable * order. Updates *new_cr if cr level needs an update. */ static int ext4_mb_scan_groups_goal_fast(struct ext4_allocation_context *ac, ext4_group_t group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int i, ret = 0; ext4_group_t start, end; start = group; end = ext4_get_groups_count(ac->ac_sb); wrap_around: i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); for (; i < MB_NUM_ORDERS(ac->ac_sb); i++) { ret = ext4_mb_scan_groups_avg_frag_order_range(ac, i, start, end); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; } if (start) { end = start; start = 0; goto wrap_around; } if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_failed[ac->ac_criteria]); /* * CR_BEST_AVAIL_LEN works based on the concept that we have * a larger normalized goal len request which can be trimmed to * a smaller goal len such that it can still satisfy original * request len. However, allocation request for non-regular * files never gets normalized. * See function ext4_mb_normalize_request() (EXT4_MB_HINT_DATA). */ if (ac->ac_flags & EXT4_MB_HINT_DATA) ac->ac_criteria = CR_BEST_AVAIL_LEN; else ac->ac_criteria = CR_GOAL_LEN_SLOW; return ret; } /* * We couldn't find a group in CR_GOAL_LEN_FAST so try to find the highest free fragment * order we have and proactively trim the goal request length to that order to * find a suitable group faster. * * This optimizes allocation speed at the cost of slightly reduced * preallocations. However, we make sure that we don't trim the request too * much and fall to CR_GOAL_LEN_SLOW in that case. */ static int ext4_mb_scan_groups_best_avail(struct ext4_allocation_context *ac, ext4_group_t group) { int ret = 0; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int i, order, min_order; unsigned long num_stripe_clusters = 0; ext4_group_t start, end; /* * mb_avg_fragment_size_order() returns order in a way that makes * retrieving back the length using (1 << order) inaccurate. Hence, use * fls() instead since we need to know the actual length while modifying * goal length. */ order = fls(ac->ac_g_ex.fe_len) - 1; if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb))) order = MB_NUM_ORDERS(ac->ac_sb); min_order = order - sbi->s_mb_best_avail_max_trim_order; if (min_order < 0) min_order = 0; if (sbi->s_stripe > 0) { /* * We are assuming that stripe size is always a multiple of * cluster ratio otherwise __ext4_fill_super exists early. */ num_stripe_clusters = EXT4_NUM_B2C(sbi, sbi->s_stripe); if (1 << min_order < num_stripe_clusters) /* * We consider 1 order less because later we round * up the goal len to num_stripe_clusters */ min_order = fls(num_stripe_clusters) - 1; } if (1 << min_order < ac->ac_o_ex.fe_len) min_order = fls(ac->ac_o_ex.fe_len); start = group; end = ext4_get_groups_count(ac->ac_sb); wrap_around: for (i = order; i >= min_order; i--) { int frag_order; /* * Scale down goal len to make sure we find something * in the free fragments list. Basically, reduce * preallocations. */ ac->ac_g_ex.fe_len = 1 << i; if (num_stripe_clusters > 0) { /* * Try to round up the adjusted goal length to * stripe size (in cluster units) multiple for * efficiency. */ ac->ac_g_ex.fe_len = roundup(ac->ac_g_ex.fe_len, num_stripe_clusters); } frag_order = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); ret = ext4_mb_scan_groups_avg_frag_order_range(ac, frag_order, start, end); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; } if (start) { end = start; start = 0; goto wrap_around; } /* Reset goal length to original goal length before falling into CR_GOAL_LEN_SLOW */ ac->ac_g_ex.fe_len = ac->ac_orig_goal_len; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_failed[ac->ac_criteria]); ac->ac_criteria = CR_GOAL_LEN_SLOW; return ret; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) { if (unlikely(!test_opt2(ac->ac_sb, MB_OPTIMIZE_SCAN))) return 0; if (ac->ac_criteria >= CR_GOAL_LEN_SLOW) return 0; if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) return 0; return 1; } /* * next linear group for allocation. */ static void next_linear_group(ext4_group_t *group, ext4_group_t ngroups) { /* * Artificially restricted ngroups for non-extent * files makes group > ngroups possible on first loop. */ *group = *group + 1 >= ngroups ? 0 : *group + 1; } static int ext4_mb_scan_groups_linear(struct ext4_allocation_context *ac, ext4_group_t ngroups, ext4_group_t *start, ext4_group_t count) { int ret, i; enum criteria cr = ac->ac_criteria; struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group = *start; for (i = 0; i < count; i++, next_linear_group(&group, ngroups)) { ret = ext4_mb_scan_group(ac, group); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; cond_resched(); } *start = group; if (count == ngroups) ac->ac_criteria++; /* Processed all groups and haven't found blocks */ if (sbi->s_mb_stats && i == ngroups) atomic64_inc(&sbi->s_bal_cX_failed[cr]); return 0; } static int ext4_mb_scan_groups(struct ext4_allocation_context *ac) { int ret = 0; ext4_group_t start; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_group_t ngroups = ext4_get_groups_count(ac->ac_sb); /* non-extent files are limited to low blocks/groups */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) ngroups = sbi->s_blockfile_groups; /* searching for the right group start from the goal value specified */ start = ac->ac_g_ex.fe_group; ac->ac_prefetch_grp = start; ac->ac_prefetch_nr = 0; if (!should_optimize_scan(ac)) return ext4_mb_scan_groups_linear(ac, ngroups, &start, ngroups); /* * Optimized scanning can return non adjacent groups which can cause * seek overhead for rotational disks. So try few linear groups before * trying optimized scan. */ if (sbi->s_mb_max_linear_groups) ret = ext4_mb_scan_groups_linear(ac, ngroups, &start, sbi->s_mb_max_linear_groups); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; switch (ac->ac_criteria) { case CR_POWER2_ALIGNED: return ext4_mb_scan_groups_p2_aligned(ac, start); case CR_GOAL_LEN_FAST: return ext4_mb_scan_groups_goal_fast(ac, start); case CR_BEST_AVAIL_LEN: return ext4_mb_scan_groups_best_avail(ac, start); default: /* * TODO: For CR_GOAL_LEN_SLOW, we can arrange groups in an * rb tree sorted by bb_free. But until that happens, we should * never come here. */ WARN_ON(1); } return 0; } /* * Cache the order of the largest free extent we have available in this block * group. */ static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int new, old = grp->bb_largest_free_order; for (new = MB_NUM_ORDERS(sb) - 1; new >= 0; new--) if (grp->bb_counters[new] > 0) break; /* No need to move between order lists? */ if (new == old) return; if (old >= 0) { struct xarray *xa = &sbi->s_mb_largest_free_orders[old]; if (!xa_empty(xa) && xa_load(xa, grp->bb_group)) xa_erase(xa, grp->bb_group); } grp->bb_largest_free_order = new; if (test_opt2(sb, MB_OPTIMIZE_SCAN) && new >= 0 && grp->bb_free) { /* * Cannot use __GFP_NOFAIL because we hold the group lock. * Although allocation for insertion may fails, it's not fatal * as we have linear traversal to fall back on. */ int err = xa_insert(&sbi->s_mb_largest_free_orders[new], grp->bb_group, grp, GFP_ATOMIC); if (err) mb_debug(sb, "insert group: %u to s_mb_largest_free_orders[%d] failed, err %d", grp->bb_group, new, err); } } static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_grpblk_t first; ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); /* initialize buddy from bitmap which is aggregation * of on-disk bitmap and preallocations */ i = mb_find_next_zero_bit(bitmap, max, 0); grp->bb_first_free = i; while (i < max) { fragments++; first = i; i = mb_find_next_bit(bitmap, max, i); len = i - first; free += len; if (len > 1) ext4_mb_mark_free_simple(sb, buddy, first, len, grp); else grp->bb_counters[0]++; if (i < max) i = mb_find_next_zero_bit(bitmap, max, i); } grp->bb_fragments = fragments; if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, "block bitmap and bg descriptor " "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); } static void mb_regenerate_buddy(struct ext4_buddy *e4b) { int count; int order = 1; void *buddy; while ((buddy = mb_find_buddy(e4b, order++, &count))) mb_set_bits(buddy, 0, count); e4b->bd_info->bb_fragments = 0; memset(e4b->bd_info->bb_counters, 0, sizeof(*e4b->bd_info->bb_counters) * (e4b->bd_sb->s_blocksize_bits + 2)); ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); } /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are * stored in the inode as * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. * So for each group we take up 2 blocks. A page can * contain blocks_per_page (PAGE_SIZE / blocksize) blocks. * So it can have information regarding groups_per_page which * is blocks_per_page/2 * * Locking note: This routine takes the block group lock of all groups * for this page; do not hold this lock when calling this routine! */ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp) { ext4_group_t ngroups; unsigned int blocksize; int blocks_per_page; int groups_per_page; int err = 0; int i; ext4_group_t first_group, group; int first_block; struct super_block *sb; struct buffer_head *bhs; struct buffer_head **bh = NULL; struct inode *inode; char *data; char *bitmap; struct ext4_group_info *grinfo; inode = folio->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = i_blocksize(inode); blocks_per_page = PAGE_SIZE / blocksize; mb_debug(sb, "init folio %lu\n", folio->index); groups_per_page = blocks_per_page >> 1; if (groups_per_page == 0) groups_per_page = 1; /* allocate buffer_heads to read bitmaps */ if (groups_per_page > 1) { i = sizeof(struct buffer_head *) * groups_per_page; bh = kzalloc(i, gfp); if (bh == NULL) return -ENOMEM; } else bh = &bhs; first_group = folio->index * blocks_per_page / 2; /* read all groups the folio covers into the cache */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { if (group >= ngroups) break; grinfo = ext4_get_group_info(sb, group); if (!grinfo) continue; /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so * we must skip all initialized uptodate buddies on the folio, * which may be currently in use by an allocating task. */ if (folio_test_uptodate(folio) && !EXT4_MB_GRP_NEED_INIT(grinfo)) { bh[i] = NULL; continue; } bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; goto out; } mb_debug(sb, "read bitmap for group %u\n", group); } /* wait for I/O completion */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { int err2; if (!bh[i]) continue; err2 = ext4_wait_block_bitmap(sb, group, bh[i]); if (!err) err = err2; } first_block = folio->index * blocks_per_page; for (i = 0; i < blocks_per_page; i++) { group = (first_block + i) >> 1; if (group >= ngroups) break; if (!bh[group - first_group]) /* skip initialized uptodate buddy */ continue; if (!buffer_verified(bh[group - first_group])) /* Skip faulty bitmaps */ continue; err = 0; /* * data carry information regarding this * particular group in the format specified * above * */ data = folio_address(folio) + (i * blocksize); bitmap = bh[group - first_group]->b_data; /* * We place the buddy block and bitmap block * close together */ grinfo = ext4_get_group_info(sb, group); if (!grinfo) { err = -EFSCORRUPTED; goto out; } if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in folio %lu/%x\n", group, folio->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * (MB_NUM_ORDERS(sb))); /* * incore got set to the group block bitmap below */ ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); ext4_mb_generate_buddy(sb, data, incore, group, grinfo); ext4_unlock_group(sb, group); incore = NULL; } else { /* this is block of bitmap */ BUG_ON(incore != NULL); mb_debug(sb, "put bitmap for group %u in folio %lu/%x\n", group, folio->index, i * blocksize); trace_ext4_mb_bitmap_load(sb, group); /* see comments in ext4_mb_put_pa() */ ext4_lock_group(sb, group); memcpy(data, bitmap, blocksize); /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root)); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be * generated using this */ incore = data; } } folio_mark_uptodate(folio); out: if (bh) { for (i = 0; i < groups_per_page; i++) brelse(bh[i]); if (bh != &bhs) kfree(bh); } return err; } /* * Lock the buddy and bitmap pages. This make sure other parallel init_group * on the same buddy page doesn't happen whild holding the buddy page lock. * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap * are on the same page e4b->bd_buddy_folio is NULL and return value is 0. */ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { struct inode *inode = EXT4_SB(sb)->s_buddy_cache; int block, pnum, poff; int blocks_per_page; struct folio *folio; e4b->bd_buddy_folio = NULL; e4b->bd_bitmap_folio = NULL; blocks_per_page = PAGE_SIZE / sb->s_blocksize; /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return PTR_ERR(folio); BUG_ON(folio->mapping != inode->i_mapping); e4b->bd_bitmap_folio = folio; e4b->bd_bitmap = folio_address(folio) + (poff * sb->s_blocksize); if (blocks_per_page >= 2) { /* buddy and bitmap are on the same page */ return 0; } /* blocks_per_page == 1, hence we need another page for the buddy */ folio = __filemap_get_folio(inode->i_mapping, block + 1, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return PTR_ERR(folio); BUG_ON(folio->mapping != inode->i_mapping); e4b->bd_buddy_folio = folio; return 0; } static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_folio) { folio_unlock(e4b->bd_bitmap_folio); folio_put(e4b->bd_bitmap_folio); } if (e4b->bd_buddy_folio) { folio_unlock(e4b->bd_buddy_folio); folio_put(e4b->bd_buddy_folio); } } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) { struct ext4_group_info *this_grp; struct ext4_buddy e4b; struct folio *folio; int ret = 0; might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); if (!this_grp) return -EFSCORRUPTED; /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. * The call to ext4_mb_get_buddy_page_lock will mark the * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { /* * somebody initialized the group * return without doing anything */ goto err; } folio = e4b.bd_bitmap_folio; ret = ext4_mb_init_cache(folio, NULL, gfp); if (ret) goto err; if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } if (e4b.bd_buddy_folio == NULL) { /* * If both the bitmap and buddy are in * the same page we don't need to force * init the buddy */ ret = 0; goto err; } /* init buddy cache */ folio = e4b.bd_buddy_folio; ret = ext4_mb_init_cache(folio, e4b.bd_bitmap, gfp); if (ret) goto err; if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } err: ext4_mb_put_buddy_page_lock(&e4b); return ret; } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { int blocks_per_page; int block; int pnum; int poff; struct folio *folio; int ret; struct ext4_group_info *grp; struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; might_sleep(); mb_debug(sb, "load group %u\n", group); blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); if (!grp) return -EFSCORRUPTED; e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; e4b->bd_sb = sb; e4b->bd_group = group; e4b->bd_buddy_folio = NULL; e4b->bd_bitmap_folio = NULL; if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { /* * we need full data about the group * to make a good selection */ ret = ext4_mb_init_group(sb, group, gfp); if (ret) return ret; } /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; /* Avoid locking the folio in the fast path ... */ folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio)) { if (!IS_ERR(folio)) /* * drop the folio reference and try * to get the folio with lock. If we * are not uptodate that implies * somebody just created the folio but * is yet to initialize it. So * wait for it to initialize. */ folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (!IS_ERR(folio)) { if (WARN_RATELIMIT(folio->mapping != inode->i_mapping, "ext4: bitmap's mapping != inode->i_mapping\n")) { /* should never happen */ folio_unlock(folio); ret = -EINVAL; goto err; } if (!folio_test_uptodate(folio)) { ret = ext4_mb_init_cache(folio, NULL, gfp); if (ret) { folio_unlock(folio); goto err; } mb_cmp_bitmaps(e4b, folio_address(folio) + (poff * sb->s_blocksize)); } folio_unlock(folio); } } if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto err; } if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } /* Folios marked accessed already */ e4b->bd_bitmap_folio = folio; e4b->bd_bitmap = folio_address(folio) + (poff * sb->s_blocksize); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio)) { if (!IS_ERR(folio)) folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (!IS_ERR(folio)) { if (WARN_RATELIMIT(folio->mapping != inode->i_mapping, "ext4: buddy bitmap's mapping != inode->i_mapping\n")) { /* should never happen */ folio_unlock(folio); ret = -EINVAL; goto err; } if (!folio_test_uptodate(folio)) { ret = ext4_mb_init_cache(folio, e4b->bd_bitmap, gfp); if (ret) { folio_unlock(folio); goto err; } } folio_unlock(folio); } } if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto err; } if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } /* Folios marked accessed already */ e4b->bd_buddy_folio = folio; e4b->bd_buddy = folio_address(folio) + (poff * sb->s_blocksize); return 0; err: if (!IS_ERR_OR_NULL(folio)) folio_put(folio); if (e4b->bd_bitmap_folio) folio_put(e4b->bd_bitmap_folio); e4b->bd_buddy = NULL; e4b->bd_bitmap = NULL; return ret; } static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) { return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS); } static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_folio) folio_put(e4b->bd_bitmap_folio); if (e4b->bd_buddy_folio) folio_put(e4b->bd_buddy_folio); } static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { int order = 1, max; void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(block >= (1 << (e4b->bd_blkbits + 3))); while (order <= e4b->bd_blkbits + 1) { bb = mb_find_buddy(e4b, order, &max); if (!mb_test_bit(block >> order, bb)) { /* this block is part of buddy of order 'order' */ return order; } order++; } return 0; } static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); *addr = 0; cur += 32; continue; } mb_clear_bit(cur, bm); cur++; } } /* clear bits in given range * will return first found zero bit if any, -1 otherwise */ static int mb_test_and_clear_bits(void *bm, int cur, int len) { __u32 *addr; int zero_bit = -1; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); if (*addr != (__u32)(-1) && zero_bit == -1) zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); *addr = 0; cur += 32; continue; } if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) zero_bit = cur; cur++; } return zero_bit; } void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: set whole word at once */ addr = bm + (cur >> 3); *addr = 0xffffffff; cur += 32; continue; } mb_set_bit(cur, bm); cur++; } } static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) { if (mb_test_bit(*bit + side, bitmap)) { mb_clear_bit(*bit, bitmap); (*bit) -= side; return 1; } else { (*bit) += side; mb_set_bit(*bit, bitmap); return -1; } } static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) { int max; int order = 1; void *buddy = mb_find_buddy(e4b, order, &max); while (buddy) { void *buddy2; /* Bits in range [first; last] are known to be set since * corresponding blocks were allocated. Bits in range * (first; last) will stay set because they form buddies on * upper layer. We just deal with borders if they don't * align with upper layer and then go up. * Releasing entire group is all about clearing * single bit of highest order buddy. */ /* Example: * --------------------------------- * | 1 | 1 | 1 | 1 | * --------------------------------- * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | * --------------------------------- * 0 1 2 3 4 5 6 7 * \_____________________/ * * Neither [1] nor [6] is aligned to above layer. * Left neighbour [0] is free, so mark it busy, * decrease bb_counters and extend range to * [0; 6] * Right neighbour [7] is busy. It can't be coaleasced with [6], so * mark [6] free, increase bb_counters and shrink range to * [0; 5]. * Then shift range to [0; 2], go up and do the same. */ if (first & 1) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); if (!(last & 1)) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); if (first > last) break; order++; buddy2 = mb_find_buddy(e4b, order, &max); if (!buddy2) { mb_clear_bits(buddy, first, last - first + 1); e4b->bd_info->bb_counters[order - 1] += last - first + 1; break; } first >>= 1; last >>= 1; buddy = buddy2; } } static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int left_is_free = 0; int right_is_free = 0; int block; int last = first + count - 1; struct super_block *sb = e4b->bd_sb; if (WARN_ON(count == 0)) return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return; mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ if (first != 0) left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); if (unlikely(block != -1)) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; /* * Fastcommit replay can free already freed blocks which * corrupts allocation info. Regenerate it. */ if (sbi->s_mount_state & EXT4_FC_REPLAY) { mb_regenerate_buddy(e4b); goto check; } blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing already freed block (bit %u); block bitmap corrupt.", block); return; } this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free += count; if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; else if (!left_is_free && !right_is_free) e4b->bd_info->bb_fragments++; /* buddy[0] == bd_bitmap is a special case, so handle * it right away and let mb_buddy_mark_free stay free of * zero order checks. * Check if neighbours are to be coaleasced, * adjust bitmap bb_counters and borders appropriately. */ if (first & 1) { first += !left_is_free; e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; } if (!(last & 1)) { last -= !right_is_free; e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; } if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); check: mb_check_buddy(e4b); } static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int max, order, next; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; return 0; } /* find actual order */ order = mb_find_order_for_block(e4b, block); ex->fe_len = (1 << order) - (block & ((1 << order) - 1)); ex->fe_start = block; ex->fe_group = e4b->bd_group; block = block >> order; while (needed > ex->fe_len && mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; next = (block + 1) * (1 << order); if (mb_test_bit(next, e4b->bd_bitmap)) break; order = mb_find_order_for_block(e4b, next); block = next >> order; ex->fe_len += 1 << order; } if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0, "corruption or bug in mb_find_extent " "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", block, order, needed, ex->fe_group, ex->fe_start, ex->fe_len, ex->fe_logical); ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; } return ex->fe_len; } static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) { int ord; int mlen = 0; int max = 0; int start = ex->fe_start; int len = ex->fe_len; unsigned ret = 0; int len0 = len; void *buddy; int ord_start, ord_end; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free -= len; if (e4b->bd_info->bb_first_free == start) e4b->bd_info->bb_first_free += len; /* let's maintain fragments counter */ if (start != 0) mlen = !mb_test_bit(start - 1, e4b->bd_bitmap); if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0]) max = !mb_test_bit(start + len, e4b->bd_bitmap); if (mlen && max) e4b->bd_info->bb_fragments++; else if (!mlen && !max) e4b->bd_info->bb_fragments--; /* let's maintain buddy itself */ while (len) { ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; buddy = mb_find_buddy(e4b, ord, &max); BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; start += mlen; len -= mlen; BUG_ON(len < 0); continue; } /* store for history */ if (ret == 0) ret = len | (ord << 16); BUG_ON(ord <= 0); buddy = mb_find_buddy(e4b, ord, &max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; ord_start = (start >> ord) << ord; ord_end = ord_start + (1 << ord); /* first chunk */ if (start > ord_start) ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy, ord_start, start - ord_start, e4b->bd_info); /* last chunk */ if (start + len < ord_end) { ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy, start + len, ord_end - (start + len), e4b->bd_info); break; } len = start + len - ord_end; start = ord_end; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info); mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; } /* * Must be called under group lock! */ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int ret; BUG_ON(ac->ac_b_ex.fe_group != e4b->bd_group); BUG_ON(ac->ac_status == AC_STATUS_FOUND); ac->ac_b_ex.fe_len = min(ac->ac_b_ex.fe_len, ac->ac_g_ex.fe_len); ac->ac_b_ex.fe_logical = ac->ac_g_ex.fe_logical; ret = mb_mark_used(e4b, &ac->ac_b_ex); /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; ac->ac_status = AC_STATUS_FOUND; ac->ac_tail = ret & 0xffff; ac->ac_buddy = ret >> 16; /* * take the page reference. We want the page to be pinned * so that we don't get a ext4_mb_init_cache_call for this * group until we update the bitmap. That would mean we * double allocate blocks. The reference is dropped * in ext4_mb_release_context */ ac->ac_bitmap_folio = e4b->bd_bitmap_folio; folio_get(ac->ac_bitmap_folio); ac->ac_buddy_folio = e4b->bd_buddy_folio; folio_get(ac->ac_buddy_folio); /* store last allocated for subsequent stream allocation */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { int hash = ac->ac_inode->i_ino % sbi->s_mb_nr_global_goals; WRITE_ONCE(sbi->s_mb_last_groups[hash], ac->ac_f_ex.fe_group); } /* * As we've just preallocated more space than * user requested originally, we store allocated * space in a special descriptor. */ if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) ext4_mb_new_preallocation(ac); } static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; if (ac->ac_status == AC_STATUS_FOUND) return; /* * We don't want to scan for a whole year */ if (ac->ac_found > sbi->s_mb_max_to_scan && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { ac->ac_status = AC_STATUS_BREAK; return; } /* * Haven't found good chunk so far, let's continue */ if (bex->fe_len < gex->fe_len) return; if (finish_group || ac->ac_found > sbi->s_mb_min_to_scan) ext4_mb_use_best_found(ac, e4b); } /* * The routine checks whether found extent is good enough. If it is, * then the extent gets marked used and flag is set to the context * to stop scanning. Otherwise, the extent is compared with the * previous found extent and if new one is better, then it's stored * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * * The algorithm used is roughly as follows: * * * If free extent found is exactly as big as goal, then * stop the scan and use it immediately * * * If free extent found is smaller than goal, then keep retrying * upto a max of sbi->s_mb_max_to_scan times (default 200). After * that stop scanning and use whatever we have. * * * If free extent found is bigger than goal, then keep retrying * upto a max of sbi->s_mb_min_to_scan times (default 10) before * stopping the scan and using the extent. * * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, struct ext4_free_extent *ex, struct ext4_buddy *e4b) { struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; BUG_ON(ex->fe_len <= 0); BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ac->ac_status != AC_STATUS_CONTINUE); ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; /* * The special case - take what you catch first */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_FIRST)) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * Let's check whether the chuck is good enough */ if (ex->fe_len == gex->fe_len) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * If this is first found extent, just store it in the context */ if (bex->fe_len == 0) { *bex = *ex; return; } /* * If new found extent is better, store it in the context */ if (bex->fe_len < gex->fe_len) { /* if the request isn't satisfied, any found extent * larger than previous best one is better */ if (ex->fe_len > bex->fe_len) *bex = *ex; } else if (ex->fe_len > gex->fe_len) { /* if the request is satisfied, then we try to find * an extent that still satisfy the request, but is * smaller than previous one */ if (ex->fe_len < bex->fe_len) *bex = *ex; } ext4_mb_check_limits(ac, e4b, 0); } static noinline_for_stack void ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; ext4_group_t group = ex.fe_group; int max; int err; BUG_ON(ex.fe_len <= 0); err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return; ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) goto out; max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); } static noinline_for_stack int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!grp) return -EFSCORRUPTED; if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) goto out; max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == EXT4_NUM_B2C(sbi, sbi->s_stripe)) { ext4_fsblk_t start; start = ext4_grp_offs_to_block(ac->ac_sb, &ex); /* use do_div to get remainder (would be 64-bit modulo) */ if (do_div(start, sbi->s_stripe) == 0) { ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } } else if (max >= ac->ac_g_ex.fe_len) { BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } else if (max > 0 && (ac->ac_flags & EXT4_MB_HINT_MERGE)) { /* Sometimes, caller may want to merge even small * number of blocks to an existing extent */ BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } /* * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ static noinline_for_stack void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_group_info *grp = e4b->bd_info; void *buddy; int i; int k; int max; BUG_ON(ac->ac_2order <= 0); for (i = ac->ac_2order; i < MB_NUM_ORDERS(sb); i++) { if (grp->bb_counters[i] == 0) continue; buddy = mb_find_buddy(e4b, i, &max); if (WARN_RATELIMIT(buddy == NULL, "ext4: mb_simple_scan_group: mb_find_buddy failed, (%d)\n", i)) continue; k = mb_find_next_zero_bit(buddy, max, 0); if (k >= max) { ext4_mark_group_bitmap_corrupted(ac->ac_sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, "%d free clusters of order %d. But found 0", grp->bb_counters[i], i); break; } ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; ac->ac_b_ex.fe_len = 1 << i; ac->ac_b_ex.fe_start = k << i; ac->ac_b_ex.fe_group = e4b->bd_group; ext4_mb_use_best_found(ac, e4b); BUG_ON(ac->ac_f_ex.fe_len != ac->ac_g_ex.fe_len); if (EXT4_SB(sb)->s_mb_stats) atomic_inc(&EXT4_SB(sb)->s_bal_2orders); break; } } /* * The routine scans the group and measures all found extents. * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ static noinline_for_stack void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; int i, j, freelen; int free; free = e4b->bd_info->bb_free; if (WARN_ON(free <= 0)) return; i = e4b->bd_info->bb_first_free; while (free && ac->ac_status == AC_STATUS_CONTINUE) { i = mb_find_next_zero_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) { /* * IF we have corrupt bitmap, we won't find any * free blocks even though group info says we * have free blocks */ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But bitmap says 0", free); break; } if (!ext4_mb_cr_expensive(ac->ac_criteria)) { /* * In CR_GOAL_LEN_FAST and CR_BEST_AVAIL_LEN, we are * sure that this group will have a large enough * continuous free extent, so skip over the smaller free * extents */ j = mb_find_next_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); freelen = j - i; if (freelen < ac->ac_g_ex.fe_len) { i = j; free -= freelen; continue; } } mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); if (WARN_ON(ex.fe_len <= 0)) break; if (free < ex.fe_len) { ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit * without claiming the space. */ break; } ex.fe_logical = 0xDEADC0DE; /* debug value */ ext4_mb_measure_extent(ac, &ex, e4b); i += ex.fe_len; free -= ex.fe_len; } ext4_mb_check_limits(ac, e4b, 1); } /* * This is a special case for storages like raid5 * we try to find stripe-aligned chunks for stripe-size-multiple requests */ static noinline_for_stack void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; ext4_fsblk_t first_group_block; ext4_fsblk_t a; ext4_grpblk_t i, stripe; int max; BUG_ON(sbi->s_stripe == 0); /* find first stripe-aligned block in group */ first_group_block = ext4_group_first_block_no(sb, e4b->bd_group); a = first_group_block + sbi->s_stripe - 1; do_div(a, sbi->s_stripe); i = (a * sbi->s_stripe) - first_group_block; stripe = EXT4_NUM_B2C(sbi, sbi->s_stripe); i = EXT4_B2C(sbi, i); while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { max = mb_find_extent(e4b, i, stripe, &ex); if (max >= stripe) { ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; ex.fe_logical = 0xDEADF00D; /* debug value */ ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); break; } } i += stripe; } } static void __ext4_mb_scan_group(struct ext4_allocation_context *ac) { bool is_stripe_aligned; struct ext4_sb_info *sbi; enum criteria cr = ac->ac_criteria; ac->ac_groups_scanned++; if (cr == CR_POWER2_ALIGNED) return ext4_mb_simple_scan_group(ac, ac->ac_e4b); sbi = EXT4_SB(ac->ac_sb); is_stripe_aligned = false; if ((sbi->s_stripe >= sbi->s_cluster_ratio) && !(ac->ac_g_ex.fe_len % EXT4_NUM_B2C(sbi, sbi->s_stripe))) is_stripe_aligned = true; if ((cr == CR_GOAL_LEN_FAST || cr == CR_BEST_AVAIL_LEN) && is_stripe_aligned) ext4_mb_scan_aligned(ac, ac->ac_e4b); if (ac->ac_status == AC_STATUS_CONTINUE) ext4_mb_complex_scan_group(ac, ac->ac_e4b); } /* * This is also called BEFORE we load the buddy bitmap. * Returns either 1 or 0 indicating that the group is either suitable * for the allocation or not. */ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr) { ext4_grpblk_t free, fragments; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < CR_POWER2_ALIGNED || cr >= EXT4_MB_NUM_CRS); if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; if (free == 0) return false; fragments = grp->bb_fragments; if (fragments == 0) return false; switch (cr) { case CR_POWER2_ALIGNED: BUG_ON(ac->ac_2order == 0); /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) && ((group % flex_size) == 0)) return false; if (free < ac->ac_g_ex.fe_len) return false; if (ac->ac_2order >= MB_NUM_ORDERS(ac->ac_sb)) return true; if (grp->bb_largest_free_order < ac->ac_2order) return false; return true; case CR_GOAL_LEN_FAST: case CR_BEST_AVAIL_LEN: if ((free / fragments) >= ac->ac_g_ex.fe_len) return true; break; case CR_GOAL_LEN_SLOW: if (free >= ac->ac_g_ex.fe_len) return true; break; case CR_ANY_FREE: return true; default: BUG(); } return false; } /* * This could return negative error code if something goes wrong * during ext4_mb_init_group(). This should not be called with * ext4_lock_group() held. * * Note: because we are conditionally operating with the group lock in * the EXT4_MB_STRICT_CHECK case, we need to fake out sparse in this * function using __acquire and __release. This means we need to be * super careful before messing with the error path handling via "goto * out"! */ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr) { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; if (!grp) return -EFSCORRUPTED; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) { ext4_lock_group(sb, group); __release(ext4_group_lock_ptr(sb, group)); } free = grp->bb_free; if (free == 0) goto out; /* * In all criterias except CR_ANY_FREE we try to avoid groups that * can't possibly satisfy the full goal request due to insufficient * free blocks. */ if (cr < CR_ANY_FREE && free < ac->ac_g_ex.fe_len) goto out; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) goto out; if (should_lock) { __acquire(ext4_group_lock_ptr(sb, group)); ext4_unlock_group(sb, group); } /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; /* * CR_POWER2_ALIGNED/CR_GOAL_LEN_FAST is a very optimistic * search to find large good chunks almost for free. If buddy * data is not ready, then this optimization makes no sense. But * we never skip the first block group in a flex_bg, since this * gets used for metadata block allocation, and we want to make * sure we locate metadata blocks in the first block group in * the flex_bg if possible. */ if (!ext4_mb_cr_expensive(cr) && (!sbi->s_log_groups_per_flex || ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) return 0; ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } if (should_lock) { ext4_lock_group(sb, group); __release(ext4_group_lock_ptr(sb, group)); } ret = ext4_mb_good_group(ac, group, cr); out: if (should_lock) { __acquire(ext4_group_lock_ptr(sb, group)); ext4_unlock_group(sb, group); } return ret; } /* * Start prefetching @nr block bitmaps starting at @group. * Return the next group which needs to be prefetched. */ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct buffer_head *bh; struct blk_plug plug; blk_start_plug(&plug); while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); /* * Prefetch block groups with free blocks; but don't * bother if it is marked uninitialized on disk, since * it won't require I/O to read. Also only try to * prefetch once, so we avoid getblk() call, which can * be expensive. */ if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 ) { bh = ext4_read_block_bitmap_nowait(sb, group, true); if (bh && !IS_ERR(bh)) { if (!buffer_uptodate(bh) && cnt) (*cnt)++; brelse(bh); } } if (++group >= ngroups) group = 0; } blk_finish_plug(&plug); return group; } /* * Batch reads of the block allocation bitmaps to get * multiple READs in flight; limit prefetching at inexpensive * CR, otherwise mballoc can spend a lot of time loading * imperfect groups */ static void ext4_mb_might_prefetch(struct ext4_allocation_context *ac, ext4_group_t group) { struct ext4_sb_info *sbi; if (ac->ac_prefetch_grp != group) return; sbi = EXT4_SB(ac->ac_sb); if (ext4_mb_cr_expensive(ac->ac_criteria) || ac->ac_prefetch_ios < sbi->s_mb_prefetch_limit) { unsigned int nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(ac->ac_sb)) { nr = 1 << sbi->s_log_groups_per_flex; nr -= group & (nr - 1); nr = umin(nr, sbi->s_mb_prefetch); } ac->ac_prefetch_nr = nr; ac->ac_prefetch_grp = ext4_mb_prefetch(ac->ac_sb, group, nr, &ac->ac_prefetch_ios); } } /* * Prefetching reads the block bitmap into the buffer cache; but we * need to make sure that the buddy bitmap in the page cache has been * initialized. Note that ext4_mb_init_group() will block if the I/O * is not yet completed, or indeed if it was not initiated by * ext4_mb_prefetch did not start the I/O. * * TODO: We should actually kick off the buddy bitmap setup in a work * queue when the buffer I/O is completed, so that we don't block * waiting for the block allocation bitmap read to finish when * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). */ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr) { struct ext4_group_desc *gdp; struct ext4_group_info *grp; while (nr-- > 0) { if (!group) group = ext4_get_groups_count(sb); group--; gdp = ext4_get_group_desc(sb, group, NULL); grp = ext4_get_group_info(sb, group); if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0) { if (ext4_mb_init_group(sb, group, GFP_NOFS)) break; } } } static int ext4_mb_scan_group(struct ext4_allocation_context *ac, ext4_group_t group) { int ret; struct super_block *sb = ac->ac_sb; enum criteria cr = ac->ac_criteria; ext4_mb_might_prefetch(ac, group); /* prevent unnecessary buddy loading. */ if (cr < CR_ANY_FREE && spin_is_locked(ext4_group_lock_ptr(sb, group))) return 0; /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!ac->ac_first_err) ac->ac_first_err = ret; return 0; } ret = ext4_mb_load_buddy(sb, group, ac->ac_e4b); if (ret) return ret; /* skip busy group */ if (cr >= CR_ANY_FREE) ext4_lock_group(sb, group); else if (!ext4_try_lock_group(sb, group)) goto out_unload; /* We need to check again after locking the block group. */ if (unlikely(!ext4_mb_good_group(ac, group, cr))) goto out_unlock; __ext4_mb_scan_group(ac); out_unlock: ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(ac->ac_e4b); return ret; } static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t i; int err = 0; struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ err = ext4_mb_find_by_goal(ac, &e4b); if (err || ac->ac_status == AC_STATUS_FOUND) goto out; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) goto out; /* * ac->ac_2order is set only if the fe_len is a power of 2 * if ac->ac_2order is set we also set criteria to CR_POWER2_ALIGNED * so that we try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); ac->ac_2order = 0; /* * We search using buddy data only if the order of the request * is greater than equal to the sbi_s_mb_order2_reqs * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req * We also support searching for power-of-two requests only for * requests upto maximum buddy size we have constructed. */ if (i >= sbi->s_mb_order2_reqs && i <= MB_NUM_ORDERS(sb)) { if (is_power_of_2(ac->ac_g_ex.fe_len)) ac->ac_2order = array_index_nospec(i - 1, MB_NUM_ORDERS(sb)); } /* if stream allocation is enabled, use global goal */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { int hash = ac->ac_inode->i_ino % sbi->s_mb_nr_global_goals; ac->ac_g_ex.fe_group = READ_ONCE(sbi->s_mb_last_groups[hash]); ac->ac_g_ex.fe_start = -1; ac->ac_flags &= ~EXT4_MB_HINT_TRY_GOAL; } /* * Let's just scan groups to find more-less suitable blocks We * start with CR_GOAL_LEN_FAST, unless it is power of 2 * aligned, in which case let's do that faster approach first. */ ac->ac_criteria = CR_GOAL_LEN_FAST; if (ac->ac_2order) ac->ac_criteria = CR_POWER2_ALIGNED; ac->ac_e4b = &e4b; ac->ac_prefetch_ios = 0; ac->ac_first_err = 0; repeat: while (ac->ac_criteria < EXT4_MB_NUM_CRS) { err = ext4_mb_scan_groups(ac); if (err) goto out; if (ac->ac_status != AC_STATUS_CONTINUE) break; } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { /* * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { int lost; /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) */ lost = atomic_inc_return(&sbi->s_mb_lost_chunks); mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, lost); ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; ac->ac_criteria = CR_ANY_FREE; goto repeat; } } if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND) { atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]); if (ac->ac_flags & EXT4_MB_STREAM_ALLOC && ac->ac_b_ex.fe_group == ac->ac_g_ex.fe_group) atomic_inc(&sbi->s_bal_stream_goals); } out: if (!err && ac->ac_status != AC_STATUS_FOUND && ac->ac_first_err) err = ac->ac_first_err; mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, ac->ac_criteria, err); if (ac->ac_prefetch_nr) ext4_mb_prefetch_fini(sb, ac->ac_prefetch_grp, ac->ac_prefetch_nr); return err; } static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i, err; char nbuf[16]; struct ext4_buddy e4b; struct ext4_group_info *grinfo; unsigned char blocksize_bits = min_t(unsigned char, sb->s_blocksize_bits, EXT4_MAX_BLOCK_LOG_SIZE); DEFINE_RAW_FLEX(struct ext4_group_info, sg, bb_counters, EXT4_MAX_BLOCK_LOG_SIZE + 2); group--; if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (blocksize_bits + 2) * sizeof(sg->bb_counters[0]) + sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); if (!grinfo) return 0; /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { seq_printf(seq, "#%-5u: %s\n", group, ext4_decode_error(NULL, err, nbuf)); return 0; } ext4_mb_unload_buddy(&e4b); } /* * We care only about free space counters in the group info and * these are safe to access even after the buddy has been unloaded */ memcpy(sg, grinfo, i); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg->bb_free, sg->bb_fragments, sg->bb_first_free); for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg->bb_counters[i] : 0); seq_puts(seq, " ]"); if (EXT4_MB_GRP_BBITMAP_CORRUPT(sg)) seq_puts(seq, " Block bitmap corrupted!"); seq_putc(seq, '\n'); return 0; } static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, .show = ext4_mb_seq_groups_show, }; int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct ext4_sb_info *sbi = EXT4_SB(sb); seq_puts(seq, "mballoc:\n"); if (!sbi->s_mb_stats) { seq_puts(seq, "\tmb stats collection turned off.\n"); seq_puts( seq, "\tTo enable, please write \"1\" to sysfs file mb_stats.\n"); return 0; } seq_printf(seq, "\treqs: %u\n", atomic_read(&sbi->s_bal_reqs)); seq_printf(seq, "\tsuccess: %u\n", atomic_read(&sbi->s_bal_success)); seq_printf(seq, "\tgroups_scanned: %u\n", atomic_read(&sbi->s_bal_groups_scanned)); /* CR_POWER2_ALIGNED stats */ seq_puts(seq, "\tcr_p2_aligned_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_POWER2_ALIGNED])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_POWER2_ALIGNED])); /* CR_GOAL_LEN_FAST stats */ seq_puts(seq, "\tcr_goal_fast_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_GOAL_LEN_FAST])); /* CR_BEST_AVAIL_LEN stats */ seq_puts(seq, "\tcr_best_avail_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_BEST_AVAIL_LEN])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_BEST_AVAIL_LEN])); /* CR_GOAL_LEN_SLOW stats */ seq_puts(seq, "\tcr_goal_slow_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_GOAL_LEN_SLOW])); /* CR_ANY_FREE stats */ seq_puts(seq, "\tcr_any_free_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_ANY_FREE])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read(&sbi->s_bal_cX_groups_considered[CR_ANY_FREE])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_ANY_FREE])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_ANY_FREE])); /* Aggregates */ seq_printf(seq, "\textents_scanned: %u\n", atomic_read(&sbi->s_bal_ex_scanned)); seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals)); seq_printf(seq, "\t\tstream_goal_hits: %u\n", atomic_read(&sbi->s_bal_stream_goals)); seq_printf(seq, "\t\tlen_goal_hits: %u\n", atomic_read(&sbi->s_bal_len_goals)); seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders)); seq_printf(seq, "\t\tbreaks: %u\n", atomic_read(&sbi->s_bal_breaks)); seq_printf(seq, "\t\tlost: %u\n", atomic_read(&sbi->s_mb_lost_chunks)); seq_printf(seq, "\tbuddies_generated: %u/%u\n", atomic_read(&sbi->s_mb_buddies_generated), ext4_get_groups_count(sb)); seq_printf(seq, "\tbuddies_time_used: %llu\n", atomic64_read(&sbi->s_mb_generation_time)); seq_printf(seq, "\tpreallocated: %u\n", atomic_read(&sbi->s_mb_preallocated)); seq_printf(seq, "\tdiscarded: %u\n", atomic_read(&sbi->s_mb_discarded)); return 0; } static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); } static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); } static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) { struct super_block *sb = pde_data(file_inode(seq->file)); struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; unsigned int count; unsigned long idx; position--; if (position >= MB_NUM_ORDERS(sb)) { position -= MB_NUM_ORDERS(sb); if (position == 0) seq_puts(seq, "avg_fragment_size_lists:\n"); count = 0; xa_for_each(&sbi->s_mb_avg_fragment_size[position], idx, grp) count++; seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); return 0; } if (position == 0) { seq_printf(seq, "optimize_scan: %d\n", test_opt2(sb, MB_OPTIMIZE_SCAN) ? 1 : 0); seq_puts(seq, "max_free_order_lists:\n"); } count = 0; xa_for_each(&sbi->s_mb_largest_free_orders[position], idx, grp) count++; seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); return 0; } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_structs_summary_ops = { .start = ext4_mb_seq_structs_summary_start, .next = ext4_mb_seq_structs_summary_next, .stop = ext4_mb_seq_structs_summary_stop, .show = ext4_mb_seq_structs_summary_show, }; static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; BUG_ON(!cachep); return cachep; } /* * Allocate the top-level s_group_info array for the specified number * of groups */ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); if (size <= sbi->s_group_info_size) return 0; size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); new_groupinfo = kvzalloc(size, GFP_KERNEL); if (!new_groupinfo) { ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } rcu_read_lock(); old_groupinfo = rcu_dereference(sbi->s_group_info); if (old_groupinfo) memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); rcu_read_unlock(); rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); if (old_groupinfo) ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; } /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { int i; int metalen = 0; int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. * If it's true, we have to allocate a new table of pointers * to ext4_group_info structures */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); meta_group_info = kmalloc(metalen, GFP_NOFS); if (meta_group_info == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate mem " "for a buddy group"); return -ENOMEM; } rcu_read_lock(); rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; rcu_read_unlock(); } meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); /* * initialize bb_free to be able to skip * empty groups without initialization */ if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { meta_group_info[i]->bb_free = ext4_free_clusters_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = ext4_free_group_clusters(sb, desc); } INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { struct ext4_group_info ***group_info; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); kfree(group_info[idx]); group_info[idx] = NULL; rcu_read_unlock(); } return -ENOMEM; } /* ext4_mb_add_groupinfo */ static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); if (err) return err; sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); goto err_freesgi; } /* To avoid potentially colliding with an valid on-disk inode number, * use EXT4_BAD_INO for the buddy cache inode number. This inode is * not in the inode hash, so it should never be found by iget(), but * this will avoid confusion if it ever shows up during debugging. */ sbi->s_buddy_cache->i_ino = EXT4_BAD_INO; EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { cond_resched(); desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i); goto err_freebuddy; } if (ext4_mb_add_groupinfo(sb, i, desc) != 0) goto err_freebuddy; } if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO. * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is * unsigned integer, so the maximum shift is 32. */ if (sbi->s_es->s_log_groups_per_flex >= 32) { ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); goto err_freebuddy; } sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32; } if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) sbi->s_mb_prefetch = ext4_get_groups_count(sb); /* * now many real IOs to prefetch within a single allocation at * CR_POWER2_ALIGNED. Given CR_POWER2_ALIGNED is an CPU-related * optimization we shouldn't try to load too many groups, at some point * we should start to use what we've got in memory. * with an average random access time 5ms, it'd take a second to get * 200 groups (* N with flex_bg), so let's make this limit 4 */ sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); return 0; err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); if (grp) kmem_cache_free(cachep, grp); } i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) kfree(group_info[i]); rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: rcu_read_lock(); kvfree(rcu_dereference(sbi->s_group_info)); rcu_read_unlock(); return -ENOMEM; } static void ext4_groupinfo_destroy_slabs(void) { int i; for (i = 0; i < NR_GRPINFO_CACHES; i++) { kmem_cache_destroy(ext4_groupinfo_caches[i]); ext4_groupinfo_caches[i] = NULL; } } static int ext4_groupinfo_create_slab(size_t size) { static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex); int slab_size; int blocksize_bits = order_base_2(size); int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep; if (cache_index >= NR_GRPINFO_CACHES) return -EINVAL; if (unlikely(cache_index < 0)) cache_index = 0; mutex_lock(&ext4_grpinfo_slab_create_mutex); if (ext4_groupinfo_caches[cache_index]) { mutex_unlock(&ext4_grpinfo_slab_create_mutex); return 0; /* Already created */ } slab_size = offsetof(struct ext4_group_info, bb_counters[blocksize_bits + 2]); cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index], slab_size, 0, SLAB_RECLAIM_ACCOUNT, NULL); ext4_groupinfo_caches[cache_index] = cachep; mutex_unlock(&ext4_grpinfo_slab_create_mutex); if (!cachep) { printk(KERN_EMERG "EXT4-fs: no memory for groupinfo slab cache\n"); return -ENOMEM; } return 0; } static void ext4_discard_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_discard_work); struct super_block *sb = sbi->s_sb; struct ext4_free_data *fd, *nfd; struct ext4_buddy e4b; LIST_HEAD(discard_list); ext4_group_t grp, load_grp; int err = 0; spin_lock(&sbi->s_md_lock); list_splice_init(&sbi->s_discard_list, &discard_list); spin_unlock(&sbi->s_md_lock); load_grp = UINT_MAX; list_for_each_entry_safe(fd, nfd, &discard_list, efd_list) { /* * If filesystem is umounting or no memory or suffering * from no space, give up the discard */ if ((sb->s_flags & SB_ACTIVE) && !err && !atomic_read(&sbi->s_retry_alloc_pending)) { grp = fd->efd_group; if (grp != load_grp) { if (load_grp != UINT_MAX) ext4_mb_unload_buddy(&e4b); err = ext4_mb_load_buddy(sb, grp, &e4b); if (err) { kmem_cache_free(ext4_free_data_cachep, fd); load_grp = UINT_MAX; continue; } else { load_grp = grp; } } ext4_lock_group(sb, grp); ext4_try_to_trim_range(sb, &e4b, fd->efd_start_cluster, fd->efd_start_cluster + fd->efd_count - 1, 1); ext4_unlock_group(sb, grp); } kmem_cache_free(ext4_free_data_cachep, fd); } if (load_grp != UINT_MAX) ext4_mb_unload_buddy(&e4b); } static inline void ext4_mb_avg_fragment_size_destroy(struct ext4_sb_info *sbi) { if (!sbi->s_mb_avg_fragment_size) return; for (int i = 0; i < MB_NUM_ORDERS(sbi->s_sb); i++) xa_destroy(&sbi->s_mb_avg_fragment_size[i]); kfree(sbi->s_mb_avg_fragment_size); sbi->s_mb_avg_fragment_size = NULL; } static inline void ext4_mb_largest_free_orders_destroy(struct ext4_sb_info *sbi) { if (!sbi->s_mb_largest_free_orders) return; for (int i = 0; i < MB_NUM_ORDERS(sbi->s_sb); i++) xa_destroy(&sbi->s_mb_largest_free_orders[i]); kfree(sbi->s_mb_largest_free_orders); sbi->s_mb_largest_free_orders = NULL; } int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; unsigned offset, offset_incr; unsigned max; int ret; i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { ret = -ENOMEM; goto out; } i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { ret = -ENOMEM; goto out; } ret = ext4_groupinfo_create_slab(sb->s_blocksize); if (ret < 0) goto out; /* order 0 is regular bitmap */ sbi->s_mb_maxs[0] = sb->s_blocksize << 3; sbi->s_mb_offsets[0] = 0; i = 1; offset = 0; offset_incr = 1 << (sb->s_blocksize_bits - 1); max = sb->s_blocksize << 2; do { sbi->s_mb_offsets[i] = offset; sbi->s_mb_maxs[i] = max; offset += offset_incr; offset_incr = offset_incr >> 1; max = max >> 1; i++; } while (i < MB_NUM_ORDERS(sb)); sbi->s_mb_avg_fragment_size = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct xarray), GFP_KERNEL); if (!sbi->s_mb_avg_fragment_size) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) xa_init(&sbi->s_mb_avg_fragment_size[i]); sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct xarray), GFP_KERNEL); if (!sbi->s_mb_largest_free_orders) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) xa_init(&sbi->s_mb_largest_free_orders[i]); spin_lock_init(&sbi->s_md_lock); atomic_set(&sbi->s_mb_free_pending, 0); INIT_LIST_HEAD(&sbi->s_freed_data_list[0]); INIT_LIST_HEAD(&sbi->s_freed_data_list[1]); INIT_LIST_HEAD(&sbi->s_discard_list); INIT_WORK(&sbi->s_discard_work, ext4_discard_work); atomic_set(&sbi->s_retry_alloc_pending, 0); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; sbi->s_mb_best_avail_max_trim_order = MB_DEFAULT_BEST_AVAIL_TRIM_ORDER; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file * systems, this is probably too big (i.e, if the cluster size * is 1 megabyte, then group preallocation size becomes half a * gigabyte!). As a default, we will keep a two megabyte * group pralloc size for cluster sizes up to 64k, and after * that, we will force a minimum group preallocation size of * 32 clusters. This translates to 8 megs when the cluster * size is 256k, and 32 megs when the cluster size is 1 meg, * which seems reasonable as a default. */ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >> sbi->s_cluster_bits, 32); /* * If there is a s_stripe > 1, then we set the s_mb_group_prealloc * to the lowest multiple of s_stripe which is bigger than * the s_mb_group_prealloc as determined above. We want * the preallocation size to be an exact multiple of the * RAID stripe size so that preallocations don't fragment * the stripes. */ if (sbi->s_stripe > 1) { sbi->s_mb_group_prealloc = roundup( sbi->s_mb_group_prealloc, EXT4_NUM_B2C(sbi, sbi->s_stripe)); } sbi->s_mb_nr_global_goals = umin(num_possible_cpus(), DIV_ROUND_UP(sbi->s_groups_count, 4)); sbi->s_mb_last_groups = kcalloc(sbi->s_mb_nr_global_goals, sizeof(ext4_group_t), GFP_KERNEL); if (sbi->s_mb_last_groups == NULL) { ret = -ENOMEM; goto out; } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { ret = -ENOMEM; goto out_free_last_groups; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; lg = per_cpu_ptr(sbi->s_locality_groups, i); mutex_init(&lg->lg_mutex); for (j = 0; j < PREALLOC_TB_SIZE; j++) INIT_LIST_HEAD(&lg->lg_prealloc_list[j]); spin_lock_init(&lg->lg_prealloc_lock); } if (bdev_nonrot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) goto out_free_locality_groups; return 0; out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out_free_last_groups: kfree(sbi->s_mb_last_groups); sbi->s_mb_last_groups = NULL; out: ext4_mb_avg_fragment_size_destroy(sbi); ext4_mb_largest_free_orders_destroy(sbi); kfree(sbi->s_mb_offsets); sbi->s_mb_offsets = NULL; kfree(sbi->s_mb_maxs); sbi->s_mb_maxs = NULL; return ret; } /* need to called with the ext4 group lock held */ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; struct list_head *cur, *tmp; int count = 0; list_for_each_safe(cur, tmp, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); list_del(&pa->pa_group_list); count++; kmem_cache_free(ext4_pspace_cachep, pa); } return count; } void ext4_mb_release(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; if (test_opt(sb, DISCARD)) { /* * wait the discard work to drain all of ext4_free_data */ flush_work(&sbi->s_discard_work); WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); } if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); if (!grinfo) continue; mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); if (count) mb_debug(sb, "mballoc: %d PAs left\n", count); ext4_unlock_group(sb, i); kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); rcu_read_unlock(); } ext4_mb_avg_fragment_size_destroy(sbi); ext4_mb_largest_free_orders_destroy(sbi); kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); iput(sbi->s_buddy_cache); if (sbi->s_mb_stats) { ext4_msg(sb, KERN_INFO, "mballoc: %u blocks %u reqs (%u success)", atomic_read(&sbi->s_bal_allocated), atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, "mballoc: %u extents scanned, %u groups scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), atomic_read(&sbi->s_bal_groups_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, "mballoc: %u generated and it took %llu", atomic_read(&sbi->s_mb_buddies_generated), atomic64_read(&sbi->s_mb_generation_time)); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), atomic_read(&sbi->s_mb_discarded)); } free_percpu(sbi->s_locality_groups); kfree(sbi->s_mb_last_groups); } static inline int ext4_issue_discard(struct super_block *sb, ext4_group_t block_group, ext4_grpblk_t cluster, int count) { ext4_fsblk_t discard_block; discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) + ext4_group_first_block_no(sb, block_group)); count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } static void ext4_free_data_in_buddy(struct super_block *sb, struct ext4_free_data *entry) { struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0; mb_debug(sb, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); atomic_sub(entry->efd_count, &EXT4_SB(sb)->s_mb_free_pending); db = e4b.bd_info; /* there are blocks to put in buddy to make them really free */ count += entry->efd_count; ext4_lock_group(sb, entry->efd_group); /* Take it out of per group rb tree */ rb_erase(&entry->efd_node, &(db->bb_free_root)); mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count); /* * Clear the trimmed flag for the group so that the next * ext4_trim_fs can trim it. */ EXT4_MB_GRP_CLEAR_TRIMMED(db); if (!db->bb_free_root.rb_node) { /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() */ folio_put(e4b.bd_buddy_folio); folio_put(e4b.bd_bitmap_folio); } ext4_unlock_group(sb, entry->efd_group); ext4_mb_unload_buddy(&e4b); mb_debug(sb, "freed %d blocks in 1 structures\n", count); } /* * This function is called by the jbd2 layer once the commit has finished, * so we know we can free the blocks that were released with that commit. */ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; LIST_HEAD(freed_data_list); struct list_head *s_freed_head = &sbi->s_freed_data_list[commit_tid & 1]; bool wake; list_replace_init(s_freed_head, &freed_data_list); list_for_each_entry(entry, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); if (test_opt(sb, DISCARD)) { spin_lock(&sbi->s_md_lock); wake = list_empty(&sbi->s_discard_list); list_splice_tail(&freed_data_list, &sbi->s_discard_list); spin_unlock(&sbi->s_md_lock); if (wake) queue_work(system_dfl_wq, &sbi->s_discard_work); } else { list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) kmem_cache_free(ext4_free_data_cachep, entry); } } int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) goto out; ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, SLAB_RECLAIM_ACCOUNT); if (ext4_ac_cachep == NULL) goto out_pa_free; ext4_free_data_cachep = KMEM_CACHE(ext4_free_data, SLAB_RECLAIM_ACCOUNT); if (ext4_free_data_cachep == NULL) goto out_ac_free; return 0; out_ac_free: kmem_cache_destroy(ext4_ac_cachep); out_pa_free: kmem_cache_destroy(ext4_pspace_cachep); out: return -ENOMEM; } void ext4_exit_mballoc(void) { /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. */ rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_data_cachep); ext4_groupinfo_destroy_slabs(); } #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 #define EXT4_MB_SYNC_UPDATE 0x0002 static int ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, ext4_group_t group, ext4_grpblk_t blkoff, ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; int err; unsigned int i, already, changed = len; KUNIT_STATIC_STUB_REDIRECT(ext4_mb_mark_context, handle, sb, state, group, blkoff, len, flags, ret_changed); if (ret_changed) *ret_changed = 0; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) return PTR_ERR(bitmap_bh); if (handle) { BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, sb, bitmap_bh, EXT4_JTR_NONE); if (err) goto out_err; } err = -EIO; gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) goto out_err; if (handle) { BUFFER_TRACE(gdp_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, gdp_bh, EXT4_JTR_NONE); if (err) goto out_err; } ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); } if (flags & EXT4_MB_BITMAP_MARKED_CHECK) { already = 0; for (i = 0; i < len; i++) if (mb_test_bit(blkoff + i, bitmap_bh->b_data) == state) already++; changed = len - already; } if (state) { mb_set_bits(bitmap_bh->b_data, blkoff, len); ext4_free_group_clusters_set(sb, gdp, ext4_free_group_clusters(sb, gdp) - changed); } else { mb_clear_bits(bitmap_bh->b_data, blkoff, len); ext4_free_group_clusters_set(sb, gdp, ext4_free_group_clusters(sb, gdp) + changed); } ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); if (ret_changed) *ret_changed = changed; if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, group); struct flex_groups *fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); if (state) atomic64_sub(changed, &fg->free_clusters); else atomic64_add(changed, &fg->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (err) goto out_err; err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); if (err) goto out_err; if (flags & EXT4_MB_SYNC_UPDATE) { sync_dirty_buffer(bitmap_bh); sync_dirty_buffer(gdp_bh); } out_err: brelse(bitmap_bh); return err; } /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps * Returns 0 if success or error code */ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle, unsigned int reserv_clstrs) { struct ext4_group_desc *gdp; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; int flags = 0; ext4_grpblk_t changed; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); sb = ac->ac_sb; sbi = EXT4_SB(sb); gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, NULL); if (!gdp) return -EIO; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, 0, NULL); if (!err) err = -EFSCORRUPTED; return err; } #ifdef AGGRESSIVE_CHECK flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, flags, &changed); if (err && changed == 0) return err; #ifdef AGGRESSIVE_CHECK BUG_ON(changed != ac->ac_b_ex.fe_len); #endif percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative */ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); return err; } /* * Idempotent helper for Ext4 fast commit replay path to set the state of * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, bool state) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; int err = 0; unsigned int clen, thisgrp_len; while (len > 0) { ext4_get_group_no_and_offset(sb, block, &group, &blkoff); /* * Check to see if we are freeing blocks across a group * boundary. * In case of flex_bg, this can happen that (block, len) may * span across more than one group. In that case we need to * get the corresponding group metadata to work with. * For this we have goto again loop. */ thisgrp_len = min_t(unsigned int, (unsigned int)len, EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff)); clen = EXT4_NUM_B2C(sbi, thisgrp_len); if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) { ext4_error(sb, "Marking blocks in system zone - " "Block = %llu, len = %u", block, thisgrp_len); break; } err = ext4_mb_mark_context(NULL, sb, state, group, blkoff, clen, EXT4_MB_BITMAP_MARKED_CHECK | EXT4_MB_SYNC_UPDATE, NULL); if (err) break; block += thisgrp_len; len -= thisgrp_len; BUG_ON(len < 0); } } /* * here we normalize request for locality group * Group request are normalized to s_mb_group_prealloc, which goes to * s_strip if we set the same via mount option. * s_mb_group_prealloc can be configured via * /sys/fs/ext4/<partition>/mb_group_prealloc * * XXX: should we try to preallocate more than the group has now? */ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; BUG_ON(lg == NULL); ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; mb_debug(sb, "goal %u blocks for locality group\n", ac->ac_g_ex.fe_len); } /* * This function returns the next element to look at during inode * PA rbtree walk. We assume that we have held the inode PA rbtree lock * (ei->i_prealloc_lock) * * new_start The start of the range we want to compare * cur_start The existing start that we are comparing against * node The node of the rb_tree */ static inline struct rb_node* ext4_mb_pa_rb_next_iter(ext4_lblk_t new_start, ext4_lblk_t cur_start, struct rb_node *node) { if (new_start < cur_start) return node->rb_left; else return node->rb_right; } static inline void ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac, ext4_lblk_t start, loff_t end) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_prealloc_space *tmp_pa; ext4_lblk_t tmp_pa_start; loff_t tmp_pa_end; struct rb_node *iter; read_lock(&ei->i_prealloc_lock); for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(start, tmp_pa_start, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; tmp_pa_end = pa_logical_end(sbi, tmp_pa); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) BUG_ON(!(start >= tmp_pa_end || end <= tmp_pa_start)); spin_unlock(&tmp_pa->pa_lock); } read_unlock(&ei->i_prealloc_lock); } /* * Given an allocation context "ac" and a range "start", "end", check * and adjust boundaries if the range overlaps with any of the existing * preallocatoins stored in the corresponding inode of the allocation context. * * Parameters: * ac allocation context * start start of the new range * end end of the new range */ static inline void ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac, ext4_lblk_t *start, loff_t *end) { struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *tmp_pa = NULL, *left_pa = NULL, *right_pa = NULL; struct rb_node *iter; ext4_lblk_t new_start, tmp_pa_start, right_pa_start = -1; loff_t new_end, tmp_pa_end, left_pa_end = -1; new_start = *start; new_end = *end; /* * Adjust the normalized range so that it doesn't overlap with any * existing preallocated blocks(PAs). Make sure to hold the rbtree lock * so it doesn't change underneath us. */ read_lock(&ei->i_prealloc_lock); /* Step 1: find any one immediate neighboring PA of the normalized range */ for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical, tmp_pa_start, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; tmp_pa_end = pa_logical_end(sbi, tmp_pa); /* PA must not overlap original request */ spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) BUG_ON(!(ac->ac_o_ex.fe_logical >= tmp_pa_end || ac->ac_o_ex.fe_logical < tmp_pa_start)); spin_unlock(&tmp_pa->pa_lock); } /* * Step 2: check if the found PA is left or right neighbor and * get the other neighbor */ if (tmp_pa) { if (tmp_pa->pa_lstart < ac->ac_o_ex.fe_logical) { struct rb_node *tmp; left_pa = tmp_pa; tmp = rb_next(&left_pa->pa_node.inode_node); if (tmp) { right_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } } else { struct rb_node *tmp; right_pa = tmp_pa; tmp = rb_prev(&right_pa->pa_node.inode_node); if (tmp) { left_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } } } /* Step 3: get the non deleted neighbors */ if (left_pa) { for (iter = &left_pa->pa_node.inode_node;; iter = rb_prev(iter)) { if (!iter) { left_pa = NULL; break; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); left_pa = tmp_pa; spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { spin_unlock(&tmp_pa->pa_lock); break; } spin_unlock(&tmp_pa->pa_lock); } } if (right_pa) { for (iter = &right_pa->pa_node.inode_node;; iter = rb_next(iter)) { if (!iter) { right_pa = NULL; break; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); right_pa = tmp_pa; spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { spin_unlock(&tmp_pa->pa_lock); break; } spin_unlock(&tmp_pa->pa_lock); } } if (left_pa) { left_pa_end = pa_logical_end(sbi, left_pa); BUG_ON(left_pa_end > ac->ac_o_ex.fe_logical); } if (right_pa) { right_pa_start = right_pa->pa_lstart; BUG_ON(right_pa_start <= ac->ac_o_ex.fe_logical); } /* Step 4: trim our normalized range to not overlap with the neighbors */ if (left_pa) { if (left_pa_end > new_start) new_start = left_pa_end; } if (right_pa) { if (right_pa_start < new_end) new_end = right_pa_start; } read_unlock(&ei->i_prealloc_lock); /* XXX: extra loop to check we really don't overlap preallocations */ ext4_mb_pa_assert_overlap(ac, new_start, new_end); *start = new_start; *end = new_end; } /* * Normalization means making request better in terms of * size and alignment */ static noinline_for_stack void ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_super_block *es = sbi->s_es; int bsbits, max; loff_t size, start_off, end; loff_t orig_size __maybe_unused; ext4_lblk_t start; /* do normalize only data requests, metadata requests do not need preallocation */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; /* sometime caller may want exact blocks */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; /* caller may indicate that preallocation isn't * required (it's a tail, for example) */ if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC) return; if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) { ext4_mb_normalize_group_request(ac); return ; } bsbits = ac->ac_sb->s_blocksize_bits; /* first, let's learn actual file size * given current request is allocated */ size = extent_logical_end(sbi, &ac->ac_o_ex); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); orig_size = size; /* max size of free chunks */ max = 2 << bsbits; #define NRL_CHECK_SIZE(req, size, max, chunk_size) \ (req <= (size) || max <= (chunk_size)) /* first, try to predict filesize */ /* XXX: should this table be tunable? */ start_off = 0; if (size <= 16 * 1024) { size = 16 * 1024; } else if (size <= 32 * 1024) { size = 32 * 1024; } else if (size <= 64 * 1024) { size = 64 * 1024; } else if (size <= 128 * 1024) { size = 128 * 1024; } else if (size <= 256 * 1024) { size = 256 * 1024; } else if (size <= 512 * 1024) { size = 512 * 1024; } else if (size <= 1024 * 1024) { size = 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (21 - bsbits)) << 21; size = 2 * 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (22 - bsbits)) << 22; size = 4 * 1024 * 1024; } else if (NRL_CHECK_SIZE(EXT4_C2B(sbi, ac->ac_o_ex.fe_len), (8<<20)>>bsbits, max, 8 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (23 - bsbits)) << 23; size = 8 * 1024 * 1024; } else { start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits; size = (loff_t) EXT4_C2B(sbi, ac->ac_o_ex.fe_len) << bsbits; } size = size >> bsbits; start = start_off >> bsbits; /* * For tiny groups (smaller than 8MB) the chosen allocation * alignment may be larger than group size. Make sure the * alignment does not move allocation to a different group which * makes mballoc fail assertions later. */ start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); /* avoid unnecessary preallocation that may trigger assertions */ if (start + size > EXT_MAX_BLOCKS) size = EXT_MAX_BLOCKS - start; /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; start = ar->lleft + 1; } if (ar->pright && start + size - 1 >= ar->lright) size -= start + size - ar->lright; /* * Trim allocation request for filesystems with artificially small * groups. */ if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb); end = start + size; ext4_mb_pa_adjust_overlap(ac, &start, &end); size = end - start; /* * In this function "start" and "size" are normalized for better * alignment and length such that we could preallocate more blocks. * This normalization is done such that original request of * ac->ac_o_ex.fe_logical & fe_len should always lie within "start" and * "size" boundaries. * (Note fe_len can be relaxed since FS block allocation API does not * provide gurantee on number of contiguous blocks allocation since that * depends upon free space left, etc). * In case of inode pa, later we use the allocated blocks * [pa_pstart + fe_logical - pa_lstart, fe_len/size] from the preallocated * range of goal/best blocks [start, size] to put it at the * ac_o_ex.fe_logical extent of this inode. * (See ext4_mb_use_inode_pa() for more details) */ if (start + size <= ac->ac_o_ex.fe_logical || start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", (unsigned long) start, (unsigned long) size, (unsigned long) ac->ac_o_ex.fe_logical); BUG(); } BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ /* XXX: is it better to align blocks WRT to logical * placement or satisfy big request as is */ ac->ac_g_ex.fe_logical = start; ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); ac->ac_orig_goal_len = ac->ac_g_ex.fe_len; /* define goal start in order to merge */ if (ar->pright && (ar->lright == (start + size)) && ar->pright >= size && ar->pright - size >= le32_to_cpu(es->s_first_data_block)) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, &ac->ac_g_ex.fe_group, &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } if (ar->pleft && (ar->lleft + 1 == start) && ar->pleft + 1 < ext4_blocks_count(es)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, &ac->ac_g_ex.fe_group, &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } mb_debug(ac->ac_sb, "goal: %lld(was %lld) blocks at %u\n", size, orig_size, start); } static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); if (sbi->s_mb_stats && ac->ac_g_ex.fe_len >= 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); for (int i=0; i<EXT4_MB_NUM_CRS; i++) { atomic_add(ac->ac_cX_found[i], &sbi->s_bal_cX_ex_scanned[i]); } atomic_add(ac->ac_groups_scanned, &sbi->s_bal_groups_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); /* did we allocate as much as normalizer originally wanted? */ if (ac->ac_f_ex.fe_len == ac->ac_orig_goal_len) atomic_inc(&sbi->s_bal_len_goals); if (ac->ac_found > sbi->s_mb_max_to_scan) atomic_inc(&sbi->s_bal_breaks); } if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) trace_ext4_mballoc_alloc(ac); else trace_ext4_mballoc_prealloc(ac); } /* * Called on failure; free up any blocks from the inode PA for this * context. We don't need this for MB_GROUP_PA because we only change * pa_free in ext4_mb_release_context(), but on failure, we've already * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. */ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; struct ext4_buddy e4b; int err; if (pa == NULL) { if (ac->ac_f_ex.fe_len == 0) return; err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); if (WARN_RATELIMIT(err, "ext4: mb_load_buddy failed (%d)", err)) /* * This should never happen since we pin the * pages in the ext4_allocation_context so * ext4_mb_load_buddy() should never fail. */ return; ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, ac->ac_f_ex.fe_len); ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ext4_mb_unload_buddy(&e4b); return; } if (pa->pa_type == MB_INODE_PA) { spin_lock(&pa->pa_lock); pa->pa_free += ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); } } /* * use blocks preallocated to inode */ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; ext4_fsblk_t end; int len; /* found preallocated blocks, use them */ start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart); end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len), start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len)); len = EXT4_NUM_B2C(sbi, end - start); ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); BUG_ON(ac->ac_b_ex.fe_len <= 0); pa->pa_free -= len; mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); } /* * use blocks preallocated to locality group */ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; /* we don't correct pa_pstart or pa_len here to avoid * possible race when the group is being loaded concurrently * instead we correct pa later, after blocks are marked * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n", pa->pa_lstart, len, pa); } /* * Return the prealloc space that have minimal distance * from the goal block. @cpa is the prealloc * space that is having currently known minimal distance * from the goal block. */ static struct ext4_prealloc_space * ext4_mb_check_group_pa(ext4_fsblk_t goal_block, struct ext4_prealloc_space *pa, struct ext4_prealloc_space *cpa) { ext4_fsblk_t cur_distance, new_distance; if (cpa == NULL) { atomic_inc(&pa->pa_count); return pa; } cur_distance = abs(goal_block - cpa->pa_pstart); new_distance = abs(goal_block - pa->pa_pstart); if (cur_distance <= new_distance) return cpa; /* drop the previous reference */ atomic_dec(&cpa->pa_count); atomic_inc(&pa->pa_count); return pa; } /* * check if found pa meets EXT4_MB_HINT_GOAL_ONLY */ static bool ext4_mb_pa_goal_check(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; if (likely(!(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))) return true; /* * If EXT4_MB_HINT_GOAL_ONLY is set, ac_g_ex will not be adjusted * in ext4_mb_normalize_request and will keep same with ac_o_ex * from ext4_mb_initialize_context. Choose ac_g_ex here to keep * consistent with ext4_mb_find_by_goal. */ start = pa->pa_pstart + (ac->ac_g_ex.fe_logical - pa->pa_lstart); if (ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex) != start) return false; if (ac->ac_g_ex.fe_len > pa->pa_len - EXT4_B2C(sbi, ac->ac_g_ex.fe_logical - pa->pa_lstart)) return false; return true; } /* * search goal blocks in preallocated space */ static noinline_for_stack bool ext4_mb_use_preallocated(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int order, i; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_locality_group *lg; struct ext4_prealloc_space *tmp_pa = NULL, *cpa = NULL; struct rb_node *iter; ext4_fsblk_t goal_block; /* only data can be preallocated */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return false; /* * first, try per-file preallocation by searching the inode pa rbtree. * * Here, we can't do a direct traversal of the tree because * ext4_mb_discard_group_preallocation() can paralelly mark the pa * deleted and that can cause direct traversal to skip some entries. */ read_lock(&ei->i_prealloc_lock); if (RB_EMPTY_ROOT(&ei->i_prealloc_node)) { goto try_group_pa; } /* * Step 1: Find a pa with logical start immediately adjacent to the * original logical start. This could be on the left or right. * * (tmp_pa->pa_lstart never changes so we can skip locking for it). */ for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical, tmp_pa->pa_lstart, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); } /* * Step 2: The adjacent pa might be to the right of logical start, find * the left adjacent pa. After this step we'd have a valid tmp_pa whose * logical start is towards the left of original request's logical start */ if (tmp_pa->pa_lstart > ac->ac_o_ex.fe_logical) { struct rb_node *tmp; tmp = rb_prev(&tmp_pa->pa_node.inode_node); if (tmp) { tmp_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } else { /* * If there is no adjacent pa to the left then finding * an overlapping pa is not possible hence stop searching * inode pa tree */ goto try_group_pa; } } BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical)); /* * Step 3: If the left adjacent pa is deleted, keep moving left to find * the first non deleted adjacent pa. After this step we should have a * valid tmp_pa which is guaranteed to be non deleted. */ for (iter = &tmp_pa->pa_node.inode_node;; iter = rb_prev(iter)) { if (!iter) { /* * no non deleted left adjacent pa, so stop searching * inode pa tree */ goto try_group_pa; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { /* * We will keep holding the pa_lock from * this point on because we don't want group discard * to delete this pa underneath us. Since group * discard is anyways an ENOSPC operation it * should be okay for it to wait a few more cycles. */ break; } else { spin_unlock(&tmp_pa->pa_lock); } } BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical)); BUG_ON(tmp_pa->pa_deleted == 1); /* * Step 4: We now have the non deleted left adjacent pa. Only this * pa can possibly satisfy the request hence check if it overlaps * original logical start and stop searching if it doesn't. */ if (ac->ac_o_ex.fe_logical >= pa_logical_end(sbi, tmp_pa)) { spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } /* non-extent files can't have physical blocks past 2^32 */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) && (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) > EXT4_MAX_BLOCK_FILE_PHYS)) { /* * Since PAs don't overlap, we won't find any other PA to * satisfy this. */ spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } if (tmp_pa->pa_free && likely(ext4_mb_pa_goal_check(ac, tmp_pa))) { atomic_inc(&tmp_pa->pa_count); ext4_mb_use_inode_pa(ac, tmp_pa); spin_unlock(&tmp_pa->pa_lock); read_unlock(&ei->i_prealloc_lock); return true; } else { /* * We found a valid overlapping pa but couldn't use it because * it had no free blocks. This should ideally never happen * because: * * 1. When a new inode pa is added to rbtree it must have * pa_free > 0 since otherwise we won't actually need * preallocation. * * 2. An inode pa that is in the rbtree can only have it's * pa_free become zero when another thread calls: * ext4_mb_new_blocks * ext4_mb_use_preallocated * ext4_mb_use_inode_pa * * 3. Further, after the above calls make pa_free == 0, we will * immediately remove it from the rbtree in: * ext4_mb_new_blocks * ext4_mb_release_context * ext4_mb_put_pa * * 4. Since the pa_free becoming 0 and pa_free getting removed * from tree both happen in ext4_mb_new_blocks, which is always * called with i_data_sem held for data allocations, we can be * sure that another process will never see a pa in rbtree with * pa_free == 0. */ WARN_ON_ONCE(tmp_pa->pa_free == 0); } spin_unlock(&tmp_pa->pa_lock); try_group_pa: read_unlock(&ei->i_prealloc_lock); /* can we use group allocation? */ if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)) return false; /* inode may have no locality group for some reason */ lg = ac->ac_lg; if (lg == NULL) return false; order = fls(ac->ac_o_ex.fe_len) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex); /* * search for the prealloc space that is having * minimal distance from the goal block. */ for (i = order; i < PREALLOC_TB_SIZE; i++) { rcu_read_lock(); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[i], pa_node.lg_list) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0 && tmp_pa->pa_free >= ac->ac_o_ex.fe_len) { cpa = ext4_mb_check_group_pa(goal_block, tmp_pa, cpa); } spin_unlock(&tmp_pa->pa_lock); } rcu_read_unlock(); } if (cpa) { ext4_mb_use_group_pa(ac, cpa); return true; } return false; } /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ static noinline_for_stack void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_prealloc_space *pa; struct list_head *cur; ext4_group_t groupnr; ext4_grpblk_t start; int preallocated = 0; int len; if (!grp) return; /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here * notice we do NOT ignore preallocations with pa_deleted * otherwise we could leave used blocks available for * allocation in buddy when concurrent ext4_mb_put_pa() * is dropping preallocation */ list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &start); len = pa->pa_len; spin_unlock(&pa->pa_lock); if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); mb_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } static void ext4_mb_mark_pa_deleted(struct super_block *sb, struct ext4_prealloc_space *pa) { struct ext4_inode_info *ei; if (pa->pa_deleted) { ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", pa->pa_type, pa->pa_pstart, pa->pa_lstart, pa->pa_len); return; } pa->pa_deleted = 1; if (pa->pa_type == MB_INODE_PA) { ei = EXT4_I(pa->pa_inode); atomic_dec(&ei->i_prealloc_active); } } static inline void ext4_mb_pa_free(struct ext4_prealloc_space *pa) { BUG_ON(!pa); BUG_ON(atomic_read(&pa->pa_count)); BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); ext4_mb_pa_free(pa); } /* * drops a reference to preallocated space descriptor * if this was the last reference and the space is consumed */ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, struct super_block *sb, struct ext4_prealloc_space *pa) { ext4_group_t grp; ext4_fsblk_t grp_blk; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { spin_unlock(&pa->pa_lock); return; } if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; } ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; /* * If doing group-based preallocation, pa_pstart may be in the * next group when pa is used up */ if (pa->pa_type == MB_GROUP_PA) grp_blk--; grp = ext4_get_group_number(sb, grp_blk); /* * possible race: * * P1 (buddy init) P2 (regular allocation) * find block B in PA * copy on-disk bitmap to buddy * mark B in on-disk bitmap * drop PA from group * mark all PAs in buddy * * thus, P1 initializes buddy with B available. to prevent this * we make "copy" and "mark all PAs" atomic and serialize "drop PA" * against that pair */ ext4_lock_group(sb, grp); list_del(&pa->pa_group_list); ext4_unlock_group(sb, grp); if (pa->pa_type == MB_INODE_PA) { write_lock(pa->pa_node_lock.inode_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); write_unlock(pa->pa_node_lock.inode_lock); ext4_mb_pa_free(pa); } else { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } static void ext4_mb_pa_rb_insert(struct rb_root *root, struct rb_node *new) { struct rb_node **iter = &root->rb_node, *parent = NULL; struct ext4_prealloc_space *iter_pa, *new_pa; ext4_lblk_t iter_start, new_start; while (*iter) { iter_pa = rb_entry(*iter, struct ext4_prealloc_space, pa_node.inode_node); new_pa = rb_entry(new, struct ext4_prealloc_space, pa_node.inode_node); iter_start = iter_pa->pa_lstart; new_start = new_pa->pa_lstart; parent = *iter; if (new_start < iter_start) iter = &((*iter)->rb_left); else iter = &((*iter)->rb_right); } rb_link_node(new, parent, iter); rb_insert_color(new, root); } /* * creates new preallocated space for given inode */ static noinline_for_stack void ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_prealloc_space *pa; struct ext4_group_info *grp; struct ext4_inode_info *ei; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_orig_goal_len) { struct ext4_free_extent ex = { .fe_logical = ac->ac_g_ex.fe_logical, .fe_len = ac->ac_orig_goal_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); /* * We can't allocate as much as normalizer wants, so we try * to get proper lstart to cover the original request, except * when the goal doesn't cover the original request as below: * * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 * best_ex:0/200(200) -> adjusted: 1848/2048(200) */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); /* * Use the below logic for adjusting best extent as it keeps * fragmentation in check while ensuring logical range of best * extent doesn't overflow out of goal extent: * * 1. Check if best ex can be kept at end of goal (before * cr_best_avail trimmed it) and still cover original start * 2. Else, check if best ex can be kept at start of goal and * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len); if (ac->ac_o_ex.fe_logical >= ex.fe_logical) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } pa->pa_lstart = ac->ac_b_ex.fe_logical; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; mb_debug(sb, "new inode pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); atomic_add(pa->pa_free, &sbi->s_mb_preallocated); ext4_mb_use_inode_pa(ac, pa); ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); if (!grp) return; pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); write_lock(pa->pa_node_lock.inode_lock); ext4_mb_pa_rb_insert(&ei->i_prealloc_node, &pa->pa_node.inode_node); write_unlock(pa->pa_node_lock.inode_lock); atomic_inc(&ei->i_prealloc_active); } /* * creates new preallocated space for locality group inodes belongs to */ static noinline_for_stack void ext4_mb_new_group_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg; struct ext4_prealloc_space *pa; struct ext4_group_info *grp; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_lstart = pa->pa_pstart; pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_node.lg_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; mb_debug(sb, "new group pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); if (!grp) return; lg = ac->ac_lg; BUG_ON(lg == NULL); pa->pa_node_lock.lg_lock = &lg->lg_prealloc_lock; pa->pa_inode = NULL; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); /* * We will later add the new pa to the right bucket * after updating the pa_free in ext4_mb_release_context */ } static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) { if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) ext4_mb_new_group_pa(ac); else ext4_mb_new_inode_pa(ac); } /* * finds all unused blocks in on-disk bitmap, frees them in * in-core bitmap and buddy. * @pa must be unlinked from inode and group lists, so that * nobody else can find/use it. * the caller MUST hold group/inode locks. * TODO: optimize the case when there are no in-core structures yet */ static noinline_for_stack void ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int end; unsigned int next; ext4_group_t group; ext4_grpblk_t bit; unsigned long long grp_blk_start; int free = 0; BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); end = bit + pa->pa_len; while (bit < end) { bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) break; next = mb_find_next_bit(bitmap_bh->b_data, end, bit); mb_debug(sb, "free preallocated %u/%u in group %u\n", (unsigned) ext4_group_first_block_no(sb, group) + bit, (unsigned) next - bit, (unsigned) group); free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); trace_ext4_mb_release_inode_pa(pa, (grp_blk_start + EXT4_C2B(sbi, bit)), next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } if (free != pa->pa_free) { ext4_msg(e4b->bd_sb, KERN_CRIT, "pa %p: logic %lu, phys. %lu, len %d", pa, (unsigned long) pa->pa_lstart, (unsigned long) pa->pa_pstart, pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* * pa is already deleted so we use the value obtained * from the bitmap and continue. */ } atomic_add(free, &sbi->s_mb_discarded); } static noinline_for_stack void ext4_mb_release_group_pa(struct ext4_buddy *e4b, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; ext4_group_t group; ext4_grpblk_t bit; trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", e4b->bd_group, group, pa->pa_pstart); return; } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); } /* * releases all preallocations in given group * * first, we need to decide discard policy: * - when do we discard * 1) ENOSPC * - how many do we discard * 1) how many requested */ static noinline_for_stack int ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_group_t group, int *busy) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; LIST_HEAD(list); struct ext4_buddy e4b; struct ext4_inode_info *ei; int err; int free = 0; if (!grp) return 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); goto out_dbg; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { ext4_warning(sb, "Error %d loading buddy information for %u", err, group); put_bh(bitmap_bh); goto out_dbg; } ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { spin_unlock(&pa->pa_lock); *busy = 1; continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); if (!free) this_cpu_inc(discard_pa_seq); /* we can trust pa_free ... */ free += pa->pa_free; spin_unlock(&pa->pa_lock); list_del(&pa->pa_group_list); list_add(&pa->u.pa_tmp_list, &list); } /* now free all selected PAs */ list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { /* remove from object (inode or locality group) */ if (pa->pa_type == MB_GROUP_PA) { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); } else { write_lock(pa->pa_node_lock.inode_lock); ei = EXT4_I(pa->pa_inode); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); write_unlock(pa->pa_node_lock.inode_lock); } list_del(&pa->u.pa_tmp_list); if (pa->pa_type == MB_GROUP_PA) { ext4_mb_release_group_pa(&e4b, pa); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } else { ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_mb_pa_free(pa); } } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", free, group, grp->bb_free); return free; } /* * releases all non-used preallocated blocks for given inode * * It's important to discard preallocations under i_data_sem * We don't want another block to be served from the prealloc * space when we are discarding the inode prealloc space. * * FIXME!! Make sure it is valid at all the call sites */ void ext4_discard_preallocations(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; ext4_group_t group = 0; LIST_HEAD(list); struct ext4_buddy e4b; struct rb_node *iter; int err; if (!S_ISREG(inode->i_mode)) return; if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return; mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, atomic_read(&ei->i_prealloc_active)); repeat: /* first, collect all pa's in the inode */ write_lock(&ei->i_prealloc_lock); for (iter = rb_first(&ei->i_prealloc_node); iter; iter = rb_next(iter)) { pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); BUG_ON(pa->pa_node_lock.inode_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* this shouldn't happen often - nobody should * use preallocation while we're discarding it */ spin_unlock(&pa->pa_lock); write_unlock(&ei->i_prealloc_lock); ext4_msg(sb, KERN_ERR, "uh-oh! used pa while discarding"); WARN_ON(1); schedule_timeout_uninterruptible(HZ); goto repeat; } if (pa->pa_deleted == 0) { ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); list_add(&pa->u.pa_tmp_list, &list); continue; } /* someone is deleting pa right now */ spin_unlock(&pa->pa_lock); write_unlock(&ei->i_prealloc_lock); /* we have to wait here because pa_deleted * doesn't mean pa is already unlinked from * the list. as we might be called from * ->clear_inode() the inode will get freed * and concurrent thread which is unlinking * pa from inode's list may access already * freed memory, bad-bad-bad */ /* XXX: if this happens too often, we can * add a flag to force wait only in case * of ->clear_inode(), but not in case of * regular truncate */ schedule_timeout_uninterruptible(HZ); goto repeat; } write_unlock(&ei->i_prealloc_lock); list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); ext4_mb_unload_buddy(&e4b); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); list_del(&pa->u.pa_tmp_list); ext4_mb_pa_free(pa); } } static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa; BUG_ON(ext4_pspace_cachep == NULL); pa = kmem_cache_zalloc(ext4_pspace_cachep, GFP_NOFS); if (!pa) return -ENOMEM; atomic_set(&pa->pa_count, 1); ac->ac_pa = pa; return 0; } static void ext4_mb_pa_put_free(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; BUG_ON(!pa); ac->ac_pa = NULL; WARN_ON(!atomic_dec_and_test(&pa->pa_count)); /* * current function is only called due to an error or due to * len of found blocks < len of requested blocks hence the PA has not * been added to grp->bb_prealloc_list. So we don't need to lock it */ pa->pa_deleted = 1; ext4_mb_pa_free(pa); } #ifdef CONFIG_EXT4_DEBUG static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; if (ext4_emergency_state(sb)) return; ngroups = ext4_get_groups_count(sb); mb_debug(sb, "groups: "); for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; if (!grp) continue; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); mb_debug(sb, "PA:%u:%d:%d\n", i, start, pa->pa_len); } ext4_unlock_group(sb, i); mb_debug(sb, "%u: %d/%d\n", i, grp->bb_free, grp->bb_fragments); } } static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; if (ext4_emergency_state(sb)) return; mb_debug(sb, "Can't allocate:" " Allocation context details:"); mb_debug(sb, "status %u flags 0x%x", ac->ac_status, ac->ac_flags); mb_debug(sb, "orig %lu/%lu/%lu@%lu, " "goal %lu/%lu/%lu@%lu, " "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, (unsigned long)ac->ac_o_ex.fe_len, (unsigned long)ac->ac_o_ex.fe_logical, (unsigned long)ac->ac_g_ex.fe_group, (unsigned long)ac->ac_g_ex.fe_start, (unsigned long)ac->ac_g_ex.fe_len, (unsigned long)ac->ac_g_ex.fe_logical, (unsigned long)ac->ac_b_ex.fe_group, (unsigned long)ac->ac_b_ex.fe_start, (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); mb_debug(sb, "%u found", ac->ac_found); mb_debug(sb, "used pa: %s, ", str_yes_no(ac->ac_pa)); if (ac->ac_pa) mb_debug(sb, "pa_type %s\n", ac->ac_pa->pa_type == MB_GROUP_PA ? "group pa" : "inode pa"); ext4_mb_show_pa(sb); } #else static inline void ext4_mb_show_pa(struct super_block *sb) { } static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { ext4_mb_show_pa(ac->ac_sb); } #endif /* * We use locality group preallocation for small size file. The size of the * file is determined by the current size or the resulting size after * allocation which ever is larger * * One can tune this size via /sys/fs/ext4/<partition>/mb_stream_req */ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; group_pa_eligible = sbi->s_mb_group_prealloc > 0; inode_pa_eligible = true; size = extent_logical_end(sbi, &ac->ac_o_ex); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && !inode_is_open_for_write(ac->ac_inode)) inode_pa_eligible = false; size = max(size, isize); /* Don't use group allocation for large files */ if (size > sbi->s_mb_stream_request) group_pa_eligible = false; if (!group_pa_eligible) { if (inode_pa_eligible) ac->ac_flags |= EXT4_MB_STREAM_ALLOC; else ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } BUG_ON(ac->ac_lg != NULL); /* * locality group prealloc space are per cpu. The reason for having * per cpu locality group is to reduce the contention between block * request from multiple CPUs. */ ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups); /* we're going to use group allocation */ ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC; /* serialize all allocations in the group */ mutex_lock(&ac->ac_lg->lg_mutex); } static noinline_for_stack void ext4_mb_initialize_context(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_group_t group; unsigned int len; ext4_fsblk_t goal; ext4_grpblk_t block; /* we can't allocate > group size */ len = ar->len; /* just a dirty hack to filter too big requests */ if (len >= EXT4_CLUSTERS_PER_GROUP(sb)) len = EXT4_CLUSTERS_PER_GROUP(sb); /* start searching from the goal */ goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical; ac->ac_o_ex.fe_group = group; ac->ac_o_ex.fe_start = block; ac->ac_o_ex.fe_len = len; ac->ac_g_ex = ac->ac_o_ex; ac->ac_orig_goal_len = ac->ac_g_ex.fe_len; ac->ac_flags = ar->flags; /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); mb_debug(sb, "init ac: %u blocks @ %u, goal %u, flags 0x%x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, (unsigned) ar->lleft, (unsigned) ar->pleft, (unsigned) ar->lright, (unsigned) ar->pright, inode_is_open_for_write(ar->inode) ? "" : "non-"); } static noinline_for_stack void ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_locality_group *lg, int order, int total_entries) { ext4_group_t group = 0; struct ext4_buddy e4b; LIST_HEAD(discard_list); struct ext4_prealloc_space *pa, *tmp; mb_debug(sb, "discard locality group preallocation\n"); spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], pa_node.lg_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* * This is the pa that we just used * for block allocation. So don't * free that */ spin_unlock(&pa->pa_lock); continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* only lg prealloc space */ BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_node.lg_list); list_add(&pa->u.pa_tmp_list, &discard_list); total_entries--; if (total_entries <= 5) { /* * we want to keep only 5 entries * allowing it to grow to 8. This * mak sure we don't call discard * soon for this list. */ break; } } spin_unlock(&lg->lg_prealloc_lock); list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { int err; group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_group_pa(&e4b, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } /* * We have incremented pa_count. So it cannot be freed at this * point. Also we hold lg_mutex. So no parallel allocation is * possible from this lg. That means pa_free cannot be updated. * * A parallel ext4_mb_discard_group_preallocations is possible. * which can cause the lg_prealloc_list to be updated. */ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) { int order, added = 0, lg_prealloc_count = 1; struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa; order = fls(pa->pa_free) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; /* Add the prealloc space to lg */ spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order], pa_node.lg_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted) { spin_unlock(&tmp_pa->pa_lock); continue; } if (!added && pa->pa_free < tmp_pa->pa_free) { /* Add to the tail of the previous entry */ list_add_tail_rcu(&pa->pa_node.lg_list, &tmp_pa->pa_node.lg_list); added = 1; /* * we want to count the total * number of entries in the list */ } spin_unlock(&tmp_pa->pa_lock); lg_prealloc_count++; } if (!added) list_add_tail_rcu(&pa->pa_node.lg_list, &lg->lg_prealloc_list[order]); spin_unlock(&lg->lg_prealloc_lock); /* Now trim the list to be not more than 8 elements */ if (lg_prealloc_count > 8) ext4_mb_discard_lg_preallocations(sb, lg, order, lg_prealloc_count); } /* * release all resource we used in allocation */ static void ext4_mb_release_context(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { if (pa->pa_type == MB_GROUP_PA) { /* see comment in ext4_mb_use_group_pa() */ spin_lock(&pa->pa_lock); pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); /* * We want to add the pa to the right bucket. * Remove it from the list and while adding * make sure the list to which we are adding * doesn't grow big. */ if (likely(pa->pa_free)) { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); ext4_mb_add_n_trim(ac); } } ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_folio) folio_put(ac->ac_bitmap_folio); if (ac->ac_buddy_folio) folio_put(ac->ac_buddy_folio); if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); } static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0, busy = 0; int retry = 0; trace_ext4_mb_discard_preallocations(sb, needed); if (needed == 0) needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; repeat: for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, &busy); freed += ret; needed -= ret; cond_resched(); } if (needed > 0 && busy && ++retry < 3) { busy = 0; goto repeat; } return freed; } static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb, struct ext4_allocation_context *ac, u64 *seq) { int freed; u64 seq_retry = 0; bool ret = false; freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); if (freed) { ret = true; goto out_dbg; } seq_retry = ext4_get_discard_pa_seq_sum(); if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) { ac->ac_flags |= EXT4_MB_STRICT_CHECK; *seq = seq_retry; ret = true; } out_dbg: mb_debug(sb, "freed %d, retry ? %s\n", freed, str_yes_no(ret)); return ret; } /* * Simple allocator for Ext4 fast commit replay path. It searches for blocks * linearly starting at the goal block and also excludes the blocks which * are going to be in use after fast commit replay. */ static ext4_fsblk_t ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) { struct buffer_head *bitmap_bh; struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group, nr; ext4_grpblk_t blkoff; ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; struct ext4_super_block *es = sbi->s_es; goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ar->len = 0; ext4_get_group_no_and_offset(sb, goal, &group, &blkoff); for (nr = ext4_get_groups_count(sb); nr > 0; nr--) { bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { *errp = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return 0; } while (1) { i = mb_find_next_zero_bit(bitmap_bh->b_data, max, blkoff); if (i >= max) break; if (ext4_fc_replay_check_excluded(sb, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i))) { blkoff = i + 1; } else break; } brelse(bitmap_bh); if (i < max) break; if (++group >= ext4_get_groups_count(sb)) group = 0; blkoff = 0; } if (i >= max) { *errp = -ENOSPC; return 0; } block = ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i); ext4_mb_mark_bb(sb, block, 1, true); ar->len = 1; *errp = 0; return block; } /* * Main entry point into mballoc to allocate blocks * it tries to use preallocation first, then falls back * to usual allocation */ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct ext4_allocation_context *ac = NULL; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; int retries = 0; u64 seq; might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); trace_ext4_request_blocks(ar); if (sbi->s_mount_state & EXT4_FC_REPLAY) return ext4_mb_new_blocks_simple(ar, errp); /* Allow to use superuser reservation for quota file */ if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { /* Without delayed allocation we need to verify * there is enough free blocks to do block allocation * and verify allocation doesn't exceed the quota limits. */ while (ar->len && ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ cond_resched(); ar->len = ar->len >> 1; } if (!ar->len) { ext4_mb_show_pa(sb); *errp = -ENOSPC; return 0; } reserv_clstrs = ar->len; if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) { dquot_alloc_block_nofail(ar->inode, EXT4_C2B(sbi, ar->len)); } else { while (ar->len && dquot_alloc_block(ar->inode, EXT4_C2B(sbi, ar->len))) { ar->flags |= EXT4_MB_HINT_NOPREALLOC; ar->len--; } } inquota = ar->len; if (ar->len == 0) { *errp = -EDQUOT; goto out; } } ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; goto out; } ext4_mb_initialize_context(ac, ar); ac->ac_op = EXT4_MB_HISTORY_PREALLOC; seq = this_cpu_read(discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); *errp = ext4_mb_pa_alloc(ac); if (*errp) goto errout; repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); /* * pa allocated above is added to grp->bb_prealloc_list only * when we were able to allocate some block i.e. when * ac->ac_status == AC_STATUS_FOUND. * And error from above mean ac->ac_status != AC_STATUS_FOUND * So we have to free this pa here itself. */ if (*errp) { ext4_mb_pa_put_free(ac); ext4_discard_allocated_blocks(ac); goto errout; } if (ac->ac_status == AC_STATUS_FOUND && ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len) ext4_mb_pa_put_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } } else { if (++retries < 3 && ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above * needs to be freed here itself. */ ext4_mb_pa_put_free(ac); *errp = -ENOSPC; } if (*errp) { errout: ac->ac_b_ex.fe_len = 0; ar->len = 0; ext4_mb_show_ac(ac); } ext4_mb_release_context(ac); kmem_cache_free(ext4_ac_cachep, ac); out: if (inquota && ar->len < inquota) dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len)); if (!ar->len) { if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); } trace_ext4_allocate_blocks(ar, (unsigned long long)block); return block; } /* * We can merge two free data extents only if the physical blocks * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ static inline bool ext4_freed_extents_can_be_merged(struct ext4_free_data *entry1, struct ext4_free_data *entry2) { if (entry1->efd_tid != entry2->efd_tid) return false; if (entry1->efd_start_cluster + entry1->efd_count != entry2->efd_start_cluster) return false; if (WARN_ON_ONCE(entry1->efd_group != entry2->efd_group)) return false; return true; } static inline void ext4_merge_freed_extents(struct ext4_sb_info *sbi, struct rb_root *root, struct ext4_free_data *entry1, struct ext4_free_data *entry2) { entry1->efd_count += entry2->efd_count; spin_lock(&sbi->s_md_lock); list_del(&entry2->efd_list); spin_unlock(&sbi->s_md_lock); rb_erase(&entry2->efd_node, root); kmem_cache_free(ext4_free_data_cachep, entry2); } static inline void ext4_try_merge_freed_extent_prev(struct ext4_sb_info *sbi, struct rb_root *root, struct ext4_free_data *entry) { struct ext4_free_data *prev; struct rb_node *node; node = rb_prev(&entry->efd_node); if (!node) return; prev = rb_entry(node, struct ext4_free_data, efd_node); if (ext4_freed_extents_can_be_merged(prev, entry)) ext4_merge_freed_extents(sbi, root, prev, entry); } static inline void ext4_try_merge_freed_extent_next(struct ext4_sb_info *sbi, struct rb_root *root, struct ext4_free_data *entry) { struct ext4_free_data *next; struct rb_node *node; node = rb_next(&entry->efd_node); if (!node) return; next = rb_entry(node, struct ext4_free_data, efd_node); if (ext4_freed_extents_can_be_merged(entry, next)) ext4_merge_freed_extents(sbi, root, entry, next); } static noinline_for_stack void ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, struct ext4_free_data *new_entry) { ext4_group_t group = e4b->bd_group; ext4_grpblk_t cluster; ext4_grpblk_t clusters = new_entry->efd_count; struct ext4_free_data *entry = NULL; struct ext4_group_info *db = e4b->bd_info; struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct rb_root *root = &db->bb_free_root; struct rb_node **n = &root->rb_node; struct rb_node *parent = NULL, *new_node; BUG_ON(!ext4_handle_valid(handle)); BUG_ON(e4b->bd_bitmap_folio == NULL); BUG_ON(e4b->bd_buddy_folio == NULL); new_node = &new_entry->efd_node; cluster = new_entry->efd_start_cluster; if (!*n) { /* first free block exent. We need to protect buddy cache from being freed, * otherwise we'll refresh it from * on-disk bitmap and lose not-yet-available * blocks */ folio_get(e4b->bd_buddy_folio); folio_get(e4b->bd_bitmap_folio); } while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_free_data, efd_node); if (cluster < entry->efd_start_cluster) n = &(*n)->rb_left; else if (cluster >= (entry->efd_start_cluster + entry->efd_count)) n = &(*n)->rb_right; else { ext4_grp_locked_error(sb, group, 0, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); kmem_cache_free(ext4_free_data_cachep, new_entry); return; } } atomic_add(clusters, &sbi->s_mb_free_pending); if (!entry) goto insert; /* Now try to see the extent can be merged to prev and next */ if (ext4_freed_extents_can_be_merged(new_entry, entry)) { entry->efd_start_cluster = cluster; entry->efd_count += new_entry->efd_count; kmem_cache_free(ext4_free_data_cachep, new_entry); ext4_try_merge_freed_extent_prev(sbi, root, entry); return; } if (ext4_freed_extents_can_be_merged(entry, new_entry)) { entry->efd_count += new_entry->efd_count; kmem_cache_free(ext4_free_data_cachep, new_entry); ext4_try_merge_freed_extent_next(sbi, root, entry); return; } insert: rb_link_node(new_node, parent, n); rb_insert_color(new_node, root); spin_lock(&sbi->s_md_lock); list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]); spin_unlock(&sbi->s_md_lock); } static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { struct super_block *sb = inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); ext4_mb_mark_context(NULL, sb, false, group, blkoff, count, EXT4_MB_BITMAP_MARKED_CHECK | EXT4_MB_SYNC_UPDATE, NULL); } /** * ext4_mb_clear_bb() -- helper function for freeing blocks. * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_fsblk_t block, unsigned long count, int flags) { struct super_block *sb = inode->i_sb; struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; int mark_flags = 0; ext4_grpblk_t changed; sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_out; } flags |= EXT4_FREE_BLOCKS_VALIDATED; do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); grp = ext4_get_group_info(sb, block_group); if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return; /* * Check to see if we are freeing blocks across a group * boundary. */ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) { overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) goto error_out; if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_clean; } #ifdef AGGRESSIVE_CHECK mark_flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif err = ext4_mb_mark_context(handle, sb, false, block_group, bit, count_clusters, mark_flags, &changed); if (err && changed == 0) goto error_clean; #ifdef AGGRESSIVE_CHECK BUG_ON(changed != count_clusters); #endif /* * We need to make sure we don't reuse the freed block until after the * transaction is committed. We make an exception if the inode is to be * written in writeback mode since writeback mode has weak data * consistency guarantees. */ if (ext4_handle_valid(handle) && ((flags & EXT4_FREE_BLOCKS_METADATA) || !ext4_should_writeback_data(inode))) { struct ext4_free_data *new_entry; /* * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed * to fail. */ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count_clusters); /* * Ignore EOPNOTSUPP error. This is consistent with * what happens when using journal. */ if (err == -EOPNOTSUPP) err = 0; if (err) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); mb_free_blocks(inode, &e4b, bit, count_clusters); } ext4_unlock_group(sb, block_group); /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they * can determine if a cluster freed here should be rereserved */ if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) { if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); } if (overflow && !err) { block += count; count = overflow; ext4_mb_unload_buddy(&e4b); /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_clean: ext4_mb_unload_buddy(&e4b); error_out: ext4_std_error(sb, err); } /** * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags) { struct super_block *sb = inode->i_sb; unsigned int overflow; struct ext4_sb_info *sbi; sbi = EXT4_SB(sb); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); else block = bh->b_blocknr; } if (sbi->s_mount_state & EXT4_FC_REPLAY) { ext4_free_blocks_simple(inode, block, EXT4_NUM_B2C(sbi, count)); return; } might_sleep(); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); return; } flags |= EXT4_FREE_BLOCKS_VALIDATED; ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { BUG_ON(count > 1); ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, inode, bh, block); } /* * If the extent to be freed does not begin on a cluster * boundary, we need to deal with partial clusters at the * beginning and end of the extent. Normally we will free * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; block += overflow; if (count > overflow) count -= overflow; else return; } else { block -= overflow; count += overflow; } /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) count -= overflow; else return; } else count += sbi->s_cluster_ratio - overflow; /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { int i; int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; for (i = 0; i < count; i++) { cond_resched(); if (is_metadata) bh = sb_find_get_block_nonatomic(inode->i_sb, block + i); ext4_forget(handle, is_metadata, inode, bh, block + i); } } ext4_mb_clear_bb(handle, inode, block, count, flags); } /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. */ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { ext4_group_t block_group; ext4_grpblk_t bit; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; int err = 0; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; ext4_grpblk_t changed; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); if (cluster_count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); /* * Check to see if we are freeing blocks across a group * boundary. */ if (bit + cluster_count > EXT4_CLUSTERS_PER_GROUP(sb)) { ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; goto error_out; } err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) goto error_out; if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; goto error_clean; } err = ext4_mb_mark_context(handle, sb, false, block_group, bit, cluster_count, EXT4_MB_BITMAP_MARKED_CHECK, &changed); if (err && changed == 0) goto error_clean; if (changed != cluster_count) ext4_error(sb, "bit already cleared in group %u", block_group); ext4_lock_group(sb, block_group); mb_free_blocks(NULL, &e4b, bit, cluster_count); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, changed); error_clean: ext4_mb_unload_buddy(&e4b); error_out: ext4_std_error(sb, err); return err; } /** * ext4_trim_extent -- function to TRIM one single free extent in the group * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ static int ext4_trim_extent(struct super_block *sb, int start, int count, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; ext4_group_t group = e4b->bd_group; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); assert_spin_locked(ext4_group_lock_ptr(sb, group)); ex.fe_start = start; ex.fe_group = group; ex.fe_len = count; /* * Mark blocks used, so no one can reuse them while * being trimmed. */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); ret = ext4_issue_discard(sb, group, start, count); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; } static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { unsigned long nr_clusters_in_group; if (grp < (ext4_get_groups_count(sb) - 1)) nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); else nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - ext4_group_first_block_no(sb, grp)) >> EXT4_CLUSTER_BITS(sb); return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) { return fatal_signal_pending(current) || freezing(current); } static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return 0; last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; if (start == 0 && max >= last) set_trimmed = true; origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; while (start <= max) { start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; next = mb_find_next_bit(bitmap, last + 1, start); if (origin_start == 0 && next >= last) set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); if (ret && ret != -EOPNOTSUPP) return count; count += next - start; } free_count += next - start; start = next + 1; if (ext4_trim_interrupted()) return count; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); cond_resched(); ext4_lock_group(sb, e4b->bd_group); } if ((e4b->bd_info->bb_free - free_count) < minblocks) break; } if (set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); return count; } /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system * @group: group to be trimmed * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy * bitmap. Then issue a TRIM command on this extent and free the extent in * the group buddy bitmap. */ static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { struct ext4_buddy e4b; int ret; trace_ext4_trim_all_free(sb, group, start, max); ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { ext4_warning(sb, "Error %d loading buddy information for %u", ret, group); return ret; } ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || minblocks < EXT4_SB(sb)->s_last_trim_minblks) ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); else ret = 0; ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", ret, group); return ret; } /** * ext4_trim_fs() -- trim ioctl handle function * @sb: superblock for filesystem * @range: fstrim_range structure * * start: First Byte to trim * len: number of Bytes to trim from start * minlen: minimum extent length in Bytes * ext4_trim_fs goes through all allocation groups containing Bytes from * start to start+len. For each such a group ext4_trim_all_free function * is invoked to trim all free space. */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; uint64_t start, end, minlen, trimmed = 0; ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); int ret = 0; start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = EXT4_NUM_B2C(EXT4_SB(sb), range->minlen >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) || start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; /* No point to try to trim less than discard granularity */ if (range->minlen < discard_granularity) { minlen = EXT4_NUM_B2C(EXT4_SB(sb), discard_granularity >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } if (end >= max_blks - 1) end = max_blks - 1; if (end <= first_data_blk) goto out; if (start < first_data_blk) start = first_data_blk; /* Determine first and last group to examine based on start and end */ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start, &first_group, &first_cluster); ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end, &last_group, &last_cluster); /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { if (ext4_trim_interrupted()) break; grp = ext4_get_group_info(sb, group); if (!grp) continue; /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) break; } /* * For all the groups except the last one, last cluster will * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ if (group == last_group) end = last_cluster; if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, end, minlen); if (cnt < 0) { ret = cnt; break; } trimmed += cnt; } /* * For every group except the first one, we are sure * that the first cluster to discard will be cluster #0. */ first_cluster = 0; } if (!ret) EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } /* Iterate all the free extents in the group. */ int ext4_mballoc_query_range( struct super_block *sb, ext4_group_t group, ext4_grpblk_t first, ext4_grpblk_t end, ext4_mballoc_query_range_fn meta_formatter, ext4_mballoc_query_range_fn formatter, void *priv) { void *bitmap; ext4_grpblk_t start, next; struct ext4_buddy e4b; int error; error = ext4_mb_load_buddy(sb, group, &e4b); if (error) return error; bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); start = max(e4b.bd_info->bb_first_free, first); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; if (meta_formatter && start != first) { if (start > end) start = end; ext4_unlock_group(sb, group); error = meta_formatter(sb, group, first, start - first, priv); if (error) goto out_unload; ext4_lock_group(sb, group); } while (start <= end) { start = mb_find_next_zero_bit(bitmap, end + 1, start); if (start > end) break; next = mb_find_next_bit(bitmap, end + 1, start); ext4_unlock_group(sb, group); error = formatter(sb, group, start, next - start, priv); if (error) goto out_unload; ext4_lock_group(sb, group); start = next + 1; } ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(&e4b); return error; } #ifdef CONFIG_EXT4_KUNIT_TESTS #include "mballoc-test.c" #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/phy.h> #include <linux/ethtool_netlink.h> #include "netlink.h" #include "common.h" struct plca_req_info { struct ethnl_req_info base; }; struct plca_reply_data { struct ethnl_reply_data base; struct phy_plca_cfg plca_cfg; struct phy_plca_status plca_st; }; // Helpers ------------------------------------------------------------------ // #define PLCA_REPDATA(__reply_base) \ container_of(__reply_base, struct plca_reply_data, base) // PLCA get configuration message ------------------------------------------- // const struct nla_policy ethnl_plca_get_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, bool *mod) { const struct nlattr *attr = tb[attrid]; if (!attr || WARN_ON_ONCE(attrid >= ARRAY_SIZE(ethnl_plca_set_cfg_policy))) return; switch (ethnl_plca_set_cfg_policy[attrid].type) { case NLA_U8: *dst = nla_get_u8(attr); break; case NLA_U32: *dst = nla_get_u32(attr); break; default: WARN_ON_ONCE(1); } *mod = true; } static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER, info->extack); // check that the PHY device is available and connected if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } // note: rtnl_lock is held already by ethnl_default_doit ops = ethtool_phy_ops; if (!ops || !ops->get_plca_cfg) { ret = -EOPNOTSUPP; goto out; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out; memset(&data->plca_cfg, 0xff, sizeof_field(struct plca_reply_data, plca_cfg)); ret = ops->get_plca_cfg(phydev, &data->plca_cfg); ethnl_ops_complete(dev); out: return ret; } static int plca_get_cfg_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u16)) + /* _VERSION */ nla_total_size(sizeof(u8)) + /* _ENABLED */ nla_total_size(sizeof(u32)) + /* _NODE_CNT */ nla_total_size(sizeof(u32)) + /* _NODE_ID */ nla_total_size(sizeof(u32)) + /* _TO_TIMER */ nla_total_size(sizeof(u32)) + /* _BURST_COUNT */ nla_total_size(sizeof(u32)); /* _BURST_TIMER */ } static int plca_get_cfg_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct plca_reply_data *data = PLCA_REPDATA(reply_base); const struct phy_plca_cfg *plca = &data->plca_cfg; if ((plca->version >= 0 && nla_put_u16(skb, ETHTOOL_A_PLCA_VERSION, plca->version)) || (plca->enabled >= 0 && nla_put_u8(skb, ETHTOOL_A_PLCA_ENABLED, !!plca->enabled)) || (plca->node_id >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_ID, plca->node_id)) || (plca->node_cnt >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_NODE_CNT, plca->node_cnt)) || (plca->to_tmr >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_TO_TMR, plca->to_tmr)) || (plca->burst_cnt >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_CNT, plca->burst_cnt)) || (plca->burst_tmr >= 0 && nla_put_u32(skb, ETHTOOL_A_PLCA_BURST_TMR, plca->burst_tmr))) return -EMSGSIZE; return 0; }; // PLCA set configuration message ------------------------------------------- // const struct nla_policy ethnl_plca_set_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), [ETHTOOL_A_PLCA_TO_TMR] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_BURST_CNT] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_BURST_TMR] = NLA_POLICY_MAX(NLA_U32, 255), }; static int ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_plca_cfg plca_cfg; struct phy_device *phydev; bool mod = false; int ret; phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PLCA_HEADER, info->extack); // check that the PHY device is available and connected if (IS_ERR_OR_NULL(phydev)) return -EOPNOTSUPP; ops = ethtool_phy_ops; if (!ops || !ops->set_plca_cfg) return -EOPNOTSUPP; memset(&plca_cfg, 0xff, sizeof(plca_cfg)); plca_update_sint(&plca_cfg.enabled, tb, ETHTOOL_A_PLCA_ENABLED, &mod); plca_update_sint(&plca_cfg.node_id, tb, ETHTOOL_A_PLCA_NODE_ID, &mod); plca_update_sint(&plca_cfg.node_cnt, tb, ETHTOOL_A_PLCA_NODE_CNT, &mod); plca_update_sint(&plca_cfg.to_tmr, tb, ETHTOOL_A_PLCA_TO_TMR, &mod); plca_update_sint(&plca_cfg.burst_cnt, tb, ETHTOOL_A_PLCA_BURST_CNT, &mod); plca_update_sint(&plca_cfg.burst_tmr, tb, ETHTOOL_A_PLCA_BURST_TMR, &mod); if (!mod) return 0; ret = ops->set_plca_cfg(phydev, &plca_cfg, info->extack); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { .request_cmd = ETHTOOL_MSG_PLCA_GET_CFG, .reply_cmd = ETHTOOL_MSG_PLCA_GET_CFG_REPLY, .hdr_attr = ETHTOOL_A_PLCA_HEADER, .req_info_size = sizeof(struct plca_req_info), .reply_data_size = sizeof(struct plca_reply_data), .prepare_data = plca_get_cfg_prepare_data, .reply_size = plca_get_cfg_reply_size, .fill_reply = plca_get_cfg_fill_reply, .set = ethnl_set_plca, .set_ntf_cmd = ETHTOOL_MSG_PLCA_NTF, }; // PLCA get status message -------------------------------------------------- // const struct nla_policy ethnl_plca_get_status_policy[] = { [ETHTOOL_A_PLCA_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER, info->extack); // check that the PHY device is available and connected if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } // note: rtnl_lock is held already by ethnl_default_doit ops = ethtool_phy_ops; if (!ops || !ops->get_plca_status) { ret = -EOPNOTSUPP; goto out; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out; memset(&data->plca_st, 0xff, sizeof_field(struct plca_reply_data, plca_st)); ret = ops->get_plca_status(phydev, &data->plca_st); ethnl_ops_complete(dev); out: return ret; } static int plca_get_status_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u8)); /* _STATUS */ } static int plca_get_status_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct plca_reply_data *data = PLCA_REPDATA(reply_base); const u8 status = data->plca_st.pst; if (nla_put_u8(skb, ETHTOOL_A_PLCA_STATUS, !!status)) return -EMSGSIZE; return 0; }; const struct ethnl_request_ops ethnl_plca_status_request_ops = { .request_cmd = ETHTOOL_MSG_PLCA_GET_STATUS, .reply_cmd = ETHTOOL_MSG_PLCA_GET_STATUS_REPLY, .hdr_attr = ETHTOOL_A_PLCA_HEADER, .req_info_size = sizeof(struct plca_req_info), .reply_data_size = sizeof(struct plca_reply_data), .prepare_data = plca_get_status_prepare_data, .reply_size = plca_get_status_reply_size, .fill_reply = plca_get_status_fill_reply, }; |
| 18 569 18 18 18 80 80 80 | 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 | #include <linux/notifier.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/fib_notifier.h> #include <net/netns/ipv6.h> #include <net/ip6_fib.h> int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET6; return call_fib_notifier(nb, event_type, info); } int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET6; return call_fib_notifiers(net, event_type, info); } static unsigned int fib6_seq_read(const struct net *net) { return fib6_tables_seq_read(net) + fib6_rules_seq_read(net); } static int fib6_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; err = fib6_rules_dump(net, nb, extack); if (err) return err; return fib6_tables_dump(net, nb, extack); } static const struct fib_notifier_ops fib6_notifier_ops_template = { .family = AF_INET6, .fib_seq_read = fib6_seq_read, .fib_dump = fib6_dump, .owner = THIS_MODULE, }; int __net_init fib6_notifier_init(struct net *net) { struct fib_notifier_ops *ops; ops = fib_notifier_ops_register(&fib6_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv6.notifier_ops = ops; return 0; } void __net_exit fib6_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv6.notifier_ops); } |
| 2 2 2 2 2 2 2 2 2 4 4 4 2 1 1 1 2 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 4 4 4 4 3 3 4 5 5 5 5 5 5 5 5 5 4 8 7 4 7 3 7 7 7 7 7 6 6 4 6 36 36 28 1 2 5 5 5 2 1 1 1 2 2 2 2 2 1 1 4 4 4 16 7 7 6 9 8 7 36 1 12 12 12 12 23 4 8 4 4 4 15 15 4 4 4 4 4 4 4 4 4 4 4 8 8 8 8 8 8 8 7 8 7 7 8 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 9 9 9 9 9 9 9 9 9 9 9 9 5 4 4 4 4 4 2 2 2 2 2 2 2 2 2 2 4 8 5 15 15 15 9 9 9 9 9 9 8 8 1 8 9 8 9 15 15 15 15 15 15 15 15 15 15 15 15 7 15 15 15 15 15 9 9 8 2 2 9 2 2 2 2 2 2 2 2 17 17 16 15 16 16 9 11 4 11 11 9 9 11 11 11 4 4 4 4 6 4 4 6 6 6 6 9 4 4 4 4 4 4 4 4 4 6 9 6 1 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS emulation layer for the mixer interface * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/string.h> #include <linux/module.h> #include <linux/compat.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/control.h> #include <sound/info.h> #include <sound/mixer_oss.h> #include <linux/soundcard.h> #define OSS_ALSAEMULVER _SIOR ('M', 249, int) MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>"); MODULE_DESCRIPTION("Mixer OSS emulation for ALSA."); MODULE_LICENSE("GPL"); MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_MIXER); static int snd_mixer_oss_open(struct inode *inode, struct file *file) { struct snd_card *card; struct snd_mixer_oss_file *fmixer; int err; err = nonseekable_open(inode, file); if (err < 0) return err; card = snd_lookup_oss_minor_data(iminor(inode), SNDRV_OSS_DEVICE_TYPE_MIXER); if (card == NULL) return -ENODEV; if (card->mixer_oss == NULL) { snd_card_unref(card); return -ENODEV; } err = snd_card_file_add(card, file); if (err < 0) { snd_card_unref(card); return err; } fmixer = kzalloc(sizeof(*fmixer), GFP_KERNEL); if (fmixer == NULL) { snd_card_file_remove(card, file); snd_card_unref(card); return -ENOMEM; } fmixer->card = card; fmixer->mixer = card->mixer_oss; file->private_data = fmixer; if (!try_module_get(card->module)) { kfree(fmixer); snd_card_file_remove(card, file); snd_card_unref(card); return -EFAULT; } snd_card_unref(card); return 0; } static int snd_mixer_oss_release(struct inode *inode, struct file *file) { struct snd_mixer_oss_file *fmixer; if (file->private_data) { fmixer = file->private_data; module_put(fmixer->card->module); snd_card_file_remove(fmixer->card, file); kfree(fmixer); } return 0; } static int snd_mixer_oss_info(struct snd_mixer_oss_file *fmixer, mixer_info __user *_info) { struct snd_card *card = fmixer->card; struct snd_mixer_oss *mixer = fmixer->mixer; struct mixer_info info; memset(&info, 0, sizeof(info)); strscpy(info.id, mixer && mixer->id[0] ? mixer->id : card->driver, sizeof(info.id)); strscpy(info.name, mixer && mixer->name[0] ? mixer->name : card->mixername, sizeof(info.name)); info.modify_counter = card->mixer_oss_change_count; if (copy_to_user(_info, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_mixer_oss_info_obsolete(struct snd_mixer_oss_file *fmixer, _old_mixer_info __user *_info) { struct snd_card *card = fmixer->card; struct snd_mixer_oss *mixer = fmixer->mixer; _old_mixer_info info; memset(&info, 0, sizeof(info)); strscpy(info.id, mixer && mixer->id[0] ? mixer->id : card->driver, sizeof(info.id)); strscpy(info.name, mixer && mixer->name[0] ? mixer->name : card->mixername, sizeof(info.name)); if (copy_to_user(_info, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_mixer_oss_caps(struct snd_mixer_oss_file *fmixer) { struct snd_mixer_oss *mixer = fmixer->mixer; int result = 0; if (mixer == NULL) return -EIO; if (mixer->get_recsrc && mixer->put_recsrc) result |= SOUND_CAP_EXCL_INPUT; return result; } static int snd_mixer_oss_devmask(struct snd_mixer_oss_file *fmixer) { struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_mixer_oss_slot *pslot; int result = 0, chn; if (mixer == NULL) return -EIO; guard(mutex)(&mixer->reg_mutex); for (chn = 0; chn < 31; chn++) { pslot = &mixer->slots[chn]; if (pslot->put_volume || pslot->put_recsrc) result |= 1 << chn; } return result; } static int snd_mixer_oss_stereodevs(struct snd_mixer_oss_file *fmixer) { struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_mixer_oss_slot *pslot; int result = 0, chn; if (mixer == NULL) return -EIO; guard(mutex)(&mixer->reg_mutex); for (chn = 0; chn < 31; chn++) { pslot = &mixer->slots[chn]; if (pslot->put_volume && pslot->stereo) result |= 1 << chn; } return result; } static int snd_mixer_oss_recmask(struct snd_mixer_oss_file *fmixer) { struct snd_mixer_oss *mixer = fmixer->mixer; int result = 0; if (mixer == NULL) return -EIO; guard(mutex)(&mixer->reg_mutex); if (mixer->put_recsrc && mixer->get_recsrc) { /* exclusive */ result = mixer->mask_recsrc; } else { struct snd_mixer_oss_slot *pslot; int chn; for (chn = 0; chn < 31; chn++) { pslot = &mixer->slots[chn]; if (pslot->put_recsrc) result |= 1 << chn; } } return result; } static int snd_mixer_oss_get_recsrc(struct snd_mixer_oss_file *fmixer) { struct snd_mixer_oss *mixer = fmixer->mixer; int result = 0; if (mixer == NULL) return -EIO; guard(mutex)(&mixer->reg_mutex); if (mixer->put_recsrc && mixer->get_recsrc) { /* exclusive */ unsigned int index; result = mixer->get_recsrc(fmixer, &index); if (result < 0) return result; result = 1 << index; } else { struct snd_mixer_oss_slot *pslot; int chn; for (chn = 0; chn < 31; chn++) { pslot = &mixer->slots[chn]; if (pslot->get_recsrc) { int active = 0; pslot->get_recsrc(fmixer, pslot, &active); if (active) result |= 1 << chn; } } } mixer->oss_recsrc = result; return result; } static int snd_mixer_oss_set_recsrc(struct snd_mixer_oss_file *fmixer, int recsrc) { struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_mixer_oss_slot *pslot; int chn, active; unsigned int index; int result = 0; if (mixer == NULL) return -EIO; guard(mutex)(&mixer->reg_mutex); if (mixer->get_recsrc && mixer->put_recsrc) { /* exclusive input */ if (recsrc & ~mixer->oss_recsrc) recsrc &= ~mixer->oss_recsrc; mixer->put_recsrc(fmixer, ffz(~recsrc)); mixer->get_recsrc(fmixer, &index); result = 1 << index; } for (chn = 0; chn < 31; chn++) { pslot = &mixer->slots[chn]; if (pslot->put_recsrc) { active = (recsrc & (1 << chn)) ? 1 : 0; pslot->put_recsrc(fmixer, pslot, active); } } if (! result) { for (chn = 0; chn < 31; chn++) { pslot = &mixer->slots[chn]; if (pslot->get_recsrc) { active = 0; pslot->get_recsrc(fmixer, pslot, &active); if (active) result |= 1 << chn; } } } return result; } static int snd_mixer_oss_get_volume(struct snd_mixer_oss_file *fmixer, int slot) { struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_mixer_oss_slot *pslot; int result = 0, left, right; if (mixer == NULL || slot > 30) return -EIO; guard(mutex)(&mixer->reg_mutex); pslot = &mixer->slots[slot]; left = pslot->volume[0]; right = pslot->volume[1]; if (pslot->get_volume) result = pslot->get_volume(fmixer, pslot, &left, &right); if (!pslot->stereo) right = left; if (snd_BUG_ON(left < 0 || left > 100)) return -EIO; if (snd_BUG_ON(right < 0 || right > 100)) return -EIO; if (result >= 0) { pslot->volume[0] = left; pslot->volume[1] = right; result = (left & 0xff) | ((right & 0xff) << 8); } return result; } static int snd_mixer_oss_set_volume(struct snd_mixer_oss_file *fmixer, int slot, int volume) { struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_mixer_oss_slot *pslot; int result = 0, left = volume & 0xff, right = (volume >> 8) & 0xff; if (mixer == NULL || slot > 30) return -EIO; guard(mutex)(&mixer->reg_mutex); pslot = &mixer->slots[slot]; if (left > 100) left = 100; if (right > 100) right = 100; if (!pslot->stereo) right = left; if (pslot->put_volume) result = pslot->put_volume(fmixer, pslot, left, right); if (result < 0) return result; pslot->volume[0] = left; pslot->volume[1] = right; result = (left & 0xff) | ((right & 0xff) << 8); return result; } static int snd_mixer_oss_ioctl1(struct snd_mixer_oss_file *fmixer, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; int __user *p = argp; int tmp; if (snd_BUG_ON(!fmixer)) return -ENXIO; if (((cmd >> 8) & 0xff) == 'M') { switch (cmd) { case SOUND_MIXER_INFO: return snd_mixer_oss_info(fmixer, argp); case SOUND_OLD_MIXER_INFO: return snd_mixer_oss_info_obsolete(fmixer, argp); case SOUND_MIXER_WRITE_RECSRC: if (get_user(tmp, p)) return -EFAULT; tmp = snd_mixer_oss_set_recsrc(fmixer, tmp); if (tmp < 0) return tmp; return put_user(tmp, p); case OSS_GETVERSION: return put_user(SNDRV_OSS_VERSION, p); case OSS_ALSAEMULVER: return put_user(1, p); case SOUND_MIXER_READ_DEVMASK: tmp = snd_mixer_oss_devmask(fmixer); if (tmp < 0) return tmp; return put_user(tmp, p); case SOUND_MIXER_READ_STEREODEVS: tmp = snd_mixer_oss_stereodevs(fmixer); if (tmp < 0) return tmp; return put_user(tmp, p); case SOUND_MIXER_READ_RECMASK: tmp = snd_mixer_oss_recmask(fmixer); if (tmp < 0) return tmp; return put_user(tmp, p); case SOUND_MIXER_READ_CAPS: tmp = snd_mixer_oss_caps(fmixer); if (tmp < 0) return tmp; return put_user(tmp, p); case SOUND_MIXER_READ_RECSRC: tmp = snd_mixer_oss_get_recsrc(fmixer); if (tmp < 0) return tmp; return put_user(tmp, p); } } if (cmd & SIOC_IN) { if (get_user(tmp, p)) return -EFAULT; tmp = snd_mixer_oss_set_volume(fmixer, cmd & 0xff, tmp); if (tmp < 0) return tmp; return put_user(tmp, p); } else if (cmd & SIOC_OUT) { tmp = snd_mixer_oss_get_volume(fmixer, cmd & 0xff); if (tmp < 0) return tmp; return put_user(tmp, p); } return -ENXIO; } static long snd_mixer_oss_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return snd_mixer_oss_ioctl1(file->private_data, cmd, arg); } int snd_mixer_oss_ioctl_card(struct snd_card *card, unsigned int cmd, unsigned long arg) { struct snd_mixer_oss_file fmixer; if (snd_BUG_ON(!card)) return -ENXIO; if (card->mixer_oss == NULL) return -ENXIO; memset(&fmixer, 0, sizeof(fmixer)); fmixer.card = card; fmixer.mixer = card->mixer_oss; return snd_mixer_oss_ioctl1(&fmixer, cmd, arg); } EXPORT_SYMBOL(snd_mixer_oss_ioctl_card); #ifdef CONFIG_COMPAT /* all compatible */ static long snd_mixer_oss_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return snd_mixer_oss_ioctl1(file->private_data, cmd, (unsigned long)compat_ptr(arg)); } #else #define snd_mixer_oss_ioctl_compat NULL #endif /* * REGISTRATION PART */ static const struct file_operations snd_mixer_oss_f_ops = { .owner = THIS_MODULE, .open = snd_mixer_oss_open, .release = snd_mixer_oss_release, .unlocked_ioctl = snd_mixer_oss_ioctl, .compat_ioctl = snd_mixer_oss_ioctl_compat, }; /* * utilities */ static long snd_mixer_oss_conv(long val, long omin, long omax, long nmin, long nmax) { long orange = omax - omin, nrange = nmax - nmin; if (orange == 0) return 0; return DIV_ROUND_CLOSEST(nrange * (val - omin), orange) + nmin; } /* convert from alsa native to oss values (0-100) */ static long snd_mixer_oss_conv1(long val, long min, long max, int *old) { if (val == snd_mixer_oss_conv(*old, 0, 100, min, max)) return *old; return snd_mixer_oss_conv(val, min, max, 0, 100); } /* convert from oss to alsa native values */ static long snd_mixer_oss_conv2(long val, long min, long max) { return snd_mixer_oss_conv(val, 0, 100, min, max); } #if 0 static void snd_mixer_oss_recsrce_set(struct snd_card *card, int slot) { struct snd_mixer_oss *mixer = card->mixer_oss; if (mixer) mixer->mask_recsrc |= 1 << slot; } static int snd_mixer_oss_recsrce_get(struct snd_card *card, int slot) { struct snd_mixer_oss *mixer = card->mixer_oss; if (mixer && (mixer->mask_recsrc & (1 << slot))) return 1; return 0; } #endif #define SNDRV_MIXER_OSS_SIGNATURE 0x65999250 #define SNDRV_MIXER_OSS_ITEM_GLOBAL 0 #define SNDRV_MIXER_OSS_ITEM_GSWITCH 1 #define SNDRV_MIXER_OSS_ITEM_GROUTE 2 #define SNDRV_MIXER_OSS_ITEM_GVOLUME 3 #define SNDRV_MIXER_OSS_ITEM_PSWITCH 4 #define SNDRV_MIXER_OSS_ITEM_PROUTE 5 #define SNDRV_MIXER_OSS_ITEM_PVOLUME 6 #define SNDRV_MIXER_OSS_ITEM_CSWITCH 7 #define SNDRV_MIXER_OSS_ITEM_CROUTE 8 #define SNDRV_MIXER_OSS_ITEM_CVOLUME 9 #define SNDRV_MIXER_OSS_ITEM_CAPTURE 10 #define SNDRV_MIXER_OSS_ITEM_COUNT 11 #define SNDRV_MIXER_OSS_PRESENT_GLOBAL (1<<0) #define SNDRV_MIXER_OSS_PRESENT_GSWITCH (1<<1) #define SNDRV_MIXER_OSS_PRESENT_GROUTE (1<<2) #define SNDRV_MIXER_OSS_PRESENT_GVOLUME (1<<3) #define SNDRV_MIXER_OSS_PRESENT_PSWITCH (1<<4) #define SNDRV_MIXER_OSS_PRESENT_PROUTE (1<<5) #define SNDRV_MIXER_OSS_PRESENT_PVOLUME (1<<6) #define SNDRV_MIXER_OSS_PRESENT_CSWITCH (1<<7) #define SNDRV_MIXER_OSS_PRESENT_CROUTE (1<<8) #define SNDRV_MIXER_OSS_PRESENT_CVOLUME (1<<9) #define SNDRV_MIXER_OSS_PRESENT_CAPTURE (1<<10) struct slot { unsigned int signature; unsigned int present; unsigned int channels; unsigned int numid[SNDRV_MIXER_OSS_ITEM_COUNT]; unsigned int capture_item; const struct snd_mixer_oss_assign_table *assigned; unsigned int allocated: 1; }; #define ID_UNKNOWN ((unsigned int)-1) static struct snd_kcontrol *snd_mixer_oss_test_id(struct snd_mixer_oss *mixer, const char *name, int index) { struct snd_card *card = mixer->card; struct snd_ctl_elem_id id; memset(&id, 0, sizeof(id)); id.iface = SNDRV_CTL_ELEM_IFACE_MIXER; strscpy(id.name, name, sizeof(id.name)); id.index = index; return snd_ctl_find_id(card, &id); } static void snd_mixer_oss_get_volume1_vol(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, unsigned int numid, int *left, int *right) { struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; struct snd_ctl_elem_value *uctl __free(kfree) = NULL; struct snd_kcontrol *kctl; struct snd_card *card = fmixer->card; if (numid == ID_UNKNOWN) return; guard(rwsem_read)(&card->controls_rwsem); kctl = snd_ctl_find_numid(card, numid); if (!kctl) return; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (uinfo == NULL || uctl == NULL) return; if (kctl->info(kctl, uinfo)) return; if (kctl->get(kctl, uctl)) return; if (uinfo->type == SNDRV_CTL_ELEM_TYPE_BOOLEAN && uinfo->value.integer.min == 0 && uinfo->value.integer.max == 1) return; *left = snd_mixer_oss_conv1(uctl->value.integer.value[0], uinfo->value.integer.min, uinfo->value.integer.max, &pslot->volume[0]); if (uinfo->count > 1) *right = snd_mixer_oss_conv1(uctl->value.integer.value[1], uinfo->value.integer.min, uinfo->value.integer.max, &pslot->volume[1]); } static void snd_mixer_oss_get_volume1_sw(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, unsigned int numid, int *left, int *right, int route) { struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; struct snd_ctl_elem_value *uctl __free(kfree) = NULL; struct snd_kcontrol *kctl; struct snd_card *card = fmixer->card; if (numid == ID_UNKNOWN) return; guard(rwsem_read)(&card->controls_rwsem); kctl = snd_ctl_find_numid(card, numid); if (!kctl) return; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (uinfo == NULL || uctl == NULL) return; if (kctl->info(kctl, uinfo)) return; if (kctl->get(kctl, uctl)) return; if (!uctl->value.integer.value[0]) { *left = 0; if (uinfo->count == 1) *right = 0; } if (uinfo->count > 1 && !uctl->value.integer.value[route ? 3 : 1]) *right = 0; } static int snd_mixer_oss_get_volume1(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, int *left, int *right) { struct slot *slot = pslot->private_data; *left = *right = 100; if (slot->present & SNDRV_MIXER_OSS_PRESENT_PVOLUME) { snd_mixer_oss_get_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PVOLUME], left, right); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GVOLUME) { snd_mixer_oss_get_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GVOLUME], left, right); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GLOBAL) { snd_mixer_oss_get_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GLOBAL], left, right); } if (slot->present & SNDRV_MIXER_OSS_PRESENT_PSWITCH) { snd_mixer_oss_get_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PSWITCH], left, right, 0); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GSWITCH) { snd_mixer_oss_get_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GSWITCH], left, right, 0); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_PROUTE) { snd_mixer_oss_get_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PROUTE], left, right, 1); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GROUTE) { snd_mixer_oss_get_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GROUTE], left, right, 1); } return 0; } static void snd_mixer_oss_put_volume1_vol(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, unsigned int numid, int left, int right) { struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; struct snd_ctl_elem_value *uctl __free(kfree) = NULL; struct snd_kcontrol *kctl; struct snd_card *card = fmixer->card; int res; if (numid == ID_UNKNOWN) return; guard(rwsem_read)(&card->controls_rwsem); kctl = snd_ctl_find_numid(card, numid); if (!kctl) return; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (uinfo == NULL || uctl == NULL) return; if (kctl->info(kctl, uinfo)) return; if (uinfo->type == SNDRV_CTL_ELEM_TYPE_BOOLEAN && uinfo->value.integer.min == 0 && uinfo->value.integer.max == 1) return; uctl->value.integer.value[0] = snd_mixer_oss_conv2(left, uinfo->value.integer.min, uinfo->value.integer.max); if (uinfo->count > 1) uctl->value.integer.value[1] = snd_mixer_oss_conv2(right, uinfo->value.integer.min, uinfo->value.integer.max); res = kctl->put(kctl, uctl); if (res < 0) return; if (res > 0) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &kctl->id); } static void snd_mixer_oss_put_volume1_sw(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, unsigned int numid, int left, int right, int route) { struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; struct snd_ctl_elem_value *uctl __free(kfree) = NULL; struct snd_kcontrol *kctl; struct snd_card *card = fmixer->card; int res; if (numid == ID_UNKNOWN) return; guard(rwsem_read)(&card->controls_rwsem); kctl = snd_ctl_find_numid(card, numid); if (!kctl) return; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (uinfo == NULL || uctl == NULL) return; if (kctl->info(kctl, uinfo)) return; if (uinfo->count > 1) { uctl->value.integer.value[0] = left > 0 ? 1 : 0; uctl->value.integer.value[route ? 3 : 1] = right > 0 ? 1 : 0; if (route) { uctl->value.integer.value[1] = uctl->value.integer.value[2] = 0; } } else { uctl->value.integer.value[0] = (left > 0 || right > 0) ? 1 : 0; } res = kctl->put(kctl, uctl); if (res < 0) return; if (res > 0) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &kctl->id); } static int snd_mixer_oss_put_volume1(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, int left, int right) { struct slot *slot = pslot->private_data; if (slot->present & SNDRV_MIXER_OSS_PRESENT_PVOLUME) { snd_mixer_oss_put_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PVOLUME], left, right); if (slot->present & SNDRV_MIXER_OSS_PRESENT_CVOLUME) snd_mixer_oss_put_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CVOLUME], left, right); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_CVOLUME) { snd_mixer_oss_put_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CVOLUME], left, right); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GVOLUME) { snd_mixer_oss_put_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GVOLUME], left, right); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GLOBAL) { snd_mixer_oss_put_volume1_vol(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GLOBAL], left, right); } if (left || right) { if (slot->present & SNDRV_MIXER_OSS_PRESENT_PSWITCH) snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PSWITCH], left, right, 0); if (slot->present & SNDRV_MIXER_OSS_PRESENT_CSWITCH) snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CSWITCH], left, right, 0); if (slot->present & SNDRV_MIXER_OSS_PRESENT_GSWITCH) snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GSWITCH], left, right, 0); if (slot->present & SNDRV_MIXER_OSS_PRESENT_PROUTE) snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PROUTE], left, right, 1); if (slot->present & SNDRV_MIXER_OSS_PRESENT_CROUTE) snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CROUTE], left, right, 1); if (slot->present & SNDRV_MIXER_OSS_PRESENT_GROUTE) snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GROUTE], left, right, 1); } else { if (slot->present & SNDRV_MIXER_OSS_PRESENT_PSWITCH) { snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PSWITCH], left, right, 0); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_CSWITCH) { snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CSWITCH], left, right, 0); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GSWITCH) { snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GSWITCH], left, right, 0); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_PROUTE) { snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_PROUTE], left, right, 1); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_CROUTE) { snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CROUTE], left, right, 1); } else if (slot->present & SNDRV_MIXER_OSS_PRESENT_GROUTE) { snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_GROUTE], left, right, 1); } } return 0; } static int snd_mixer_oss_get_recsrc1_sw(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, int *active) { struct slot *slot = pslot->private_data; int left, right; left = right = 1; snd_mixer_oss_get_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CSWITCH], &left, &right, 0); *active = (left || right) ? 1 : 0; return 0; } static int snd_mixer_oss_get_recsrc1_route(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, int *active) { struct slot *slot = pslot->private_data; int left, right; left = right = 1; snd_mixer_oss_get_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CROUTE], &left, &right, 1); *active = (left || right) ? 1 : 0; return 0; } static int snd_mixer_oss_put_recsrc1_sw(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, int active) { struct slot *slot = pslot->private_data; snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CSWITCH], active, active, 0); return 0; } static int snd_mixer_oss_put_recsrc1_route(struct snd_mixer_oss_file *fmixer, struct snd_mixer_oss_slot *pslot, int active) { struct slot *slot = pslot->private_data; snd_mixer_oss_put_volume1_sw(fmixer, pslot, slot->numid[SNDRV_MIXER_OSS_ITEM_CROUTE], active, active, 1); return 0; } static int snd_mixer_oss_get_recsrc2(struct snd_mixer_oss_file *fmixer, unsigned int *active_index) { struct snd_card *card = fmixer->card; struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_kcontrol *kctl; struct snd_mixer_oss_slot *pslot; struct slot *slot; struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; struct snd_ctl_elem_value *uctl __free(kfree) = NULL; int err, idx; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (uinfo == NULL || uctl == NULL) return -ENOMEM; guard(rwsem_read)(&card->controls_rwsem); kctl = snd_mixer_oss_test_id(mixer, "Capture Source", 0); if (!kctl) return -ENOENT; err = kctl->info(kctl, uinfo); if (err < 0) return err; err = kctl->get(kctl, uctl); if (err < 0) return err; for (idx = 0; idx < 32; idx++) { if (!(mixer->mask_recsrc & (1 << idx))) continue; pslot = &mixer->slots[idx]; slot = pslot->private_data; if (slot->signature != SNDRV_MIXER_OSS_SIGNATURE) continue; if (!(slot->present & SNDRV_MIXER_OSS_PRESENT_CAPTURE)) continue; if (slot->capture_item == uctl->value.enumerated.item[0]) { *active_index = idx; break; } } return 0; } static int snd_mixer_oss_put_recsrc2(struct snd_mixer_oss_file *fmixer, unsigned int active_index) { struct snd_card *card = fmixer->card; struct snd_mixer_oss *mixer = fmixer->mixer; struct snd_kcontrol *kctl; struct snd_mixer_oss_slot *pslot; struct slot *slot = NULL; struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; struct snd_ctl_elem_value *uctl __free(kfree) = NULL; int err; unsigned int idx; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (uinfo == NULL || uctl == NULL) return -ENOMEM; guard(rwsem_read)(&card->controls_rwsem); kctl = snd_mixer_oss_test_id(mixer, "Capture Source", 0); if (!kctl) return -ENOENT; err = kctl->info(kctl, uinfo); if (err < 0) return err; for (idx = 0; idx < 32; idx++) { if (!(mixer->mask_recsrc & (1 << idx))) continue; pslot = &mixer->slots[idx]; slot = pslot->private_data; if (slot->signature != SNDRV_MIXER_OSS_SIGNATURE) continue; if (!(slot->present & SNDRV_MIXER_OSS_PRESENT_CAPTURE)) continue; if (idx == active_index) break; slot = NULL; } if (!slot) return 0; for (idx = 0; idx < uinfo->count; idx++) uctl->value.enumerated.item[idx] = slot->capture_item; err = kctl->put(kctl, uctl); if (err > 0) snd_ctl_notify(fmixer->card, SNDRV_CTL_EVENT_MASK_VALUE, &kctl->id); return 0; } struct snd_mixer_oss_assign_table { int oss_id; const char *name; int index; }; static int snd_mixer_oss_build_test(struct snd_mixer_oss *mixer, struct slot *slot, const char *name, int index, int item) { struct snd_ctl_elem_info *info __free(kfree) = NULL; struct snd_kcontrol *kcontrol; struct snd_card *card = mixer->card; int err; scoped_guard(rwsem_read, &card->controls_rwsem) { kcontrol = snd_mixer_oss_test_id(mixer, name, index); if (kcontrol == NULL) return 0; info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; err = kcontrol->info(kcontrol, info); if (err < 0) return err; slot->numid[item] = kcontrol->id.numid; } if (info->count > slot->channels) slot->channels = info->count; slot->present |= 1 << item; return 0; } static void snd_mixer_oss_slot_free(struct snd_mixer_oss_slot *chn) { struct slot *p = chn->private_data; if (p) { if (p->allocated && p->assigned) { kfree(p->assigned->name); kfree(p->assigned); } kfree(p); } } static void mixer_slot_clear(struct snd_mixer_oss_slot *rslot) { int idx = rslot->number; /* remember this */ if (rslot->private_free) rslot->private_free(rslot); memset(rslot, 0, sizeof(*rslot)); rslot->number = idx; } /* In a separate function to keep gcc 3.2 happy - do NOT merge this in snd_mixer_oss_build_input! */ static int snd_mixer_oss_build_test_all(struct snd_mixer_oss *mixer, const struct snd_mixer_oss_assign_table *ptr, struct slot *slot) { char str[64]; int err; err = snd_mixer_oss_build_test(mixer, slot, ptr->name, ptr->index, SNDRV_MIXER_OSS_ITEM_GLOBAL); if (err) return err; sprintf(str, "%s Switch", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_GSWITCH); if (err) return err; sprintf(str, "%s Route", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_GROUTE); if (err) return err; sprintf(str, "%s Volume", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_GVOLUME); if (err) return err; sprintf(str, "%s Playback Switch", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_PSWITCH); if (err) return err; sprintf(str, "%s Playback Route", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_PROUTE); if (err) return err; sprintf(str, "%s Playback Volume", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_PVOLUME); if (err) return err; sprintf(str, "%s Capture Switch", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_CSWITCH); if (err) return err; sprintf(str, "%s Capture Route", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_CROUTE); if (err) return err; sprintf(str, "%s Capture Volume", ptr->name); err = snd_mixer_oss_build_test(mixer, slot, str, ptr->index, SNDRV_MIXER_OSS_ITEM_CVOLUME); if (err) return err; return 0; } /* * build an OSS mixer element. * ptr_allocated means the entry is dynamically allocated (change via proc file). * when replace_old = 1, the old entry is replaced with the new one. */ static int snd_mixer_oss_build_input(struct snd_mixer_oss *mixer, const struct snd_mixer_oss_assign_table *ptr, int ptr_allocated, int replace_old) { struct slot slot; struct slot *pslot; struct snd_kcontrol *kctl; struct snd_mixer_oss_slot *rslot; const char *str; /* check if already assigned */ if (mixer->slots[ptr->oss_id].get_volume && ! replace_old) return 0; memset(&slot, 0, sizeof(slot)); memset(slot.numid, 0xff, sizeof(slot.numid)); /* ID_UNKNOWN */ if (snd_mixer_oss_build_test_all(mixer, ptr, &slot)) return 0; guard(rwsem_read)(&mixer->card->controls_rwsem); kctl = NULL; if (!ptr->index) kctl = snd_mixer_oss_test_id(mixer, "Capture Source", 0); if (kctl) { struct snd_ctl_elem_info *uinfo __free(kfree) = NULL; uinfo = kzalloc(sizeof(*uinfo), GFP_KERNEL); if (!uinfo) return -ENOMEM; if (kctl->info(kctl, uinfo)) return 0; str = ptr->name; if (!strcmp(str, "Master")) str = "Mix"; else if (!strcmp(str, "Master Mono")) str = "Mix Mono"; slot.capture_item = 0; if (!strcmp(uinfo->value.enumerated.name, str)) { slot.present |= SNDRV_MIXER_OSS_PRESENT_CAPTURE; } else { for (slot.capture_item = 1; slot.capture_item < uinfo->value.enumerated.items; slot.capture_item++) { uinfo->value.enumerated.item = slot.capture_item; if (kctl->info(kctl, uinfo)) return 0; if (!strcmp(uinfo->value.enumerated.name, str)) { slot.present |= SNDRV_MIXER_OSS_PRESENT_CAPTURE; break; } } } } if (slot.present != 0) { pslot = kmalloc(sizeof(slot), GFP_KERNEL); if (! pslot) return -ENOMEM; *pslot = slot; pslot->signature = SNDRV_MIXER_OSS_SIGNATURE; pslot->assigned = ptr; pslot->allocated = ptr_allocated; rslot = &mixer->slots[ptr->oss_id]; mixer_slot_clear(rslot); rslot->stereo = slot.channels > 1 ? 1 : 0; rslot->get_volume = snd_mixer_oss_get_volume1; rslot->put_volume = snd_mixer_oss_put_volume1; /* note: ES18xx have both Capture Source and XX Capture Volume !!! */ if (slot.present & SNDRV_MIXER_OSS_PRESENT_CSWITCH) { rslot->get_recsrc = snd_mixer_oss_get_recsrc1_sw; rslot->put_recsrc = snd_mixer_oss_put_recsrc1_sw; } else if (slot.present & SNDRV_MIXER_OSS_PRESENT_CROUTE) { rslot->get_recsrc = snd_mixer_oss_get_recsrc1_route; rslot->put_recsrc = snd_mixer_oss_put_recsrc1_route; } else if (slot.present & SNDRV_MIXER_OSS_PRESENT_CAPTURE) { mixer->mask_recsrc |= 1 << ptr->oss_id; } rslot->private_data = pslot; rslot->private_free = snd_mixer_oss_slot_free; return 1; } return 0; } #ifdef CONFIG_SND_PROC_FS /* */ #define MIXER_VOL(name) [SOUND_MIXER_##name] = #name static const char * const oss_mixer_names[SNDRV_OSS_MAX_MIXERS] = { MIXER_VOL(VOLUME), MIXER_VOL(BASS), MIXER_VOL(TREBLE), MIXER_VOL(SYNTH), MIXER_VOL(PCM), MIXER_VOL(SPEAKER), MIXER_VOL(LINE), MIXER_VOL(MIC), MIXER_VOL(CD), MIXER_VOL(IMIX), MIXER_VOL(ALTPCM), MIXER_VOL(RECLEV), MIXER_VOL(IGAIN), MIXER_VOL(OGAIN), MIXER_VOL(LINE1), MIXER_VOL(LINE2), MIXER_VOL(LINE3), MIXER_VOL(DIGITAL1), MIXER_VOL(DIGITAL2), MIXER_VOL(DIGITAL3), MIXER_VOL(PHONEIN), MIXER_VOL(PHONEOUT), MIXER_VOL(VIDEO), MIXER_VOL(RADIO), MIXER_VOL(MONITOR), }; /* * /proc interface */ static void snd_mixer_oss_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_mixer_oss *mixer = entry->private_data; int i; guard(mutex)(&mixer->reg_mutex); for (i = 0; i < SNDRV_OSS_MAX_MIXERS; i++) { struct slot *p; if (! oss_mixer_names[i]) continue; p = (struct slot *)mixer->slots[i].private_data; snd_iprintf(buffer, "%s ", oss_mixer_names[i]); if (p && p->assigned) snd_iprintf(buffer, "\"%s\" %d\n", p->assigned->name, p->assigned->index); else snd_iprintf(buffer, "\"\" 0\n"); } } static void snd_mixer_oss_proc_write(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_mixer_oss *mixer = entry->private_data; char line[128], str[32], idxstr[16]; const char *cptr; unsigned int idx; int ch; struct snd_mixer_oss_assign_table *tbl; struct slot *slot; while (!snd_info_get_line(buffer, line, sizeof(line))) { cptr = snd_info_get_str(str, line, sizeof(str)); for (ch = 0; ch < SNDRV_OSS_MAX_MIXERS; ch++) if (oss_mixer_names[ch] && strcmp(oss_mixer_names[ch], str) == 0) break; if (ch >= SNDRV_OSS_MAX_MIXERS) { pr_err("ALSA: mixer_oss: invalid OSS volume '%s'\n", str); continue; } cptr = snd_info_get_str(str, cptr, sizeof(str)); if (! *str) { /* remove the entry */ scoped_guard(mutex, &mixer->reg_mutex) mixer_slot_clear(&mixer->slots[ch]); continue; } snd_info_get_str(idxstr, cptr, sizeof(idxstr)); idx = simple_strtoul(idxstr, NULL, 10); if (idx >= 0x4000) { /* too big */ pr_err("ALSA: mixer_oss: invalid index %d\n", idx); continue; } scoped_guard(mutex, &mixer->reg_mutex) { slot = (struct slot *)mixer->slots[ch].private_data; if (slot && slot->assigned && slot->assigned->index == idx && !strcmp(slot->assigned->name, str)) /* not changed */ break; tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); if (!tbl) break; tbl->oss_id = ch; tbl->name = kstrdup(str, GFP_KERNEL); if (!tbl->name) { kfree(tbl); break; } tbl->index = idx; if (snd_mixer_oss_build_input(mixer, tbl, 1, 1) <= 0) { kfree(tbl->name); kfree(tbl); } } } } static void snd_mixer_oss_proc_init(struct snd_mixer_oss *mixer) { struct snd_info_entry *entry; entry = snd_info_create_card_entry(mixer->card, "oss_mixer", mixer->card->proc_root); if (! entry) return; entry->content = SNDRV_INFO_CONTENT_TEXT; entry->mode = S_IFREG | 0644; entry->c.text.read = snd_mixer_oss_proc_read; entry->c.text.write = snd_mixer_oss_proc_write; entry->private_data = mixer; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } mixer->proc_entry = entry; } static void snd_mixer_oss_proc_done(struct snd_mixer_oss *mixer) { snd_info_free_entry(mixer->proc_entry); mixer->proc_entry = NULL; } #else /* !CONFIG_SND_PROC_FS */ #define snd_mixer_oss_proc_init(mix) #define snd_mixer_oss_proc_done(mix) #endif /* CONFIG_SND_PROC_FS */ static void snd_mixer_oss_build(struct snd_mixer_oss *mixer) { static const struct snd_mixer_oss_assign_table table[] = { { SOUND_MIXER_VOLUME, "Master", 0 }, { SOUND_MIXER_VOLUME, "Front", 0 }, /* fallback */ { SOUND_MIXER_BASS, "Tone Control - Bass", 0 }, { SOUND_MIXER_TREBLE, "Tone Control - Treble", 0 }, { SOUND_MIXER_SYNTH, "Synth", 0 }, { SOUND_MIXER_SYNTH, "FM", 0 }, /* fallback */ { SOUND_MIXER_SYNTH, "Music", 0 }, /* fallback */ { SOUND_MIXER_PCM, "PCM", 0 }, { SOUND_MIXER_SPEAKER, "Beep", 0 }, { SOUND_MIXER_SPEAKER, "PC Speaker", 0 }, /* fallback */ { SOUND_MIXER_SPEAKER, "Speaker", 0 }, /* fallback */ { SOUND_MIXER_LINE, "Line", 0 }, { SOUND_MIXER_MIC, "Mic", 0 }, { SOUND_MIXER_CD, "CD", 0 }, { SOUND_MIXER_IMIX, "Monitor Mix", 0 }, { SOUND_MIXER_ALTPCM, "PCM", 1 }, { SOUND_MIXER_ALTPCM, "Headphone", 0 }, /* fallback */ { SOUND_MIXER_ALTPCM, "Wave", 0 }, /* fallback */ { SOUND_MIXER_RECLEV, "-- nothing --", 0 }, { SOUND_MIXER_IGAIN, "Capture", 0 }, { SOUND_MIXER_OGAIN, "Playback", 0 }, { SOUND_MIXER_LINE1, "Aux", 0 }, { SOUND_MIXER_LINE2, "Aux", 1 }, { SOUND_MIXER_LINE3, "Aux", 2 }, { SOUND_MIXER_DIGITAL1, "Digital", 0 }, { SOUND_MIXER_DIGITAL1, "IEC958", 0 }, /* fallback */ { SOUND_MIXER_DIGITAL1, "IEC958 Optical", 0 }, /* fallback */ { SOUND_MIXER_DIGITAL1, "IEC958 Coaxial", 0 }, /* fallback */ { SOUND_MIXER_DIGITAL2, "Digital", 1 }, { SOUND_MIXER_DIGITAL3, "Digital", 2 }, { SOUND_MIXER_PHONEIN, "Phone", 0 }, { SOUND_MIXER_PHONEOUT, "Master Mono", 0 }, { SOUND_MIXER_PHONEOUT, "Speaker", 0 }, /*fallback*/ { SOUND_MIXER_PHONEOUT, "Mono", 0 }, /*fallback*/ { SOUND_MIXER_PHONEOUT, "Phone", 0 }, /* fallback */ { SOUND_MIXER_VIDEO, "Video", 0 }, { SOUND_MIXER_RADIO, "Radio", 0 }, { SOUND_MIXER_MONITOR, "Monitor", 0 } }; unsigned int idx; for (idx = 0; idx < ARRAY_SIZE(table); idx++) snd_mixer_oss_build_input(mixer, &table[idx], 0, 0); if (mixer->mask_recsrc) { mixer->get_recsrc = snd_mixer_oss_get_recsrc2; mixer->put_recsrc = snd_mixer_oss_put_recsrc2; } } /* * */ static int snd_mixer_oss_free1(void *private) { struct snd_mixer_oss *mixer = private; struct snd_card *card; int idx; if (!mixer) return 0; card = mixer->card; if (snd_BUG_ON(mixer != card->mixer_oss)) return -ENXIO; card->mixer_oss = NULL; for (idx = 0; idx < SNDRV_OSS_MAX_MIXERS; idx++) { struct snd_mixer_oss_slot *chn = &mixer->slots[idx]; if (chn->private_free) chn->private_free(chn); } kfree(mixer); return 0; } static int snd_mixer_oss_notify_handler(struct snd_card *card, int cmd) { struct snd_mixer_oss *mixer; if (cmd == SND_MIXER_OSS_NOTIFY_REGISTER) { int idx, err; mixer = kcalloc(2, sizeof(*mixer), GFP_KERNEL); if (mixer == NULL) return -ENOMEM; mutex_init(&mixer->reg_mutex); err = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_MIXER, card, 0, &snd_mixer_oss_f_ops, card); if (err < 0) { dev_err(card->dev, "unable to register OSS mixer device %i:%i\n", card->number, 0); kfree(mixer); return err; } mixer->oss_dev_alloc = 1; mixer->card = card; if (*card->mixername) strscpy(mixer->name, card->mixername, sizeof(mixer->name)); else snprintf(mixer->name, sizeof(mixer->name), "mixer%i", card->number); #ifdef SNDRV_OSS_INFO_DEV_MIXERS snd_oss_info_register(SNDRV_OSS_INFO_DEV_MIXERS, card->number, mixer->name); #endif for (idx = 0; idx < SNDRV_OSS_MAX_MIXERS; idx++) mixer->slots[idx].number = idx; card->mixer_oss = mixer; snd_mixer_oss_build(mixer); snd_mixer_oss_proc_init(mixer); } else { mixer = card->mixer_oss; if (mixer == NULL) return 0; if (mixer->oss_dev_alloc) { #ifdef SNDRV_OSS_INFO_DEV_MIXERS snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_MIXERS, mixer->card->number); #endif snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_MIXER, mixer->card, 0); mixer->oss_dev_alloc = 0; } if (cmd == SND_MIXER_OSS_NOTIFY_DISCONNECT) return 0; snd_mixer_oss_proc_done(mixer); return snd_mixer_oss_free1(mixer); } return 0; } static int __init alsa_mixer_oss_init(void) { struct snd_card *card; int idx; snd_mixer_oss_notify_callback = snd_mixer_oss_notify_handler; for (idx = 0; idx < SNDRV_CARDS; idx++) { card = snd_card_ref(idx); if (card) { snd_mixer_oss_notify_handler(card, SND_MIXER_OSS_NOTIFY_REGISTER); snd_card_unref(card); } } return 0; } static void __exit alsa_mixer_oss_exit(void) { struct snd_card *card; int idx; snd_mixer_oss_notify_callback = NULL; for (idx = 0; idx < SNDRV_CARDS; idx++) { card = snd_card_ref(idx); if (card) { snd_mixer_oss_notify_handler(card, SND_MIXER_OSS_NOTIFY_FREE); snd_card_unref(card); } } } module_init(alsa_mixer_oss_init) module_exit(alsa_mixer_oss_exit) |
| 4 1 2 2 2 2 2 2 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" struct devlink_linecard { struct list_head list; struct devlink *devlink; unsigned int index; const struct devlink_linecard_ops *ops; void *priv; enum devlink_linecard_state state; struct mutex state_lock; /* Protects state */ const char *type; struct devlink_linecard_type *types; unsigned int types_count; u32 rel_index; }; unsigned int devlink_linecard_index(struct devlink_linecard *linecard) { return linecard->index; } static struct devlink_linecard * devlink_linecard_get_by_index(struct devlink *devlink, unsigned int linecard_index) { struct devlink_linecard *devlink_linecard; list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) { if (devlink_linecard->index == linecard_index) return devlink_linecard; } return NULL; } static bool devlink_linecard_index_exists(struct devlink *devlink, unsigned int linecard_index) { return devlink_linecard_get_by_index(devlink, linecard_index); } static struct devlink_linecard * devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) { u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]); struct devlink_linecard *linecard; linecard = devlink_linecard_get_by_index(devlink, linecard_index); if (!linecard) return ERR_PTR(-ENODEV); return linecard; } return ERR_PTR(-EINVAL); } static struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_linecard_get_from_attrs(devlink, info->attrs); } struct devlink_linecard_type { const char *type; const void *priv; }; static int devlink_nl_linecard_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_linecard *linecard, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct devlink_linecard_type *linecard_type; struct nlattr *attr; void *hdr; int i; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state)) goto nla_put_failure; if (linecard->type && nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type)) goto nla_put_failure; if (linecard->types_count) { attr = nla_nest_start(msg, DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES); if (!attr) goto nla_put_failure; for (i = 0; i < linecard->types_count; i++) { linecard_type = &linecard->types[i]; if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard_type->type)) { nla_nest_cancel(msg, attr); goto nla_put_failure; } } nla_nest_end(msg, attr); } if (devlink_rel_devlink_handle_put(msg, devlink, linecard->rel_index, DEVLINK_ATTR_NESTED_DEVLINK, NULL)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_linecard_notify(struct devlink_linecard *linecard, enum devlink_command cmd) { struct devlink *devlink = linecard->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW && cmd != DEVLINK_CMD_LINECARD_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } devlink_nl_notify_send(devlink, msg); } void devlink_linecards_notify_register(struct devlink *devlink) { struct devlink_linecard *linecard; list_for_each_entry(linecard, &devlink->linecard_list, list) devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); } void devlink_linecards_notify_unregister(struct devlink *devlink) { struct devlink_linecard *linecard; list_for_each_entry_reverse(linecard, &devlink->linecard_list, list) devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); } int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_linecard *linecard; struct sk_buff *msg; int err; linecard = devlink_linecard_get_from_info(devlink, info); if (IS_ERR(linecard)) return PTR_ERR(linecard); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; mutex_lock(&linecard->state_lock); err = devlink_nl_linecard_fill(msg, devlink, linecard, DEVLINK_CMD_LINECARD_NEW, info->snd_portid, info->snd_seq, 0, info->extack); mutex_unlock(&linecard->state_lock); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_linecard_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_linecard *linecard; int idx = 0; int err = 0; list_for_each_entry(linecard, &devlink->linecard_list, list) { if (idx < state->idx) { idx++; continue; } mutex_lock(&linecard->state_lock); err = devlink_nl_linecard_fill(msg, devlink, linecard, DEVLINK_CMD_LINECARD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); mutex_unlock(&linecard->state_lock); if (err) { state->idx = idx; break; } idx++; } return err; } int devlink_nl_linecard_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_linecard_get_dump_one); } static struct devlink_linecard_type * devlink_linecard_type_lookup(struct devlink_linecard *linecard, const char *type) { struct devlink_linecard_type *linecard_type; int i; for (i = 0; i < linecard->types_count; i++) { linecard_type = &linecard->types[i]; if (!strcmp(type, linecard_type->type)) return linecard_type; } return NULL; } static int devlink_linecard_type_set(struct devlink_linecard *linecard, const char *type, struct netlink_ext_ack *extack) { const struct devlink_linecard_ops *ops = linecard->ops; struct devlink_linecard_type *linecard_type; int err; mutex_lock(&linecard->state_lock); if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being provisioned"); err = -EBUSY; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned"); err = -EBUSY; goto out; } linecard_type = devlink_linecard_type_lookup(linecard, type); if (!linecard_type) { NL_SET_ERR_MSG(extack, "Unsupported line card type provided"); err = -EINVAL; goto out; } if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED && linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { NL_SET_ERR_MSG(extack, "Line card already provisioned"); err = -EBUSY; /* Check if the line card is provisioned in the same * way the user asks. In case it is, make the operation * to return success. */ if (ops->same_provision && ops->same_provision(linecard, linecard->priv, linecard_type->type, linecard_type->priv)) err = 0; goto out; } linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING; linecard->type = linecard_type->type; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); err = ops->provision(linecard, linecard->priv, linecard_type->type, linecard_type->priv, extack); if (err) { /* Provisioning failed. Assume the linecard is unprovisioned * for future operations. */ mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } return err; out: mutex_unlock(&linecard->state_lock); return err; } static int devlink_linecard_type_unset(struct devlink_linecard *linecard, struct netlink_ext_ack *extack) { int err; mutex_lock(&linecard->state_lock); if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being provisioned"); err = -EBUSY; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) { NL_SET_ERR_MSG(extack, "Line card is currently being unprovisioned"); err = -EBUSY; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) { linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); err = 0; goto out; } if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) { NL_SET_ERR_MSG(extack, "Line card is not provisioned"); err = 0; goto out; } linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); err = linecard->ops->unprovision(linecard, linecard->priv, extack); if (err) { /* Unprovisioning failed. Assume the linecard is unprovisioned * for future operations. */ mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } return err; out: mutex_unlock(&linecard->state_lock); return err; } int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct devlink_linecard *linecard; int err; linecard = devlink_linecard_get_from_info(devlink, info); if (IS_ERR(linecard)) return PTR_ERR(linecard); if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) { const char *type; type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]); if (strcmp(type, "")) { err = devlink_linecard_type_set(linecard, type, extack); if (err) return err; } else { err = devlink_linecard_type_unset(linecard, extack); if (err) return err; } } return 0; } static int devlink_linecard_types_init(struct devlink_linecard *linecard) { struct devlink_linecard_type *linecard_type; unsigned int count; int i; count = linecard->ops->types_count(linecard, linecard->priv); linecard->types = kmalloc_array(count, sizeof(*linecard_type), GFP_KERNEL); if (!linecard->types) return -ENOMEM; linecard->types_count = count; for (i = 0; i < count; i++) { linecard_type = &linecard->types[i]; linecard->ops->types_get(linecard, linecard->priv, i, &linecard_type->type, &linecard_type->priv); } return 0; } static void devlink_linecard_types_fini(struct devlink_linecard *linecard) { kfree(linecard->types); } /** * devl_linecard_create - Create devlink linecard * * @devlink: devlink * @linecard_index: driver-specific numerical identifier of the linecard * @ops: linecards ops * @priv: user priv pointer * * Create devlink linecard instance with provided linecard index. * Caller can use any indexing, even hw-related one. * * Return: Line card structure or an ERR_PTR() encoded error code. */ struct devlink_linecard * devl_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv) { struct devlink_linecard *linecard; int err; if (WARN_ON(!ops || !ops->provision || !ops->unprovision || !ops->types_count || !ops->types_get)) return ERR_PTR(-EINVAL); if (devlink_linecard_index_exists(devlink, linecard_index)) return ERR_PTR(-EEXIST); linecard = kzalloc(sizeof(*linecard), GFP_KERNEL); if (!linecard) return ERR_PTR(-ENOMEM); linecard->devlink = devlink; linecard->index = linecard_index; linecard->ops = ops; linecard->priv = priv; linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; mutex_init(&linecard->state_lock); err = devlink_linecard_types_init(linecard); if (err) { mutex_destroy(&linecard->state_lock); kfree(linecard); return ERR_PTR(err); } list_add_tail(&linecard->list, &devlink->linecard_list); devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); return linecard; } EXPORT_SYMBOL_GPL(devl_linecard_create); /** * devl_linecard_destroy - Destroy devlink linecard * * @linecard: devlink linecard */ void devl_linecard_destroy(struct devlink_linecard *linecard) { devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL); list_del(&linecard->list); devlink_linecard_types_fini(linecard); mutex_destroy(&linecard->state_lock); kfree(linecard); } EXPORT_SYMBOL_GPL(devl_linecard_destroy); /** * devlink_linecard_provision_set - Set provisioning on linecard * * @linecard: devlink linecard * @type: linecard type * * This is either called directly from the provision() op call or * as a result of the provision() op call asynchronously. */ void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type) { mutex_lock(&linecard->state_lock); WARN_ON(linecard->type && strcmp(linecard->type, type)); linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; linecard->type = type; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_provision_set); /** * devlink_linecard_provision_clear - Clear provisioning on linecard * * @linecard: devlink linecard * * This is either called directly from the unprovision() op call or * as a result of the unprovision() op call asynchronously. */ void devlink_linecard_provision_clear(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED; linecard->type = NULL; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear); /** * devlink_linecard_provision_fail - Fail provisioning on linecard * * @linecard: devlink linecard * * This is either called directly from the provision() op call or * as a result of the provision() op call asynchronously. */ void devlink_linecard_provision_fail(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail); /** * devlink_linecard_activate - Set linecard active * * @linecard: devlink linecard */ void devlink_linecard_activate(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED); linecard->state = DEVLINK_LINECARD_STATE_ACTIVE; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_activate); /** * devlink_linecard_deactivate - Set linecard inactive * * @linecard: devlink linecard */ void devlink_linecard_deactivate(struct devlink_linecard *linecard) { mutex_lock(&linecard->state_lock); switch (linecard->state) { case DEVLINK_LINECARD_STATE_ACTIVE: linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); break; case DEVLINK_LINECARD_STATE_UNPROVISIONING: /* Line card is being deactivated as part * of unprovisioning flow. */ break; default: WARN_ON(1); break; } mutex_unlock(&linecard->state_lock); } EXPORT_SYMBOL_GPL(devlink_linecard_deactivate); static void devlink_linecard_rel_notify_cb(struct devlink *devlink, u32 linecard_index) { struct devlink_linecard *linecard; linecard = devlink_linecard_get_by_index(devlink, linecard_index); if (!linecard) return; devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW); } static void devlink_linecard_rel_cleanup_cb(struct devlink *devlink, u32 linecard_index, u32 rel_index) { struct devlink_linecard *linecard; linecard = devlink_linecard_get_by_index(devlink, linecard_index); if (linecard && linecard->rel_index == rel_index) linecard->rel_index = 0; } /** * devlink_linecard_nested_dl_set - Attach/detach nested devlink * instance to linecard. * * @linecard: devlink linecard * @nested_devlink: devlink instance to attach or NULL to detach */ int devlink_linecard_nested_dl_set(struct devlink_linecard *linecard, struct devlink *nested_devlink) { return devlink_rel_nested_in_add(&linecard->rel_index, linecard->devlink->index, linecard->index, devlink_linecard_rel_notify_cb, devlink_linecard_rel_cleanup_cb, nested_devlink); } EXPORT_SYMBOL_GPL(devlink_linecard_nested_dl_set); |
| 6 6 31 31 31 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 | // SPDX-License-Identifier: GPL-2.0-or-later /* In-software asymmetric public-key crypto subtype * * See Documentation/crypto/asymmetric-keys.rst * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) "PKEY: "fmt #include <crypto/akcipher.h> #include <crypto/public_key.h> #include <crypto/sig.h> #include <keys/asymmetric-subtype.h> #include <linux/asn1.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> MODULE_DESCRIPTION("In-software asymmetric public-key subtype"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); /* * Provide a part of a description of the key for /proc/keys. */ static void public_key_describe(const struct key *asymmetric_key, struct seq_file *m) { struct public_key *key = asymmetric_key->payload.data[asym_crypto]; if (key) seq_printf(m, "%s.%s", key->id_type, key->pkey_algo); } /* * Destroy a public key algorithm key. */ void public_key_free(struct public_key *key) { if (key) { kfree_sensitive(key->key); kfree(key->params); kfree(key); } } EXPORT_SYMBOL_GPL(public_key_free); /* * Destroy a public key algorithm key. */ static void public_key_destroy(void *payload0, void *payload3) { public_key_free(payload0); public_key_signature_free(payload3); } /* * Given a public_key, and an encoding and hash_algo to be used for signing * and/or verification with that key, determine the name of the corresponding * akcipher algorithm. Also check that encoding and hash_algo are allowed. */ static int software_key_determine_akcipher(const struct public_key *pkey, const char *encoding, const char *hash_algo, char alg_name[CRYPTO_MAX_ALG_NAME], bool *sig, enum kernel_pkey_operation op) { int n; *sig = true; if (!encoding) return -EINVAL; if (strcmp(pkey->pkey_algo, "rsa") == 0) { /* * RSA signatures usually use EMSA-PKCS1-1_5 [RFC3447 sec 8.2]. */ if (strcmp(encoding, "pkcs1") == 0) { *sig = op == kernel_pkey_sign || op == kernel_pkey_verify; if (!*sig) { /* * For encrypt/decrypt, hash_algo is not used * but allowed to be set for historic reasons. */ n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)", pkey->pkey_algo); } else { if (!hash_algo) hash_algo = "none"; n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, "pkcs1(%s,%s)", pkey->pkey_algo, hash_algo); } return n >= CRYPTO_MAX_ALG_NAME ? -EINVAL : 0; } if (strcmp(encoding, "raw") != 0) return -EINVAL; /* * Raw RSA cannot differentiate between different hash * algorithms. */ if (hash_algo) return -EINVAL; *sig = false; } else if (strncmp(pkey->pkey_algo, "ecdsa", 5) == 0) { if (strcmp(encoding, "x962") != 0 && strcmp(encoding, "p1363") != 0) return -EINVAL; /* * ECDSA signatures are taken over a raw hash, so they don't * differentiate between different hash algorithms. That means * that the verifier should hard-code a specific hash algorithm. * Unfortunately, in practice ECDSA is used with multiple SHAs, * so we have to allow all of them and not just one. */ if (!hash_algo) return -EINVAL; if (strcmp(hash_algo, "sha1") != 0 && strcmp(hash_algo, "sha224") != 0 && strcmp(hash_algo, "sha256") != 0 && strcmp(hash_algo, "sha384") != 0 && strcmp(hash_algo, "sha512") != 0 && strcmp(hash_algo, "sha3-256") != 0 && strcmp(hash_algo, "sha3-384") != 0 && strcmp(hash_algo, "sha3-512") != 0) return -EINVAL; n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", encoding, pkey->pkey_algo); return n >= CRYPTO_MAX_ALG_NAME ? -EINVAL : 0; } else if (strcmp(pkey->pkey_algo, "ecrdsa") == 0) { if (strcmp(encoding, "raw") != 0) return -EINVAL; if (!hash_algo) return -EINVAL; if (strcmp(hash_algo, "streebog256") != 0 && strcmp(hash_algo, "streebog512") != 0) return -EINVAL; } else { /* Unknown public key algorithm */ return -ENOPKG; } if (strscpy(alg_name, pkey->pkey_algo, CRYPTO_MAX_ALG_NAME) < 0) return -EINVAL; return 0; } static u8 *pkey_pack_u32(u8 *dst, u32 val) { memcpy(dst, &val, sizeof(val)); return dst + sizeof(val); } /* * Query information about a key. */ static int software_key_query(const struct kernel_pkey_params *params, struct kernel_pkey_query *info) { struct public_key *pkey = params->key->payload.data[asym_crypto]; char alg_name[CRYPTO_MAX_ALG_NAME]; u8 *key, *ptr; int ret, len; bool issig; ret = software_key_determine_akcipher(pkey, params->encoding, params->hash_algo, alg_name, &issig, kernel_pkey_sign); if (ret < 0) return ret; key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, GFP_KERNEL); if (!key) return -ENOMEM; memcpy(key, pkey->key, pkey->keylen); ptr = key + pkey->keylen; ptr = pkey_pack_u32(ptr, pkey->algo); ptr = pkey_pack_u32(ptr, pkey->paramlen); memcpy(ptr, pkey->params, pkey->paramlen); memset(info, 0, sizeof(*info)); if (issig) { struct crypto_sig *sig; sig = crypto_alloc_sig(alg_name, 0, 0); if (IS_ERR(sig)) { ret = PTR_ERR(sig); goto error_free_key; } if (pkey->key_is_private) ret = crypto_sig_set_privkey(sig, key, pkey->keylen); else ret = crypto_sig_set_pubkey(sig, key, pkey->keylen); if (ret < 0) goto error_free_sig; len = crypto_sig_keysize(sig); info->key_size = len; info->max_sig_size = crypto_sig_maxsize(sig); info->max_data_size = crypto_sig_digestsize(sig); info->supported_ops = KEYCTL_SUPPORTS_VERIFY; if (pkey->key_is_private) info->supported_ops |= KEYCTL_SUPPORTS_SIGN; if (strcmp(params->encoding, "pkcs1") == 0) { info->max_enc_size = len / BITS_PER_BYTE; info->max_dec_size = len / BITS_PER_BYTE; info->supported_ops |= KEYCTL_SUPPORTS_ENCRYPT; if (pkey->key_is_private) info->supported_ops |= KEYCTL_SUPPORTS_DECRYPT; } error_free_sig: crypto_free_sig(sig); } else { struct crypto_akcipher *tfm; tfm = crypto_alloc_akcipher(alg_name, 0, 0); if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); goto error_free_key; } if (pkey->key_is_private) ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen); else ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen); if (ret < 0) goto error_free_akcipher; len = crypto_akcipher_maxsize(tfm); info->key_size = len * BITS_PER_BYTE; info->max_sig_size = len; info->max_data_size = len; info->max_enc_size = len; info->max_dec_size = len; info->supported_ops = KEYCTL_SUPPORTS_ENCRYPT; if (pkey->key_is_private) info->supported_ops |= KEYCTL_SUPPORTS_DECRYPT; error_free_akcipher: crypto_free_akcipher(tfm); } error_free_key: kfree_sensitive(key); pr_devel("<==%s() = %d\n", __func__, ret); return ret; } /* * Do encryption, decryption and signing ops. */ static int software_key_eds_op(struct kernel_pkey_params *params, const void *in, void *out) { const struct public_key *pkey = params->key->payload.data[asym_crypto]; char alg_name[CRYPTO_MAX_ALG_NAME]; struct crypto_akcipher *tfm; struct crypto_sig *sig; char *key, *ptr; bool issig; int ret; pr_devel("==>%s()\n", __func__); ret = software_key_determine_akcipher(pkey, params->encoding, params->hash_algo, alg_name, &issig, params->op); if (ret < 0) return ret; key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, GFP_KERNEL); if (!key) return -ENOMEM; memcpy(key, pkey->key, pkey->keylen); ptr = key + pkey->keylen; ptr = pkey_pack_u32(ptr, pkey->algo); ptr = pkey_pack_u32(ptr, pkey->paramlen); memcpy(ptr, pkey->params, pkey->paramlen); if (issig) { sig = crypto_alloc_sig(alg_name, 0, 0); if (IS_ERR(sig)) { ret = PTR_ERR(sig); goto error_free_key; } if (pkey->key_is_private) ret = crypto_sig_set_privkey(sig, key, pkey->keylen); else ret = crypto_sig_set_pubkey(sig, key, pkey->keylen); if (ret) goto error_free_tfm; } else { tfm = crypto_alloc_akcipher(alg_name, 0, 0); if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); goto error_free_key; } if (pkey->key_is_private) ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen); else ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen); if (ret) goto error_free_tfm; } ret = -EINVAL; /* Perform the encryption calculation. */ switch (params->op) { case kernel_pkey_encrypt: if (issig) break; ret = crypto_akcipher_sync_encrypt(tfm, in, params->in_len, out, params->out_len); break; case kernel_pkey_decrypt: if (issig) break; ret = crypto_akcipher_sync_decrypt(tfm, in, params->in_len, out, params->out_len); break; case kernel_pkey_sign: if (!issig) break; ret = crypto_sig_sign(sig, in, params->in_len, out, params->out_len); break; default: BUG(); } if (!issig && ret == 0) ret = crypto_akcipher_maxsize(tfm); error_free_tfm: if (issig) crypto_free_sig(sig); else crypto_free_akcipher(tfm); error_free_key: kfree_sensitive(key); pr_devel("<==%s() = %d\n", __func__, ret); return ret; } /* * Verify a signature using a public key. */ int public_key_verify_signature(const struct public_key *pkey, const struct public_key_signature *sig) { char alg_name[CRYPTO_MAX_ALG_NAME]; struct crypto_sig *tfm; char *key, *ptr; bool issig; int ret; pr_devel("==>%s()\n", __func__); BUG_ON(!pkey); BUG_ON(!sig); BUG_ON(!sig->s); /* * If the signature specifies a public key algorithm, it *must* match * the key's actual public key algorithm. * * Small exception: ECDSA signatures don't specify the curve, but ECDSA * keys do. So the strings can mismatch slightly in that case: * "ecdsa-nist-*" for the key, but "ecdsa" for the signature. */ if (sig->pkey_algo) { if (strcmp(pkey->pkey_algo, sig->pkey_algo) != 0 && (strncmp(pkey->pkey_algo, "ecdsa-", 6) != 0 || strcmp(sig->pkey_algo, "ecdsa") != 0)) return -EKEYREJECTED; } ret = software_key_determine_akcipher(pkey, sig->encoding, sig->hash_algo, alg_name, &issig, kernel_pkey_verify); if (ret < 0) return ret; tfm = crypto_alloc_sig(alg_name, 0, 0); if (IS_ERR(tfm)) return PTR_ERR(tfm); key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, GFP_KERNEL); if (!key) { ret = -ENOMEM; goto error_free_tfm; } memcpy(key, pkey->key, pkey->keylen); ptr = key + pkey->keylen; ptr = pkey_pack_u32(ptr, pkey->algo); ptr = pkey_pack_u32(ptr, pkey->paramlen); memcpy(ptr, pkey->params, pkey->paramlen); if (pkey->key_is_private) ret = crypto_sig_set_privkey(tfm, key, pkey->keylen); else ret = crypto_sig_set_pubkey(tfm, key, pkey->keylen); if (ret) goto error_free_key; ret = crypto_sig_verify(tfm, sig->s, sig->s_size, sig->digest, sig->digest_size); error_free_key: kfree_sensitive(key); error_free_tfm: crypto_free_sig(tfm); pr_devel("<==%s() = %d\n", __func__, ret); if (WARN_ON_ONCE(ret > 0)) ret = -EINVAL; return ret; } EXPORT_SYMBOL_GPL(public_key_verify_signature); static int public_key_verify_signature_2(const struct key *key, const struct public_key_signature *sig) { const struct public_key *pk = key->payload.data[asym_crypto]; return public_key_verify_signature(pk, sig); } /* * Public key algorithm asymmetric key subtype */ struct asymmetric_key_subtype public_key_subtype = { .owner = THIS_MODULE, .name = "public_key", .name_len = sizeof("public_key") - 1, .describe = public_key_describe, .destroy = public_key_destroy, .query = software_key_query, .eds_op = software_key_eds_op, .verify_signature = public_key_verify_signature_2, }; EXPORT_SYMBOL_GPL(public_key_subtype); |
| 5 1 5 1 1 1 1 1 1 1 5 5 1 4 5 4 4 5 5 5 5 3 4 4 4 9 4 4 4 4 8 6 4 4 3 2 14 13 4 8 2 9 7 6 1 3 2 2 3 3 3 3 3 3 2 1 3 3 3 3 3 3 3 2 3 1 1 1 3 3 1 1 1 1 1 1 1 1 1 1 3 2 2 2 3 3 3 3 4 4 4 4 4 4 3 4 3 4 3 3 3 3 3 3 3 1 1 1 14 14 14 14 14 9 9 7 9 7 7 5 4 4 4 3 8 3 2 9 16 16 15 13 14 16 13 13 13 1 1 1 13 2 3 2 3 36 36 36 35 3 33 32 2 2 1 2 2 1 2 1 2 1 1 2 15 6 9 5 5 24 19 24 15 8 9 24 14 14 24 21 23 24 2 24 14 10 24 24 2 24 3 24 1 24 24 24 24 24 15 24 23 24 26 26 36 35 36 3 2 34 32 32 2 31 30 29 28 27 2 26 26 4 26 26 26 26 26 26 25 25 22 5 24 23 23 1 3 35 19 19 19 19 16 19 29 24 5 29 29 7 22 5 57 52 57 55 55 55 46 7 53 51 7 51 49 49 1 47 48 46 46 4 45 3 45 45 43 18 15 41 37 39 3 36 32 29 31 19 19 29 23 6 2 4 4 6 6 29 11 6 6 2 5 23 17 6 3 27 24 3 33 57 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fanotify.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/anon_inodes.h> #include <linux/fsnotify_backend.h> #include <linux/init.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/poll.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/memcontrol.h> #include <linux/statfs.h> #include <linux/exportfs.h> #include <asm/ioctls.h> #include "../fsnotify.h" #include "../fdinfo.h" #include "fanotify.h" #define FANOTIFY_DEFAULT_MAX_EVENTS 16384 #define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192 #define FANOTIFY_DEFAULT_MAX_GROUPS 128 #define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32 /* * Legacy fanotify marks limits (8192) is per group and we introduced a tunable * limit of marks per user, similar to inotify. Effectively, the legacy limit * of fanotify marks per user is <max marks per group> * <max groups per user>. * This default limit (1M) also happens to match the increased limit of inotify * max_user_watches since v5.10. */ #define FANOTIFY_DEFAULT_MAX_USER_MARKS \ (FANOTIFY_OLD_DEFAULT_MAX_MARKS * FANOTIFY_DEFAULT_MAX_GROUPS) /* * Most of the memory cost of adding an inode mark is pinning the marked inode. * The size of the filesystem inode struct is not uniform across filesystems, * so double the size of a VFS inode is used as a conservative approximation. */ #define INODE_MARK_COST (2 * sizeof(struct inode)) /* configurable via /proc/sys/fs/fanotify/ */ static int fanotify_max_queued_events __read_mostly; static int perm_group_timeout __read_mostly; #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long ft_zero = 0; static long ft_int_max = INT_MAX; static const struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &ft_zero, .extra2 = &ft_int_max, }, { .procname = "max_user_marks", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS], .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &ft_zero, .extra2 = &ft_int_max, }, { .procname = "max_queued_events", .data = &fanotify_max_queued_events, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO }, { .procname = "watchdog_timeout", .data = &perm_group_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, }; static void __init fanotify_sysctls_init(void) { register_sysctl("fs/fanotify", fanotify_table); } #else #define fanotify_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static LIST_HEAD(perm_group_list); static DEFINE_SPINLOCK(perm_group_lock); static void perm_group_watchdog(struct work_struct *work); static DECLARE_DELAYED_WORK(perm_group_work, perm_group_watchdog); static void perm_group_watchdog_schedule(void) { schedule_delayed_work(&perm_group_work, secs_to_jiffies(perm_group_timeout)); } static void perm_group_watchdog(struct work_struct *work) { struct fsnotify_group *group; struct fanotify_perm_event *event; struct task_struct *task; pid_t failed_pid = 0; guard(spinlock)(&perm_group_lock); if (list_empty(&perm_group_list)) return; list_for_each_entry(group, &perm_group_list, fanotify_data.perm_grp_list) { /* * Ok to test without lock, racing with an addition is * fine, will deal with it next round */ if (list_empty(&group->fanotify_data.access_list)) continue; spin_lock(&group->notification_lock); list_for_each_entry(event, &group->fanotify_data.access_list, fae.fse.list) { if (likely(event->watchdog_cnt == 0)) { event->watchdog_cnt = 1; } else if (event->watchdog_cnt == 1) { /* Report on event only once */ event->watchdog_cnt = 2; /* Do not report same pid repeatedly */ if (event->recv_pid == failed_pid) continue; failed_pid = event->recv_pid; rcu_read_lock(); task = find_task_by_pid_ns(event->recv_pid, &init_pid_ns); pr_warn_ratelimited( "PID %u (%s) failed to respond to fanotify queue for more than %d seconds\n", event->recv_pid, task ? task->comm : NULL, perm_group_timeout); rcu_read_unlock(); } } spin_unlock(&group->notification_lock); } perm_group_watchdog_schedule(); } static void fanotify_perm_watchdog_group_remove(struct fsnotify_group *group) { if (!list_empty(&group->fanotify_data.perm_grp_list)) { /* Perm event watchdog can no longer scan this group. */ spin_lock(&perm_group_lock); list_del_init(&group->fanotify_data.perm_grp_list); spin_unlock(&perm_group_lock); } } static void fanotify_perm_watchdog_group_add(struct fsnotify_group *group) { if (!perm_group_timeout) return; spin_lock(&perm_group_lock); if (list_empty(&group->fanotify_data.perm_grp_list)) { /* Add to perm_group_list for monitoring by watchdog. */ if (list_empty(&perm_group_list)) perm_group_watchdog_schedule(); list_add_tail(&group->fanotify_data.perm_grp_list, &perm_group_list); } spin_unlock(&perm_group_lock); } /* * All flags that may be specified in parameter event_f_flags of fanotify_init. * * Internal and external open flags are stored together in field f_flags of * struct file. Only external open flags shall be allowed in event_f_flags. * Internal flags like FMODE_EXEC shall be excluded. */ #define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \ O_ACCMODE | O_APPEND | O_NONBLOCK | \ __O_SYNC | O_DSYNC | O_CLOEXEC | \ O_LARGEFILE | O_NOATIME ) extern const struct fsnotify_ops fanotify_fsnotify_ops; struct kmem_cache *fanotify_mark_cache __ro_after_init; struct kmem_cache *fanotify_fid_event_cachep __ro_after_init; struct kmem_cache *fanotify_path_event_cachep __ro_after_init; struct kmem_cache *fanotify_perm_event_cachep __ro_after_init; struct kmem_cache *fanotify_mnt_event_cachep __ro_after_init; #define FANOTIFY_EVENT_ALIGN 4 #define FANOTIFY_FID_INFO_HDR_LEN \ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) #define FANOTIFY_PIDFD_INFO_LEN \ sizeof(struct fanotify_event_info_pidfd) #define FANOTIFY_ERROR_INFO_LEN \ (sizeof(struct fanotify_event_info_error)) #define FANOTIFY_RANGE_INFO_LEN \ (sizeof(struct fanotify_event_info_range)) #define FANOTIFY_MNT_INFO_LEN \ (sizeof(struct fanotify_event_info_mnt)) static int fanotify_fid_info_len(int fh_len, int name_len) { int info_len = fh_len; if (name_len) info_len += name_len + 1; return roundup(FANOTIFY_FID_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN); } /* FAN_RENAME may have one or two dir+name info records */ static int fanotify_dir_name_info_len(struct fanotify_event *event) { struct fanotify_info *info = fanotify_event_info(event); int dir_fh_len = fanotify_event_dir_fh_len(event); int dir2_fh_len = fanotify_event_dir2_fh_len(event); int info_len = 0; if (dir_fh_len) info_len += fanotify_fid_info_len(dir_fh_len, info->name_len); if (dir2_fh_len) info_len += fanotify_fid_info_len(dir2_fh_len, info->name2_len); return info_len; } static size_t fanotify_event_len(unsigned int info_mode, struct fanotify_event *event) { size_t event_len = FAN_EVENT_METADATA_LEN; int fh_len; int dot_len = 0; if (fanotify_is_error_event(event->mask)) event_len += FANOTIFY_ERROR_INFO_LEN; if (fanotify_event_has_any_dir_fh(event)) { event_len += fanotify_dir_name_info_len(event); } else if ((info_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { /* * With group flag FAN_REPORT_NAME, if name was not recorded in * event on a directory, we will report the name ".". */ dot_len = 1; } if (fanotify_event_has_object_fh(event)) { fh_len = fanotify_event_object_fh_len(event); event_len += fanotify_fid_info_len(fh_len, dot_len); } if (fanotify_is_mnt_event(event->mask)) event_len += FANOTIFY_MNT_INFO_LEN; if (info_mode & FAN_REPORT_PIDFD) event_len += FANOTIFY_PIDFD_INFO_LEN; if (fanotify_event_has_access_range(event)) event_len += FANOTIFY_RANGE_INFO_LEN; return event_len; } /* * Remove an hashed event from merge hash table. */ static void fanotify_unhash_event(struct fsnotify_group *group, struct fanotify_event *event) { assert_spin_locked(&group->notification_lock); pr_debug("%s: group=%p event=%p bucket=%u\n", __func__, group, event, fanotify_event_hash_bucket(group, event)); if (WARN_ON_ONCE(hlist_unhashed(&event->merge_list))) return; hlist_del_init(&event->merge_list); } /* * Get an fanotify notification event if one exists and is small * enough to fit in "count". Return an error pointer if the count * is not large enough. When permission event is dequeued, its state is * updated accordingly. */ static struct fanotify_event *get_one_event(struct fsnotify_group *group, size_t count) { size_t event_size; struct fanotify_event *event = NULL; struct fsnotify_event *fsn_event; unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); pr_debug("%s: group=%p count=%zd\n", __func__, group, count); spin_lock(&group->notification_lock); fsn_event = fsnotify_peek_first_event(group); if (!fsn_event) goto out; event = FANOTIFY_E(fsn_event); event_size = fanotify_event_len(info_mode, event); if (event_size > count) { event = ERR_PTR(-EINVAL); goto out; } /* * Held the notification_lock the whole time, so this is the * same event we peeked above. */ fsnotify_remove_first_event(group); if (fanotify_is_perm_event(event->mask)) FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED; if (fanotify_is_hashed_event(event->mask)) fanotify_unhash_event(group, event); out: spin_unlock(&group->notification_lock); return event; } static int create_fd(struct fsnotify_group *group, const struct path *path, struct file **file) { int client_fd; struct file *new_file; client_fd = get_unused_fd_flags(group->fanotify_data.f_flags); if (client_fd < 0) return client_fd; /* * We provide an fd for the userspace program, so it could access the * file without generating fanotify events itself. */ new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags, current_cred()); if (IS_ERR(new_file)) { put_unused_fd(client_fd); client_fd = PTR_ERR(new_file); } else { *file = new_file; } return client_fd; } static int process_access_response_info(const char __user *info, size_t info_len, struct fanotify_response_info_audit_rule *friar) { if (info_len != sizeof(*friar)) return -EINVAL; if (copy_from_user(friar, info, sizeof(*friar))) return -EFAULT; if (friar->hdr.type != FAN_RESPONSE_INFO_AUDIT_RULE) return -EINVAL; if (friar->hdr.pad != 0) return -EINVAL; if (friar->hdr.len != sizeof(*friar)) return -EINVAL; return info_len; } /* * Finish processing of permission event by setting it to ANSWERED state and * drop group->notification_lock. */ static void finish_permission_event(struct fsnotify_group *group, struct fanotify_perm_event *event, u32 response, struct fanotify_response_info_audit_rule *friar) __releases(&group->notification_lock) { bool destroy = false; assert_spin_locked(&group->notification_lock); event->response = response & ~FAN_INFO; if (response & FAN_INFO) memcpy(&event->audit_rule, friar, sizeof(*friar)); if (event->state == FAN_EVENT_CANCELED) destroy = true; else event->state = FAN_EVENT_ANSWERED; spin_unlock(&group->notification_lock); if (destroy) fsnotify_destroy_event(group, &event->fae.fse); } static int process_access_response(struct fsnotify_group *group, struct fanotify_response *response_struct, const char __user *info, size_t info_len) { struct fanotify_perm_event *event; int fd = response_struct->fd; u32 response = response_struct->response; int errno = fanotify_get_response_errno(response); int ret = info_len; struct fanotify_response_info_audit_rule friar; pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n", __func__, group, fd, response, errno, info, info_len); /* * make sure the response is valid, if invalid we do nothing and either * userspace can send a valid response or we will clean it up after the * timeout */ if (response & ~FANOTIFY_RESPONSE_VALID_MASK) return -EINVAL; switch (response & FANOTIFY_RESPONSE_ACCESS) { case FAN_ALLOW: if (errno) return -EINVAL; break; case FAN_DENY: /* Custom errno is supported only for pre-content groups */ if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT) return -EINVAL; /* * Limit errno to values expected on open(2)/read(2)/write(2) * of regular files. */ switch (errno) { case 0: case EIO: case EPERM: case EBUSY: case ETXTBSY: case EAGAIN: case ENOSPC: case EDQUOT: break; default: return -EINVAL; } break; default: return -EINVAL; } if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) return -EINVAL; if (response & FAN_INFO) { ret = process_access_response_info(info, info_len, &friar); if (ret < 0) return ret; if (fd == FAN_NOFD) return ret; } else { ret = 0; } if (fd < 0) return -EINVAL; spin_lock(&group->notification_lock); list_for_each_entry(event, &group->fanotify_data.access_list, fae.fse.list) { if (event->fd != fd) continue; list_del_init(&event->fae.fse.list); finish_permission_event(group, event, response, &friar); wake_up(&group->fanotify_data.access_waitq); return ret; } spin_unlock(&group->notification_lock); return -ENOENT; } static size_t copy_mnt_info_to_user(struct fanotify_event *event, char __user *buf, int count) { struct fanotify_event_info_mnt info = { }; info.hdr.info_type = FAN_EVENT_INFO_TYPE_MNT; info.hdr.len = FANOTIFY_MNT_INFO_LEN; if (WARN_ON(count < info.hdr.len)) return -EFAULT; info.mnt_id = FANOTIFY_ME(event)->mnt_id; if (copy_to_user(buf, &info, sizeof(info))) return -EFAULT; return info.hdr.len; } static size_t copy_error_info_to_user(struct fanotify_event *event, char __user *buf, int count) { struct fanotify_event_info_error info = { }; struct fanotify_error_event *fee = FANOTIFY_EE(event); info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR; info.hdr.len = FANOTIFY_ERROR_INFO_LEN; if (WARN_ON(count < info.hdr.len)) return -EFAULT; info.error = fee->error; info.error_count = fee->err_count; if (copy_to_user(buf, &info, sizeof(info))) return -EFAULT; return info.hdr.len; } static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, int info_type, const char *name, size_t name_len, char __user *buf, size_t count) { struct fanotify_event_info_fid info = { }; struct file_handle handle = { }; unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf; size_t fh_len = fh ? fh->len : 0; size_t info_len = fanotify_fid_info_len(fh_len, name_len); size_t len = info_len; pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n", __func__, fh_len, name_len, info_len, count); if (WARN_ON_ONCE(len < sizeof(info) || len > count)) return -EFAULT; /* * Copy event info fid header followed by variable sized file handle * and optionally followed by variable sized filename. */ switch (info_type) { case FAN_EVENT_INFO_TYPE_FID: case FAN_EVENT_INFO_TYPE_DFID: if (WARN_ON_ONCE(name_len)) return -EFAULT; break; case FAN_EVENT_INFO_TYPE_DFID_NAME: case FAN_EVENT_INFO_TYPE_OLD_DFID_NAME: case FAN_EVENT_INFO_TYPE_NEW_DFID_NAME: if (WARN_ON_ONCE(!name || !name_len)) return -EFAULT; break; default: return -EFAULT; } info.hdr.info_type = info_type; info.hdr.len = len; info.fsid = *fsid; if (copy_to_user(buf, &info, sizeof(info))) return -EFAULT; buf += sizeof(info); len -= sizeof(info); if (WARN_ON_ONCE(len < sizeof(handle))) return -EFAULT; handle.handle_type = fh->type; handle.handle_bytes = fh_len; /* Mangle handle_type for bad file_handle */ if (!fh_len) handle.handle_type = FILEID_INVALID; if (copy_to_user(buf, &handle, sizeof(handle))) return -EFAULT; buf += sizeof(handle); len -= sizeof(handle); if (WARN_ON_ONCE(len < fh_len)) return -EFAULT; /* * For an inline fh and inline file name, copy through stack to exclude * the copy from usercopy hardening protections. */ fh_buf = fanotify_fh_buf(fh); if (fh_len <= FANOTIFY_INLINE_FH_LEN) { memcpy(bounce, fh_buf, fh_len); fh_buf = bounce; } if (copy_to_user(buf, fh_buf, fh_len)) return -EFAULT; buf += fh_len; len -= fh_len; if (name_len) { /* Copy the filename with terminating null */ name_len++; if (WARN_ON_ONCE(len < name_len)) return -EFAULT; if (copy_to_user(buf, name, name_len)) return -EFAULT; buf += name_len; len -= name_len; } /* Pad with 0's */ WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN); if (len > 0 && clear_user(buf, len)) return -EFAULT; return info_len; } static int copy_pidfd_info_to_user(int pidfd, char __user *buf, size_t count) { struct fanotify_event_info_pidfd info = { }; size_t info_len = FANOTIFY_PIDFD_INFO_LEN; if (WARN_ON_ONCE(info_len > count)) return -EFAULT; info.hdr.info_type = FAN_EVENT_INFO_TYPE_PIDFD; info.hdr.len = info_len; info.pidfd = pidfd; if (copy_to_user(buf, &info, info_len)) return -EFAULT; return info_len; } static size_t copy_range_info_to_user(struct fanotify_event *event, char __user *buf, int count) { struct fanotify_perm_event *pevent = FANOTIFY_PERM(event); struct fanotify_event_info_range info = { }; size_t info_len = FANOTIFY_RANGE_INFO_LEN; if (WARN_ON_ONCE(info_len > count)) return -EFAULT; if (WARN_ON_ONCE(!pevent->ppos)) return -EINVAL; info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE; info.hdr.len = info_len; info.offset = *(pevent->ppos); info.count = pevent->count; if (copy_to_user(buf, &info, info_len)) return -EFAULT; return info_len; } static int copy_info_records_to_user(struct fanotify_event *event, struct fanotify_info *info, unsigned int info_mode, int pidfd, char __user *buf, size_t count) { int ret, total_bytes = 0, info_type = 0; unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS; unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; /* * Event info records order is as follows: * 1. dir fid + name * 2. (optional) new dir fid + new name * 3. (optional) child fid */ if (fanotify_event_has_dir_fh(event)) { info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : FAN_EVENT_INFO_TYPE_DFID; /* FAN_RENAME uses special info types */ if (event->mask & FAN_RENAME) info_type = FAN_EVENT_INFO_TYPE_OLD_DFID_NAME; ret = copy_fid_info_to_user(fanotify_event_fsid(event), fanotify_info_dir_fh(info), info_type, fanotify_info_name(info), info->name_len, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } /* New dir fid+name may be reported in addition to old dir fid+name */ if (fanotify_event_has_dir2_fh(event)) { info_type = FAN_EVENT_INFO_TYPE_NEW_DFID_NAME; ret = copy_fid_info_to_user(fanotify_event_fsid(event), fanotify_info_dir2_fh(info), info_type, fanotify_info_name2(info), info->name2_len, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } if (fanotify_event_has_object_fh(event)) { const char *dot = NULL; int dot_len = 0; if (fid_mode == FAN_REPORT_FID || info_type) { /* * With only group flag FAN_REPORT_FID only type FID is * reported. Second info record type is always FID. */ info_type = FAN_EVENT_INFO_TYPE_FID; } else if ((fid_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { /* * With group flag FAN_REPORT_NAME, if name was not * recorded in an event on a directory, report the name * "." with info type DFID_NAME. */ info_type = FAN_EVENT_INFO_TYPE_DFID_NAME; dot = "."; dot_len = 1; } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) || (event->mask & FAN_ONDIR)) { /* * With group flag FAN_REPORT_DIR_FID, a single info * record has type DFID for directory entry modification * event and for event on a directory. */ info_type = FAN_EVENT_INFO_TYPE_DFID; } else { /* * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID, * a single info record has type FID for event on a * non-directory, when there is no directory to report. * For example, on FAN_DELETE_SELF event. */ info_type = FAN_EVENT_INFO_TYPE_FID; } ret = copy_fid_info_to_user(fanotify_event_fsid(event), fanotify_event_object_fh(event), info_type, dot, dot_len, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } if (pidfd_mode) { ret = copy_pidfd_info_to_user(pidfd, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } if (fanotify_is_error_event(event->mask)) { ret = copy_error_info_to_user(event, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } if (fanotify_event_has_access_range(event)) { ret = copy_range_info_to_user(event, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } if (fanotify_is_mnt_event(event->mask)) { ret = copy_mnt_info_to_user(event, buf, count); if (ret < 0) return ret; buf += ret; count -= ret; total_bytes += ret; } return total_bytes; } static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fanotify_event *event, char __user *buf, size_t count) { struct fanotify_event_metadata metadata; const struct path *path = fanotify_event_path(event); struct fanotify_info *info = fanotify_event_info(event); unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; struct file *f = NULL, *pidfd_file = NULL; int ret, pidfd = -ESRCH, fd = -EBADF; pr_debug("%s: group=%p event=%p\n", __func__, group, event); metadata.event_len = fanotify_event_len(info_mode, event); metadata.metadata_len = FAN_EVENT_METADATA_LEN; metadata.vers = FANOTIFY_METADATA_VERSION; metadata.reserved = 0; metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS; metadata.pid = pid_vnr(event->pid); /* * For an unprivileged listener, event->pid can be used to identify the * events generated by the listener process itself, without disclosing * the pids of other processes. */ if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) && task_tgid(current) != event->pid) metadata.pid = 0; /* * For now, fid mode is required for an unprivileged listener and * fid mode does not report fd in events. Keep this check anyway * for safety in case fid mode requirement is relaxed in the future * to allow unprivileged listener to get events with no fd and no fid. */ if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) && path && path->mnt && path->dentry) { fd = create_fd(group, path, &f); /* * Opening an fd from dentry can fail for several reasons. * For example, when tasks are gone and we try to open their * /proc files or we try to open a WRONLY file like in sysfs * or when trying to open a file that was deleted on the * remote network server. * * For a group with FAN_REPORT_FD_ERROR, we will send the * event with the error instead of the open fd, otherwise * Userspace may not get the error at all. * In any case, userspace will not know which file failed to * open, so add a debug print for further investigation. */ if (fd < 0) { pr_debug("fanotify: create_fd(%pd2) failed err=%d\n", path->dentry, fd); if (!FAN_GROUP_FLAG(group, FAN_REPORT_FD_ERROR)) { /* * Historically, we've handled EOPENSTALE in a * special way and silently dropped such * events. Now we have to keep it to maintain * backward compatibility... */ if (fd == -EOPENSTALE) fd = 0; return fd; } } } if (FAN_GROUP_FLAG(group, FAN_REPORT_FD_ERROR)) metadata.fd = fd; else metadata.fd = fd >= 0 ? fd : FAN_NOFD; if (pidfd_mode) { /* * Complain if the FAN_REPORT_PIDFD and FAN_REPORT_TID mutual * exclusion is ever lifted. At the time of incoporating pidfd * support within fanotify, the pidfd API only supported the * creation of pidfds for thread-group leaders. */ WARN_ON_ONCE(FAN_GROUP_FLAG(group, FAN_REPORT_TID)); /* * The PIDTYPE_TGID check for an event->pid is performed * preemptively in an attempt to catch out cases where the event * listener reads events after the event generating process has * already terminated. Depending on flag FAN_REPORT_FD_ERROR, * report either -ESRCH or FAN_NOPIDFD to the event listener in * those cases with all other pidfd creation errors reported as * the error code itself or as FAN_EPIDFD. */ if (metadata.pid && pid_has_task(event->pid, PIDTYPE_TGID)) pidfd = pidfd_prepare(event->pid, 0, &pidfd_file); if (!FAN_GROUP_FLAG(group, FAN_REPORT_FD_ERROR) && pidfd < 0) pidfd = pidfd == -ESRCH ? FAN_NOPIDFD : FAN_EPIDFD; } ret = -EFAULT; /* * Sanity check copy size in case get_one_event() and * event_len sizes ever get out of sync. */ if (WARN_ON_ONCE(metadata.event_len > count)) goto out_close_fd; if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN)) goto out_close_fd; buf += FAN_EVENT_METADATA_LEN; count -= FAN_EVENT_METADATA_LEN; ret = copy_info_records_to_user(event, info, info_mode, pidfd, buf, count); if (ret < 0) goto out_close_fd; if (f) fd_install(fd, f); if (pidfd_file) fd_install(pidfd, pidfd_file); if (fanotify_is_perm_event(event->mask)) FANOTIFY_PERM(event)->fd = fd; return metadata.event_len; out_close_fd: if (f) { put_unused_fd(fd); fput(f); } if (pidfd_file) { put_unused_fd(pidfd); fput(pidfd_file); } return ret; } /* intofiy userspace file descriptor functions */ static __poll_t fanotify_poll(struct file *file, poll_table *wait) { struct fsnotify_group *group = file->private_data; __poll_t ret = 0; poll_wait(file, &group->notification_waitq, wait); spin_lock(&group->notification_lock); if (!fsnotify_notify_queue_is_empty(group)) ret = EPOLLIN | EPOLLRDNORM; spin_unlock(&group->notification_lock); return ret; } static ssize_t fanotify_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct fsnotify_group *group; struct fanotify_event *event; char __user *start; int ret; DEFINE_WAIT_FUNC(wait, woken_wake_function); start = buf; group = file->private_data; pr_debug("%s: group=%p\n", __func__, group); add_wait_queue(&group->notification_waitq, &wait); while (1) { /* * User can supply arbitrarily large buffer. Avoid softlockups * in case there are lots of available events. */ cond_resched(); event = get_one_event(group, count); if (IS_ERR(event)) { ret = PTR_ERR(event); break; } if (!event) { ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; if (start != buf) break; wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); continue; } ret = copy_event_to_user(group, event, buf, count); /* * Permission events get queued to wait for response. Other * events can be destroyed now. */ if (!fanotify_is_perm_event(event->mask)) { fsnotify_destroy_event(group, &event->fse); } else { if (ret <= 0 || FANOTIFY_PERM(event)->fd < 0) { spin_lock(&group->notification_lock); finish_permission_event(group, FANOTIFY_PERM(event), FAN_DENY, NULL); wake_up(&group->fanotify_data.access_waitq); } else { spin_lock(&group->notification_lock); list_add_tail(&event->fse.list, &group->fanotify_data.access_list); FANOTIFY_PERM(event)->recv_pid = current->pid; spin_unlock(&group->notification_lock); } } if (ret < 0) break; buf += ret; count -= ret; } remove_wait_queue(&group->notification_waitq, &wait); if (start != buf && ret != -EFAULT) ret = buf - start; return ret; } static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { struct fanotify_response response; struct fsnotify_group *group; int ret; const char __user *info_buf = buf + sizeof(struct fanotify_response); size_t info_len; if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) return -EINVAL; group = file->private_data; pr_debug("%s: group=%p count=%zu\n", __func__, group, count); if (count < sizeof(response)) return -EINVAL; if (copy_from_user(&response, buf, sizeof(response))) return -EFAULT; info_len = count - sizeof(response); ret = process_access_response(group, &response, info_buf, info_len); if (ret < 0) count = ret; else count = sizeof(response) + ret; return count; } static int fanotify_release(struct inode *ignored, struct file *file) { struct fsnotify_group *group = file->private_data; struct fsnotify_event *fsn_event; /* * Stop new events from arriving in the notification queue. since * userspace cannot use fanotify fd anymore, no event can enter or * leave access_list by now either. */ fsnotify_group_stop_queueing(group); fanotify_perm_watchdog_group_remove(group); /* * Process all permission events on access_list and notification queue * and simulate reply from userspace. */ spin_lock(&group->notification_lock); while (!list_empty(&group->fanotify_data.access_list)) { struct fanotify_perm_event *event; event = list_first_entry(&group->fanotify_data.access_list, struct fanotify_perm_event, fae.fse.list); list_del_init(&event->fae.fse.list); finish_permission_event(group, event, FAN_ALLOW, NULL); spin_lock(&group->notification_lock); } /* * Destroy all non-permission events. For permission events just * dequeue them and set the response. They will be freed once the * response is consumed and fanotify_get_response() returns. */ while ((fsn_event = fsnotify_remove_first_event(group))) { struct fanotify_event *event = FANOTIFY_E(fsn_event); if (!(event->mask & FANOTIFY_PERM_EVENTS)) { spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, fsn_event); } else { finish_permission_event(group, FANOTIFY_PERM(event), FAN_ALLOW, NULL); } spin_lock(&group->notification_lock); } spin_unlock(&group->notification_lock); /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); /* matches the fanotify_init->fsnotify_alloc_group */ fsnotify_destroy_group(group); return 0; } static long fanotify_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct fsnotify_group *group; struct fsnotify_event *fsn_event; void __user *p; int ret = -ENOTTY; size_t send_len = 0; group = file->private_data; p = (void __user *) arg; switch (cmd) { case FIONREAD: spin_lock(&group->notification_lock); list_for_each_entry(fsn_event, &group->notification_list, list) send_len += FAN_EVENT_METADATA_LEN; spin_unlock(&group->notification_lock); ret = put_user(send_len, (int __user *) p); break; } return ret; } static const struct file_operations fanotify_fops = { .show_fdinfo = fanotify_show_fdinfo, .poll = fanotify_poll, .read = fanotify_read, .write = fanotify_write, .fasync = NULL, .release = fanotify_release, .unlocked_ioctl = fanotify_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static int fanotify_find_path(int dfd, const char __user *filename, struct path *path, unsigned int flags, __u64 mask, unsigned int obj_type) { int ret; pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__, dfd, filename, flags); if (filename == NULL) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; if ((flags & FAN_MARK_ONLYDIR) && !(S_ISDIR(file_inode(fd_file(f))->i_mode))) return -ENOTDIR; *path = fd_file(f)->f_path; path_get(path); } else { unsigned int lookup_flags = 0; if (!(flags & FAN_MARK_DONT_FOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (flags & FAN_MARK_ONLYDIR) lookup_flags |= LOOKUP_DIRECTORY; ret = user_path_at(dfd, filename, lookup_flags, path); if (ret) goto out; } /* you can only watch an inode if you have read permissions on it */ ret = path_permission(path, MAY_READ); if (ret) { path_put(path); goto out; } ret = security_path_notify(path, mask, obj_type); if (ret) path_put(path); out: return ret; } static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, __u32 mask, unsigned int flags, __u32 umask, int *destroy) { __u32 oldmask, newmask; /* umask bits cannot be removed by user */ mask &= ~umask; spin_lock(&fsn_mark->lock); oldmask = fsnotify_calc_mask(fsn_mark); if (!(flags & FANOTIFY_MARK_IGNORE_BITS)) { fsn_mark->mask &= ~mask; } else { fsn_mark->ignore_mask &= ~mask; } newmask = fsnotify_calc_mask(fsn_mark); /* * We need to keep the mark around even if remaining mask cannot * result in any events (e.g. mask == FAN_ONDIR) to support incremenal * changes to the mask. * Destroy mark when only umask bits remain. */ *destroy = !((fsn_mark->mask | fsn_mark->ignore_mask) & ~umask); spin_unlock(&fsn_mark->lock); return oldmask & ~newmask; } static int fanotify_remove_mark(struct fsnotify_group *group, void *obj, unsigned int obj_type, __u32 mask, unsigned int flags, __u32 umask) { struct fsnotify_mark *fsn_mark = NULL; __u32 removed; int destroy_mark; fsnotify_group_lock(group); fsn_mark = fsnotify_find_mark(obj, obj_type, group); if (!fsn_mark) { fsnotify_group_unlock(group); return -ENOENT; } removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags, umask, &destroy_mark); if (removed & fsnotify_conn_mask(fsn_mark->connector)) fsnotify_recalc_mask(fsn_mark->connector); if (destroy_mark) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(group); if (destroy_mark) fsnotify_free_mark(fsn_mark); /* matches the fsnotify_find_mark() */ fsnotify_put_mark(fsn_mark); return 0; } static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark, unsigned int fan_flags) { bool want_iref = !(fan_flags & FAN_MARK_EVICTABLE); unsigned int ignore = fan_flags & FANOTIFY_MARK_IGNORE_BITS; bool recalc = false; /* * When using FAN_MARK_IGNORE for the first time, mark starts using * independent event flags in ignore mask. After that, trying to * update the ignore mask with the old FAN_MARK_IGNORED_MASK API * will result in EEXIST error. */ if (ignore == FAN_MARK_IGNORE) fsn_mark->flags |= FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS; /* * Setting FAN_MARK_IGNORED_SURV_MODIFY for the first time may lead to * the removal of the FS_MODIFY bit in calculated mask if it was set * because of an ignore mask that is now going to survive FS_MODIFY. */ if (ignore && (fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) && !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) { fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; if (!(fsn_mark->mask & FS_MODIFY)) recalc = true; } if (fsn_mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) return recalc; /* * NO_IREF may be removed from a mark, but not added. * When removed, fsnotify_recalc_mask() will take the inode ref. */ WARN_ON_ONCE(!want_iref); fsn_mark->flags &= ~FSNOTIFY_MARK_FLAG_NO_IREF; return true; } static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, __u32 mask, unsigned int fan_flags) { bool recalc; spin_lock(&fsn_mark->lock); if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS)) fsn_mark->mask |= mask; else fsn_mark->ignore_mask |= mask; recalc = fsnotify_calc_mask(fsn_mark) & ~fsnotify_conn_mask(fsn_mark->connector); recalc |= fanotify_mark_update_flags(fsn_mark, fan_flags); spin_unlock(&fsn_mark->lock); return recalc; } struct fan_fsid { struct super_block *sb; __kernel_fsid_t id; bool weak; }; static int fanotify_set_mark_fsid(struct fsnotify_group *group, struct fsnotify_mark *mark, struct fan_fsid *fsid) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *old; struct super_block *old_sb = NULL; FANOTIFY_MARK(mark)->fsid = fsid->id; mark->flags |= FSNOTIFY_MARK_FLAG_HAS_FSID; if (fsid->weak) mark->flags |= FSNOTIFY_MARK_FLAG_WEAK_FSID; /* First mark added will determine if group is single or multi fsid */ if (list_empty(&group->marks_list)) return 0; /* Find sb of an existing mark */ list_for_each_entry(old, &group->marks_list, g_list) { conn = READ_ONCE(old->connector); if (!conn) continue; old_sb = fsnotify_connector_sb(conn); if (old_sb) break; } /* Only detached marks left? */ if (!old_sb) return 0; /* Do not allow mixing of marks with weak and strong fsid */ if ((mark->flags ^ old->flags) & FSNOTIFY_MARK_FLAG_WEAK_FSID) return -EXDEV; /* Allow mixing of marks with strong fsid from different fs */ if (!fsid->weak) return 0; /* Do not allow mixing marks with weak fsid from different fs */ if (old_sb != fsid->sb) return -EXDEV; /* Do not allow mixing marks from different btrfs sub-volumes */ if (!fanotify_fsid_equal(&FANOTIFY_MARK(old)->fsid, &FANOTIFY_MARK(mark)->fsid)) return -EXDEV; return 0; } static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, void *obj, unsigned int obj_type, unsigned int fan_flags, struct fan_fsid *fsid) { struct ucounts *ucounts = group->fanotify_data.ucounts; struct fanotify_mark *fan_mark; struct fsnotify_mark *mark; int ret; /* * Enforce per user marks limits per user in all containing user ns. * A group with FAN_UNLIMITED_MARKS does not contribute to mark count * in the limited groups account. */ BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_MARKS)); if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) && !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS)) return ERR_PTR(-ENOSPC); fan_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL); if (!fan_mark) { ret = -ENOMEM; goto out_dec_ucounts; } mark = &fan_mark->fsn_mark; fsnotify_init_mark(mark, group); if (fan_flags & FAN_MARK_EVICTABLE) mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF; /* Cache fsid of filesystem containing the marked object */ if (fsid) { ret = fanotify_set_mark_fsid(group, mark, fsid); if (ret) goto out_put_mark; } else { fan_mark->fsid.val[0] = fan_mark->fsid.val[1] = 0; } ret = fsnotify_add_mark_locked(mark, obj, obj_type, 0); if (ret) goto out_put_mark; return mark; out_put_mark: fsnotify_put_mark(mark); out_dec_ucounts: if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS)) dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS); return ERR_PTR(ret); } static int fanotify_group_init_error_pool(struct fsnotify_group *group) { if (mempool_initialized(&group->fanotify_data.error_events_pool)) return 0; return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool, FANOTIFY_DEFAULT_FEE_POOL_SIZE, sizeof(struct fanotify_error_event)); } static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark, __u32 mask, unsigned int fan_flags) { /* * Non evictable mark cannot be downgraded to evictable mark. */ if (fan_flags & FAN_MARK_EVICTABLE && !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) return -EEXIST; /* * New ignore mask semantics cannot be downgraded to old semantics. */ if (fan_flags & FAN_MARK_IGNORED_MASK && fsn_mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return -EEXIST; /* * An ignore mask that survives modify could never be downgraded to not * survive modify. With new FAN_MARK_IGNORE semantics we make that rule * explicit and return an error when trying to update the ignore mask * without the original FAN_MARK_IGNORED_SURV_MODIFY value. */ if (fan_flags & FAN_MARK_IGNORE && !(fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) && fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) return -EEXIST; /* For now pre-content events are not generated for directories */ mask |= fsn_mark->mask; if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) return -EEXIST; return 0; } static int fanotify_add_mark(struct fsnotify_group *group, void *obj, unsigned int obj_type, __u32 mask, unsigned int fan_flags, struct fan_fsid *fsid) { struct fsnotify_mark *fsn_mark; bool recalc; int ret = 0; fsnotify_group_lock(group); fsn_mark = fsnotify_find_mark(obj, obj_type, group); if (!fsn_mark) { fsn_mark = fanotify_add_new_mark(group, obj, obj_type, fan_flags, fsid); if (IS_ERR(fsn_mark)) { fsnotify_group_unlock(group); return PTR_ERR(fsn_mark); } } /* * Check if requested mark flags conflict with an existing mark flags. */ ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags); if (ret) goto out; /* * Error events are pre-allocated per group, only if strictly * needed (i.e. FAN_FS_ERROR was requested). */ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS) && (mask & FAN_FS_ERROR)) { ret = fanotify_group_init_error_pool(group); if (ret) goto out; } recalc = fanotify_mark_add_to_mask(fsn_mark, mask, fan_flags); if (recalc) fsnotify_recalc_mask(fsn_mark->connector); out: fsnotify_group_unlock(group); fsnotify_put_mark(fsn_mark); if (!ret && (mask & FANOTIFY_PERM_EVENTS)) fanotify_perm_watchdog_group_add(group); return ret; } static struct fsnotify_event *fanotify_alloc_overflow_event(void) { struct fanotify_event *oevent; oevent = kmalloc(sizeof(*oevent), GFP_KERNEL_ACCOUNT); if (!oevent) return NULL; fanotify_init_event(oevent, 0, FS_Q_OVERFLOW); oevent->type = FANOTIFY_EVENT_TYPE_OVERFLOW; return &oevent->fse; } static struct hlist_head *fanotify_alloc_merge_hash(void) { struct hlist_head *hash; hash = kmalloc(sizeof(struct hlist_head) << FANOTIFY_HTABLE_BITS, GFP_KERNEL_ACCOUNT); if (!hash) return NULL; __hash_init(hash, FANOTIFY_HTABLE_SIZE); return hash; } /* fanotify syscalls */ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) { struct user_namespace *user_ns = current_user_ns(); struct fsnotify_group *group; int f_flags, fd; unsigned int fid_mode = flags & FANOTIFY_FID_BITS; unsigned int class = flags & FANOTIFY_CLASS_BITS; unsigned int internal_flags = 0; struct file *file; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); if (!capable(CAP_SYS_ADMIN)) { /* * An unprivileged user can setup an fanotify group with * limited functionality - an unprivileged group is limited to * notification events with file handles or mount ids and it * cannot use unlimited queue/marks. */ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !(flags & (FANOTIFY_FID_BITS | FAN_REPORT_MNT))) return -EPERM; /* * Setting the internal flag FANOTIFY_UNPRIV on the group * prevents setting mount/filesystem marks on this group and * prevents reporting pid and open fd in events. */ internal_flags |= FANOTIFY_UNPRIV; } #ifdef CONFIG_AUDITSYSCALL if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT)) #else if (flags & ~FANOTIFY_INIT_FLAGS) #endif return -EINVAL; /* * A pidfd can only be returned for a thread-group leader; thus * FAN_REPORT_PIDFD and FAN_REPORT_TID need to remain mutually * exclusive. */ if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID)) return -EINVAL; /* Don't allow mixing mnt events with inode events for now */ if (flags & FAN_REPORT_MNT) { if (class != FAN_CLASS_NOTIF) return -EINVAL; if (flags & (FANOTIFY_FID_BITS | FAN_REPORT_FD_ERROR)) return -EINVAL; } if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS) return -EINVAL; switch (event_f_flags & O_ACCMODE) { case O_RDONLY: case O_RDWR: case O_WRONLY: break; default: return -EINVAL; } if (fid_mode && class != FAN_CLASS_NOTIF) return -EINVAL; /* * Child name is reported with parent fid so requires dir fid. * We can report both child fid and dir fid with or without name. */ if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID)) return -EINVAL; /* * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID * and is used as an indication to report both dir and child fid on all * dirent events. */ if ((fid_mode & FAN_REPORT_TARGET_FID) && (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) return -EINVAL; f_flags = O_RDWR; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; if (flags & FAN_NONBLOCK) f_flags |= O_NONBLOCK; /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */ group = fsnotify_alloc_group(&fanotify_fsnotify_ops, FSNOTIFY_GROUP_USER); if (IS_ERR(group)) { return PTR_ERR(group); } /* Enforce groups limits per user in all containing user ns */ group->fanotify_data.ucounts = inc_ucount(user_ns, current_euid(), UCOUNT_FANOTIFY_GROUPS); if (!group->fanotify_data.ucounts) { fd = -EMFILE; goto out_destroy_group; } group->fanotify_data.flags = flags | internal_flags; group->memcg = get_mem_cgroup_from_mm(current->mm); group->user_ns = get_user_ns(user_ns); group->fanotify_data.merge_hash = fanotify_alloc_merge_hash(); if (!group->fanotify_data.merge_hash) { fd = -ENOMEM; goto out_destroy_group; } group->overflow_event = fanotify_alloc_overflow_event(); if (unlikely(!group->overflow_event)) { fd = -ENOMEM; goto out_destroy_group; } if (force_o_largefile()) event_f_flags |= O_LARGEFILE; group->fanotify_data.f_flags = event_f_flags; init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); INIT_LIST_HEAD(&group->fanotify_data.perm_grp_list); switch (class) { case FAN_CLASS_NOTIF: group->priority = FSNOTIFY_PRIO_NORMAL; break; case FAN_CLASS_CONTENT: group->priority = FSNOTIFY_PRIO_CONTENT; break; case FAN_CLASS_PRE_CONTENT: group->priority = FSNOTIFY_PRIO_PRE_CONTENT; break; default: fd = -EINVAL; goto out_destroy_group; } BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_QUEUE)); if (flags & FAN_UNLIMITED_QUEUE) { group->max_events = UINT_MAX; } else { group->max_events = fanotify_max_queued_events; } if (flags & FAN_ENABLE_AUDIT) { fd = -EPERM; if (!capable(CAP_AUDIT_WRITE)) goto out_destroy_group; } fd = get_unused_fd_flags(f_flags); if (fd < 0) goto out_destroy_group; file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group, f_flags, FMODE_NONOTIFY); if (IS_ERR(file)) { put_unused_fd(fd); fd = PTR_ERR(file); goto out_destroy_group; } fd_install(fd, file); return fd; out_destroy_group: fsnotify_destroy_group(group); return fd; } static int fanotify_test_fsid(struct dentry *dentry, unsigned int flags, struct fan_fsid *fsid) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; __kernel_fsid_t root_fsid; int err; /* * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse). */ err = vfs_get_fsid(dentry, &fsid->id); if (err) return err; fsid->sb = dentry->d_sb; if (!fsid->id.val[0] && !fsid->id.val[1]) { err = -ENODEV; goto weak; } /* * Make sure dentry is not of a filesystem subvolume (e.g. btrfs) * which uses a different fsid than sb root. */ err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid); if (err) return err; if (!fanotify_fsid_equal(&root_fsid, &fsid->id)) { err = -EXDEV; goto weak; } fsid->weak = false; return 0; weak: /* Allow weak fsid when marking inodes */ fsid->weak = true; return (mark_type == FAN_MARK_INODE) ? 0 : err; } /* Check if filesystem can encode a unique fid */ static int fanotify_test_fid(struct dentry *dentry, unsigned int flags) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; const struct export_operations *nop = dentry->d_sb->s_export_op; /* * We need to make sure that the filesystem supports encoding of * file handles so user can use name_to_handle_at() to compare fids * reported with events to the file handle of watched objects. */ if (!exportfs_can_encode_fid(nop)) return -EOPNOTSUPP; /* * For sb/mount mark, we also need to make sure that the filesystem * supports decoding file handles, so user has a way to map back the * reported fids to filesystem objects. */ if (mark_type != FAN_MARK_INODE && !exportfs_can_decode_fh(nop)) return -EOPNOTSUPP; return 0; } static int fanotify_events_supported(struct fsnotify_group *group, const struct path *path, __u64 mask, unsigned int flags) { unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; bool is_dir = d_is_dir(path->dentry); /* Strict validation of events in non-dir inode mask with v5.17+ APIs */ bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) || (mask & FAN_RENAME) || (flags & FAN_MARK_IGNORE); /* * Filesystems need to opt-into pre-content evnets (a.k.a HSM) * and they are only supported on regular files and directories. */ if (mask & FANOTIFY_PRE_CONTENT_EVENTS) { if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM)) return -EOPNOTSUPP; if (!is_dir && !d_is_reg(path->dentry)) return -EINVAL; } /* * Some filesystems such as 'proc' acquire unusual locks when opening * files. For them fanotify permission events have high chances of * deadlocking the system - open done when reporting fanotify event * blocks on this "unusual" lock while another process holding the lock * waits for fanotify permission event to be answered. Just disallow * permission events for such filesystems. */ if (mask & FANOTIFY_PERM_EVENTS && path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM) return -EINVAL; /* * mount and sb marks are not allowed on kernel internal pseudo fs, * like pipe_mnt, because that would subscribe to events on all the * anonynous pipes in the system. * * SB_NOUSER covers all of the internal pseudo fs whose objects are not * exposed to user's mount namespace, but there are other SB_KERNMOUNT * fs, like nsfs, debugfs, for which the value of allowing sb and mount * mark is questionable. For now we leave them alone. */ if (mark_type != FAN_MARK_INODE && path->mnt->mnt_sb->s_flags & SB_NOUSER) return -EINVAL; /* * We shouldn't have allowed setting dirent events and the directory * flags FAN_ONDIR and FAN_EVENT_ON_CHILD in mask of non-dir inode, * but because we always allowed it, error only when using new APIs. */ if (strict_dir_events && mark_type == FAN_MARK_INODE && !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS)) return -ENOTDIR; return 0; } static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, int dfd, const char __user *pathname) { struct inode *inode = NULL; struct fsnotify_group *group; struct path path; struct fan_fsid __fsid, *fsid = NULL; struct user_namespace *user_ns = NULL; struct mnt_namespace *mntns; u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS; unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS; unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS; unsigned int obj_type, fid_mode; void *obj = NULL; u32 umask = 0; int ret; pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n", __func__, fanotify_fd, flags, dfd, pathname, mask); /* we only use the lower 32 bits as of right now. */ if (upper_32_bits(mask)) return -EINVAL; if (flags & ~FANOTIFY_MARK_FLAGS) return -EINVAL; switch (mark_type) { case FAN_MARK_INODE: obj_type = FSNOTIFY_OBJ_TYPE_INODE; break; case FAN_MARK_MOUNT: obj_type = FSNOTIFY_OBJ_TYPE_VFSMOUNT; break; case FAN_MARK_FILESYSTEM: obj_type = FSNOTIFY_OBJ_TYPE_SB; break; case FAN_MARK_MNTNS: obj_type = FSNOTIFY_OBJ_TYPE_MNTNS; break; default: return -EINVAL; } switch (mark_cmd) { case FAN_MARK_ADD: case FAN_MARK_REMOVE: if (!mask) return -EINVAL; break; case FAN_MARK_FLUSH: if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH)) return -EINVAL; break; default: return -EINVAL; } if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) valid_mask |= FANOTIFY_PERM_EVENTS; if (mask & ~valid_mask) return -EINVAL; /* We don't allow FAN_MARK_IGNORE & FAN_MARK_IGNORED_MASK together */ if (ignore == (FAN_MARK_IGNORE | FAN_MARK_IGNORED_MASK)) return -EINVAL; /* * Event flags (FAN_ONDIR, FAN_EVENT_ON_CHILD) have no effect with * FAN_MARK_IGNORED_MASK. */ if (ignore == FAN_MARK_IGNORED_MASK) { mask &= ~FANOTIFY_EVENT_FLAGS; umask = FANOTIFY_EVENT_FLAGS; } CLASS(fd, f)(fanotify_fd); if (fd_empty(f)) return -EBADF; /* verify that this is indeed an fanotify instance */ if (unlikely(fd_file(f)->f_op != &fanotify_fops)) return -EINVAL; group = fd_file(f)->private_data; /* Only report mount events on mnt namespace */ if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) { if (mask & ~FANOTIFY_MOUNT_EVENTS) return -EINVAL; if (mark_type != FAN_MARK_MNTNS) return -EINVAL; } else { if (mask & FANOTIFY_MOUNT_EVENTS) return -EINVAL; if (mark_type == FAN_MARK_MNTNS) return -EINVAL; } /* * A user is allowed to setup sb/mount/mntns marks only if it is * capable in the user ns where the group was created. */ if (!ns_capable(group->user_ns, CAP_SYS_ADMIN) && mark_type != FAN_MARK_INODE) return -EPERM; /* * Permission events are not allowed for FAN_CLASS_NOTIF. * Pre-content permission events are not allowed for FAN_CLASS_CONTENT. */ if (mask & FANOTIFY_PERM_EVENTS && group->priority == FSNOTIFY_PRIO_NORMAL) return -EINVAL; else if (mask & FANOTIFY_PRE_CONTENT_EVENTS && group->priority == FSNOTIFY_PRIO_CONTENT) return -EINVAL; if (mask & FAN_FS_ERROR && mark_type != FAN_MARK_FILESYSTEM) return -EINVAL; /* * Evictable is only relevant for inode marks, because only inode object * can be evicted on memory pressure. */ if (flags & FAN_MARK_EVICTABLE && mark_type != FAN_MARK_INODE) return -EINVAL; /* * Events that do not carry enough information to report * event->fd require a group that supports reporting fid. Those * events are not supported on a mount mark, because they do not * carry enough information (i.e. path) to be filtered by mount * point. */ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_MOUNT_EVENTS|FANOTIFY_EVENT_FLAGS) && (!fid_mode || mark_type == FAN_MARK_MOUNT)) return -EINVAL; /* * FAN_RENAME uses special info type records to report the old and * new parent+name. Reporting only old and new parent id is less * useful and was not implemented. */ if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME)) return -EINVAL; /* Pre-content events are not currently generated for directories. */ if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR) return -EINVAL; if (mark_cmd == FAN_MARK_FLUSH) { fsnotify_clear_marks_by_group(group, obj_type); return 0; } ret = fanotify_find_path(dfd, pathname, &path, flags, (mask & ALL_FSNOTIFY_EVENTS), obj_type); if (ret) return ret; if (mark_cmd == FAN_MARK_ADD) { ret = fanotify_events_supported(group, &path, mask, flags); if (ret) goto path_put_and_out; } if (fid_mode) { ret = fanotify_test_fsid(path.dentry, flags, &__fsid); if (ret) goto path_put_and_out; ret = fanotify_test_fid(path.dentry, flags); if (ret) goto path_put_and_out; fsid = &__fsid; } /* * In addition to being capable in the user ns where group was created, * the user also needs to be capable in the user ns associated with * the filesystem or in the user ns associated with the mntns * (when marking mntns). */ if (obj_type == FSNOTIFY_OBJ_TYPE_INODE) { inode = path.dentry->d_inode; obj = inode; } else if (obj_type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { user_ns = path.mnt->mnt_sb->s_user_ns; obj = path.mnt; } else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) { user_ns = path.mnt->mnt_sb->s_user_ns; obj = path.mnt->mnt_sb; } else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) { ret = -EINVAL; mntns = mnt_ns_from_dentry(path.dentry); if (!mntns) goto path_put_and_out; user_ns = mntns->user_ns; obj = mntns; } ret = -EPERM; if (user_ns && !ns_capable(user_ns, CAP_SYS_ADMIN)) goto path_put_and_out; ret = -EINVAL; if (!obj) goto path_put_and_out; /* * If some other task has this inode open for write we should not add * an ignore mask, unless that ignore mask is supposed to survive * modification changes anyway. */ if (mark_cmd == FAN_MARK_ADD && (flags & FANOTIFY_MARK_IGNORE_BITS) && !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) { ret = !inode ? -EINVAL : -EISDIR; /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */ if (ignore == FAN_MARK_IGNORE && (!inode || S_ISDIR(inode->i_mode))) goto path_put_and_out; ret = 0; if (inode && inode_is_open_for_write(inode)) goto path_put_and_out; } /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ if (!inode || !S_ISDIR(inode->i_mode)) { mask &= ~FAN_EVENT_ON_CHILD; umask = FAN_EVENT_ON_CHILD; /* * If group needs to report parent fid, register for getting * events with parent/name info for non-directory. */ if ((fid_mode & FAN_REPORT_DIR_FID) && (flags & FAN_MARK_ADD) && !ignore) mask |= FAN_EVENT_ON_CHILD; } /* create/update an inode mark */ switch (mark_cmd) { case FAN_MARK_ADD: ret = fanotify_add_mark(group, obj, obj_type, mask, flags, fsid); break; case FAN_MARK_REMOVE: ret = fanotify_remove_mark(group, obj, obj_type, mask, flags, umask); break; default: ret = -EINVAL; } path_put_and_out: path_put(&path); return ret; } #ifndef CONFIG_ARCH_SPLIT_ARG64 SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, __u64, mask, int, dfd, const char __user *, pathname) { return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname); } #endif #if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT) SYSCALL32_DEFINE6(fanotify_mark, int, fanotify_fd, unsigned int, flags, SC_ARG64(mask), int, dfd, const char __user *, pathname) { return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask), dfd, pathname); } #endif /* * fanotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here * must result in panic(). */ static int __init fanotify_user_setup(void) { struct sysinfo si; int max_marks; si_meminfo(&si); /* * Allow up to 1% of addressable memory to be accounted for per user * marks limited to the range [8192, 1048576]. mount and sb marks are * a lot cheaper than inode marks, but there is no reason for a user * to have many of those, so calculate by the cost of inode marks. */ max_marks = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) / INODE_MARK_COST; max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS, FANOTIFY_DEFAULT_MAX_USER_MARKS); BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 14); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11); fanotify_mark_cache = KMEM_CACHE(fanotify_mark, SLAB_PANIC|SLAB_ACCOUNT); fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event, SLAB_PANIC); fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event, SLAB_PANIC); if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) { fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event, SLAB_PANIC); } fanotify_mnt_event_cachep = KMEM_CACHE(fanotify_mnt_event, SLAB_PANIC); fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS; init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] = FANOTIFY_DEFAULT_MAX_GROUPS; init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks; fanotify_sysctls_init(); return 0; } device_initcall(fanotify_user_setup); |
| 14 14 2 13 8 6 1 9 5 4 1 3 2 2 2 2 1 3 3 3 2 2 2 3 3 7 7 7 6 6 7 7 7 7 7 7 7 7 1 2 2 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 3 3 16 16 9 10 6 5 3 10 11 5 3 6 3 2 2 4 3 3 2 3 2 1 2 1 2 2 16 2 11 2 1 1 1 2 32 31 2 1 1 1 1 1 2 1 2 1 1 1 3 3 3 3 4 1 1 1 1 1 16 15 16 1 32 9 9 2 7 7 7 9 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2001 Paul Stewart * Copyright (c) 2001 Vojtech Pavlik * * HID char devices, giving access to raw HID device events. */ /* * * Should you need to contact me, the author, you can do so either by * e-mail - mail your message to Paul Stewart <stewart@wetlogic.net> */ #include <linux/poll.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/module.h> #include <linux/init.h> #include <linux/input.h> #include <linux/usb.h> #include <linux/hid.h> #include <linux/hiddev.h> #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/nospec.h> #include "usbhid.h" #ifdef CONFIG_USB_DYNAMIC_MINORS #define HIDDEV_MINOR_BASE 0 #define HIDDEV_MINORS 256 #else #define HIDDEV_MINOR_BASE 96 #define HIDDEV_MINORS 16 #endif #define HIDDEV_BUFFER_SIZE 2048 struct hiddev_list { struct hiddev_usage_ref buffer[HIDDEV_BUFFER_SIZE]; int head; int tail; unsigned flags; struct fasync_struct *fasync; struct hiddev *hiddev; struct list_head node; struct mutex thread_lock; }; /* * Find a report, given the report's type and ID. The ID can be specified * indirectly by REPORT_ID_FIRST (which returns the first report of the given * type) or by (REPORT_ID_NEXT | old_id), which returns the next report of the * given type which follows old_id. */ static struct hid_report * hiddev_lookup_report(struct hid_device *hid, struct hiddev_report_info *rinfo) { unsigned int flags = rinfo->report_id & ~HID_REPORT_ID_MASK; unsigned int rid = rinfo->report_id & HID_REPORT_ID_MASK; struct hid_report_enum *report_enum; struct hid_report *report; struct list_head *list; if (rinfo->report_type < HID_REPORT_TYPE_MIN || rinfo->report_type > HID_REPORT_TYPE_MAX) return NULL; report_enum = hid->report_enum + (rinfo->report_type - HID_REPORT_TYPE_MIN); switch (flags) { case 0: /* Nothing to do -- report_id is already set correctly */ break; case HID_REPORT_ID_FIRST: if (list_empty(&report_enum->report_list)) return NULL; list = report_enum->report_list.next; report = list_entry(list, struct hid_report, list); rinfo->report_id = report->id; break; case HID_REPORT_ID_NEXT: report = report_enum->report_id_hash[rid]; if (!report) return NULL; list = report->list.next; if (list == &report_enum->report_list) return NULL; report = list_entry(list, struct hid_report, list); rinfo->report_id = report->id; break; default: return NULL; } return report_enum->report_id_hash[rinfo->report_id]; } /* * Perform an exhaustive search of the report table for a usage, given its * type and usage id. */ static struct hid_field * hiddev_lookup_usage(struct hid_device *hid, struct hiddev_usage_ref *uref) { int i, j; struct hid_report *report; struct hid_report_enum *report_enum; struct hid_field *field; if (uref->report_type < HID_REPORT_TYPE_MIN || uref->report_type > HID_REPORT_TYPE_MAX) return NULL; report_enum = hid->report_enum + (uref->report_type - HID_REPORT_TYPE_MIN); list_for_each_entry(report, &report_enum->report_list, list) { for (i = 0; i < report->maxfield; i++) { field = report->field[i]; for (j = 0; j < field->maxusage; j++) { if (field->usage[j].hid == uref->usage_code) { uref->report_id = report->id; uref->field_index = i; uref->usage_index = j; return field; } } } } return NULL; } static void hiddev_send_event(struct hid_device *hid, struct hiddev_usage_ref *uref) { struct hiddev *hiddev = hid->hiddev; struct hiddev_list *list; unsigned long flags; spin_lock_irqsave(&hiddev->list_lock, flags); list_for_each_entry(list, &hiddev->list, node) { if (uref->field_index != HID_FIELD_INDEX_NONE || (list->flags & HIDDEV_FLAG_REPORT) != 0) { list->buffer[list->head] = *uref; list->head = (list->head + 1) & (HIDDEV_BUFFER_SIZE - 1); kill_fasync(&list->fasync, SIGIO, POLL_IN); } } spin_unlock_irqrestore(&hiddev->list_lock, flags); wake_up_interruptible(&hiddev->wait); } /* * This is where hid.c calls into hiddev to pass an event that occurred over * the interrupt pipe */ void hiddev_hid_event(struct hid_device *hid, struct hid_field *field, struct hid_usage *usage, __s32 value) { unsigned type = field->report_type; struct hiddev_usage_ref uref; uref.report_type = (type == HID_INPUT_REPORT) ? HID_REPORT_TYPE_INPUT : ((type == HID_OUTPUT_REPORT) ? HID_REPORT_TYPE_OUTPUT : ((type == HID_FEATURE_REPORT) ? HID_REPORT_TYPE_FEATURE : 0)); uref.report_id = field->report->id; uref.field_index = field->index; uref.usage_index = (usage - field->usage); uref.usage_code = usage->hid; uref.value = value; hiddev_send_event(hid, &uref); } EXPORT_SYMBOL_GPL(hiddev_hid_event); void hiddev_report_event(struct hid_device *hid, struct hid_report *report) { unsigned type = report->type; struct hiddev_usage_ref uref; memset(&uref, 0, sizeof(uref)); uref.report_type = (type == HID_INPUT_REPORT) ? HID_REPORT_TYPE_INPUT : ((type == HID_OUTPUT_REPORT) ? HID_REPORT_TYPE_OUTPUT : ((type == HID_FEATURE_REPORT) ? HID_REPORT_TYPE_FEATURE : 0)); uref.report_id = report->id; uref.field_index = HID_FIELD_INDEX_NONE; hiddev_send_event(hid, &uref); } /* * fasync file op */ static int hiddev_fasync(int fd, struct file *file, int on) { struct hiddev_list *list = file->private_data; return fasync_helper(fd, file, on, &list->fasync); } /* * release file op */ static int hiddev_release(struct inode * inode, struct file * file) { struct hiddev_list *list = file->private_data; unsigned long flags; spin_lock_irqsave(&list->hiddev->list_lock, flags); list_del(&list->node); spin_unlock_irqrestore(&list->hiddev->list_lock, flags); mutex_lock(&list->hiddev->existancelock); if (!--list->hiddev->open) { if (list->hiddev->exist) { hid_hw_close(list->hiddev->hid); hid_hw_power(list->hiddev->hid, PM_HINT_NORMAL); } else { mutex_unlock(&list->hiddev->existancelock); kfree(list->hiddev); vfree(list); return 0; } } mutex_unlock(&list->hiddev->existancelock); vfree(list); return 0; } static int __hiddev_open(struct hiddev *hiddev, struct file *file) { struct hiddev_list *list; int error; lockdep_assert_held(&hiddev->existancelock); list = vzalloc(sizeof(*list)); if (!list) return -ENOMEM; mutex_init(&list->thread_lock); list->hiddev = hiddev; if (!hiddev->open++) { error = hid_hw_power(hiddev->hid, PM_HINT_FULLON); if (error < 0) goto err_drop_count; error = hid_hw_open(hiddev->hid); if (error < 0) goto err_normal_power; } spin_lock_irq(&hiddev->list_lock); list_add_tail(&list->node, &hiddev->list); spin_unlock_irq(&hiddev->list_lock); file->private_data = list; return 0; err_normal_power: hid_hw_power(hiddev->hid, PM_HINT_NORMAL); err_drop_count: hiddev->open--; vfree(list); return error; } /* * open file op */ static int hiddev_open(struct inode *inode, struct file *file) { struct usb_interface *intf; struct hid_device *hid; struct hiddev *hiddev; int res; intf = usbhid_find_interface(iminor(inode)); if (!intf) return -ENODEV; hid = usb_get_intfdata(intf); hiddev = hid->hiddev; mutex_lock(&hiddev->existancelock); res = hiddev->exist ? __hiddev_open(hiddev, file) : -ENODEV; mutex_unlock(&hiddev->existancelock); return res; } /* * "write" file op */ static ssize_t hiddev_write(struct file * file, const char __user * buffer, size_t count, loff_t *ppos) { return -EINVAL; } /* * "read" file op */ static ssize_t hiddev_read(struct file * file, char __user * buffer, size_t count, loff_t *ppos) { DEFINE_WAIT(wait); struct hiddev_list *list = file->private_data; int event_size; int retval; event_size = ((list->flags & HIDDEV_FLAG_UREF) != 0) ? sizeof(struct hiddev_usage_ref) : sizeof(struct hiddev_event); if (count < event_size) return 0; /* lock against other threads */ retval = mutex_lock_interruptible(&list->thread_lock); if (retval) return -ERESTARTSYS; while (retval == 0) { if (list->head == list->tail) { prepare_to_wait(&list->hiddev->wait, &wait, TASK_INTERRUPTIBLE); while (list->head == list->tail) { if (signal_pending(current)) { retval = -ERESTARTSYS; break; } if (!list->hiddev->exist) { retval = -EIO; break; } if (file->f_flags & O_NONBLOCK) { retval = -EAGAIN; break; } /* let O_NONBLOCK tasks run */ mutex_unlock(&list->thread_lock); schedule(); if (mutex_lock_interruptible(&list->thread_lock)) { finish_wait(&list->hiddev->wait, &wait); return -EINTR; } set_current_state(TASK_INTERRUPTIBLE); } finish_wait(&list->hiddev->wait, &wait); } if (retval) { mutex_unlock(&list->thread_lock); return retval; } while (list->head != list->tail && retval + event_size <= count) { if ((list->flags & HIDDEV_FLAG_UREF) == 0) { if (list->buffer[list->tail].field_index != HID_FIELD_INDEX_NONE) { struct hiddev_event event; event.hid = list->buffer[list->tail].usage_code; event.value = list->buffer[list->tail].value; if (copy_to_user(buffer + retval, &event, sizeof(struct hiddev_event))) { mutex_unlock(&list->thread_lock); return -EFAULT; } retval += sizeof(struct hiddev_event); } } else { if (list->buffer[list->tail].field_index != HID_FIELD_INDEX_NONE || (list->flags & HIDDEV_FLAG_REPORT) != 0) { if (copy_to_user(buffer + retval, list->buffer + list->tail, sizeof(struct hiddev_usage_ref))) { mutex_unlock(&list->thread_lock); return -EFAULT; } retval += sizeof(struct hiddev_usage_ref); } } list->tail = (list->tail + 1) & (HIDDEV_BUFFER_SIZE - 1); } } mutex_unlock(&list->thread_lock); return retval; } /* * "poll" file op * No kernel lock - fine */ static __poll_t hiddev_poll(struct file *file, poll_table *wait) { struct hiddev_list *list = file->private_data; poll_wait(file, &list->hiddev->wait, wait); if (list->head != list->tail) return EPOLLIN | EPOLLRDNORM | EPOLLOUT; if (!list->hiddev->exist) return EPOLLERR | EPOLLHUP; return 0; } /* * "ioctl" file op */ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, void __user *user_arg) { struct hid_device *hid = hiddev->hid; struct hiddev_report_info rinfo; struct hiddev_usage_ref_multi *uref_multi = NULL; struct hiddev_usage_ref *uref; struct hid_report *report; struct hid_field *field; int i; uref_multi = kmalloc(sizeof(struct hiddev_usage_ref_multi), GFP_KERNEL); if (!uref_multi) return -ENOMEM; uref = &uref_multi->uref; if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { if (copy_from_user(uref_multi, user_arg, sizeof(*uref_multi))) goto fault; } else { if (copy_from_user(uref, user_arg, sizeof(*uref))) goto fault; } switch (cmd) { case HIDIOCGUCODE: rinfo.report_type = uref->report_type; rinfo.report_id = uref->report_id; if ((report = hiddev_lookup_report(hid, &rinfo)) == NULL) goto inval; if (uref->field_index >= report->maxfield) goto inval; uref->field_index = array_index_nospec(uref->field_index, report->maxfield); field = report->field[uref->field_index]; if (uref->usage_index >= field->maxusage) goto inval; uref->usage_index = array_index_nospec(uref->usage_index, field->maxusage); uref->usage_code = field->usage[uref->usage_index].hid; if (copy_to_user(user_arg, uref, sizeof(*uref))) goto fault; goto goodreturn; default: if (cmd != HIDIOCGUSAGE && cmd != HIDIOCGUSAGES && uref->report_type == HID_REPORT_TYPE_INPUT) goto inval; if (uref->report_id == HID_REPORT_ID_UNKNOWN) { field = hiddev_lookup_usage(hid, uref); if (field == NULL) goto inval; } else { rinfo.report_type = uref->report_type; rinfo.report_id = uref->report_id; if ((report = hiddev_lookup_report(hid, &rinfo)) == NULL) goto inval; if (uref->field_index >= report->maxfield) goto inval; uref->field_index = array_index_nospec(uref->field_index, report->maxfield); field = report->field[uref->field_index]; if (cmd == HIDIOCGCOLLECTIONINDEX) { if (uref->usage_index >= field->maxusage) goto inval; uref->usage_index = array_index_nospec(uref->usage_index, field->maxusage); } else if (uref->usage_index >= field->report_count) goto inval; } if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { if (uref_multi->num_values > HID_MAX_MULTI_USAGES || uref->usage_index + uref_multi->num_values > field->report_count) goto inval; uref->usage_index = array_index_nospec(uref->usage_index, field->report_count - uref_multi->num_values); } switch (cmd) { case HIDIOCGUSAGE: if (uref->usage_index >= field->report_count) goto inval; uref->value = field->value[uref->usage_index]; if (copy_to_user(user_arg, uref, sizeof(*uref))) goto fault; goto goodreturn; case HIDIOCSUSAGE: if (uref->usage_index >= field->report_count) goto inval; field->value[uref->usage_index] = uref->value; goto goodreturn; case HIDIOCGCOLLECTIONINDEX: i = field->usage[uref->usage_index].collection_index; kfree(uref_multi); return i; case HIDIOCGUSAGES: for (i = 0; i < uref_multi->num_values; i++) uref_multi->values[i] = field->value[uref->usage_index + i]; if (copy_to_user(user_arg, uref_multi, sizeof(*uref_multi))) goto fault; goto goodreturn; case HIDIOCSUSAGES: for (i = 0; i < uref_multi->num_values; i++) field->value[uref->usage_index + i] = uref_multi->values[i]; goto goodreturn; } goodreturn: kfree(uref_multi); return 0; fault: kfree(uref_multi); return -EFAULT; inval: kfree(uref_multi); return -EINVAL; } } static noinline int hiddev_ioctl_string(struct hiddev *hiddev, unsigned int cmd, void __user *user_arg) { struct hid_device *hid = hiddev->hid; struct usb_device *dev = hid_to_usb_dev(hid); int idx, len; char *buf; if (get_user(idx, (int __user *)user_arg)) return -EFAULT; if ((buf = kmalloc(HID_STRING_SIZE, GFP_KERNEL)) == NULL) return -ENOMEM; if ((len = usb_string(dev, idx, buf, HID_STRING_SIZE-1)) < 0) { kfree(buf); return -EINVAL; } if (copy_to_user(user_arg+sizeof(int), buf, len+1)) { kfree(buf); return -EFAULT; } kfree(buf); return len; } static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct hiddev_list *list = file->private_data; struct hiddev *hiddev = list->hiddev; struct hid_device *hid; struct hiddev_collection_info cinfo; struct hiddev_report_info rinfo; struct hiddev_field_info finfo; struct hiddev_devinfo dinfo; struct hid_report *report; struct hid_field *field; void __user *user_arg = (void __user *)arg; int i, r = -EINVAL; /* Called without BKL by compat methods so no BKL taken */ mutex_lock(&hiddev->existancelock); if (!hiddev->exist) { r = -ENODEV; goto ret_unlock; } hid = hiddev->hid; switch (cmd) { case HIDIOCGVERSION: r = put_user(HID_VERSION, (int __user *)arg) ? -EFAULT : 0; break; case HIDIOCAPPLICATION: if (arg >= hid->maxapplication) break; for (i = 0; i < hid->maxcollection; i++) if (hid->collection[i].type == HID_COLLECTION_APPLICATION && arg-- == 0) break; if (i < hid->maxcollection) r = hid->collection[i].usage; break; case HIDIOCGDEVINFO: { struct usb_device *dev = hid_to_usb_dev(hid); struct usbhid_device *usbhid = hid->driver_data; memset(&dinfo, 0, sizeof(dinfo)); dinfo.bustype = BUS_USB; dinfo.busnum = dev->bus->busnum; dinfo.devnum = dev->devnum; dinfo.ifnum = usbhid->ifnum; dinfo.vendor = le16_to_cpu(dev->descriptor.idVendor); dinfo.product = le16_to_cpu(dev->descriptor.idProduct); dinfo.version = le16_to_cpu(dev->descriptor.bcdDevice); dinfo.num_applications = hid->maxapplication; r = copy_to_user(user_arg, &dinfo, sizeof(dinfo)) ? -EFAULT : 0; break; } case HIDIOCGFLAG: r = put_user(list->flags, (int __user *)arg) ? -EFAULT : 0; break; case HIDIOCSFLAG: { int newflags; if (get_user(newflags, (int __user *)arg)) { r = -EFAULT; break; } if ((newflags & ~HIDDEV_FLAGS) != 0 || ((newflags & HIDDEV_FLAG_REPORT) != 0 && (newflags & HIDDEV_FLAG_UREF) == 0)) break; list->flags = newflags; r = 0; break; } case HIDIOCGSTRING: r = hiddev_ioctl_string(hiddev, cmd, user_arg); break; case HIDIOCINITREPORT: usbhid_init_reports(hid); hiddev->initialized = true; r = 0; break; case HIDIOCGREPORT: if (copy_from_user(&rinfo, user_arg, sizeof(rinfo))) { r = -EFAULT; break; } if (rinfo.report_type == HID_REPORT_TYPE_OUTPUT) break; report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; hid_hw_request(hid, report, HID_REQ_GET_REPORT); hid_hw_wait(hid); r = 0; break; case HIDIOCSREPORT: if (copy_from_user(&rinfo, user_arg, sizeof(rinfo))) { r = -EFAULT; break; } if (rinfo.report_type == HID_REPORT_TYPE_INPUT) break; report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; hid_hw_request(hid, report, HID_REQ_SET_REPORT); hid_hw_wait(hid); r = 0; break; case HIDIOCGREPORTINFO: if (copy_from_user(&rinfo, user_arg, sizeof(rinfo))) { r = -EFAULT; break; } report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; rinfo.num_fields = report->maxfield; r = copy_to_user(user_arg, &rinfo, sizeof(rinfo)) ? -EFAULT : 0; break; case HIDIOCGFIELDINFO: if (copy_from_user(&finfo, user_arg, sizeof(finfo))) { r = -EFAULT; break; } rinfo.report_type = finfo.report_type; rinfo.report_id = finfo.report_id; report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; if (finfo.field_index >= report->maxfield) break; finfo.field_index = array_index_nospec(finfo.field_index, report->maxfield); field = report->field[finfo.field_index]; memset(&finfo, 0, sizeof(finfo)); finfo.report_type = rinfo.report_type; finfo.report_id = rinfo.report_id; finfo.field_index = field->report_count - 1; finfo.maxusage = field->maxusage; finfo.flags = field->flags; finfo.physical = field->physical; finfo.logical = field->logical; finfo.application = field->application; finfo.logical_minimum = field->logical_minimum; finfo.logical_maximum = field->logical_maximum; finfo.physical_minimum = field->physical_minimum; finfo.physical_maximum = field->physical_maximum; finfo.unit_exponent = field->unit_exponent; finfo.unit = field->unit; r = copy_to_user(user_arg, &finfo, sizeof(finfo)) ? -EFAULT : 0; break; case HIDIOCGUCODE: case HIDIOCGUSAGE: case HIDIOCSUSAGE: case HIDIOCGUSAGES: case HIDIOCSUSAGES: case HIDIOCGCOLLECTIONINDEX: if (!hiddev->initialized) { usbhid_init_reports(hid); hiddev->initialized = true; } r = hiddev_ioctl_usage(hiddev, cmd, user_arg); break; case HIDIOCGCOLLECTIONINFO: if (copy_from_user(&cinfo, user_arg, sizeof(cinfo))) { r = -EFAULT; break; } if (cinfo.index >= hid->maxcollection) break; cinfo.index = array_index_nospec(cinfo.index, hid->maxcollection); cinfo.type = hid->collection[cinfo.index].type; cinfo.usage = hid->collection[cinfo.index].usage; cinfo.level = hid->collection[cinfo.index].level; r = copy_to_user(user_arg, &cinfo, sizeof(cinfo)) ? -EFAULT : 0; break; default: if (_IOC_TYPE(cmd) != 'H' || _IOC_DIR(cmd) != _IOC_READ) break; if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGNAME(0))) { int len = strlen(hid->name) + 1; if (len > _IOC_SIZE(cmd)) len = _IOC_SIZE(cmd); r = copy_to_user(user_arg, hid->name, len) ? -EFAULT : len; break; } if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGPHYS(0))) { int len = strlen(hid->phys) + 1; if (len > _IOC_SIZE(cmd)) len = _IOC_SIZE(cmd); r = copy_to_user(user_arg, hid->phys, len) ? -EFAULT : len; break; } } ret_unlock: mutex_unlock(&hiddev->existancelock); return r; } static const struct file_operations hiddev_fops = { .owner = THIS_MODULE, .read = hiddev_read, .write = hiddev_write, .poll = hiddev_poll, .open = hiddev_open, .release = hiddev_release, .unlocked_ioctl = hiddev_ioctl, .fasync = hiddev_fasync, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static char *hiddev_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "usb/%s", dev_name(dev)); } static struct usb_class_driver hiddev_class = { .name = "hiddev%d", .devnode = hiddev_devnode, .fops = &hiddev_fops, .minor_base = HIDDEV_MINOR_BASE, }; /* * This is where hid.c calls us to connect a hid device to the hiddev driver */ int hiddev_connect(struct hid_device *hid, unsigned int force) { struct hiddev *hiddev; struct usbhid_device *usbhid = hid->driver_data; int retval; if (!force) { unsigned int i; for (i = 0; i < hid->maxcollection; i++) if (hid->collection[i].type == HID_COLLECTION_APPLICATION && !IS_INPUT_APPLICATION(hid->collection[i].usage)) break; if (i == hid->maxcollection) return -EINVAL; } if (!(hiddev = kzalloc(sizeof(struct hiddev), GFP_KERNEL))) return -ENOMEM; init_waitqueue_head(&hiddev->wait); INIT_LIST_HEAD(&hiddev->list); spin_lock_init(&hiddev->list_lock); mutex_init(&hiddev->existancelock); hid->hiddev = hiddev; hiddev->hid = hid; hiddev->exist = 1; retval = usb_register_dev(usbhid->intf, &hiddev_class); if (retval) { hid_err(hid, "Not able to get a minor for this device\n"); hid->hiddev = NULL; kfree(hiddev); return retval; } /* * If HID_QUIRK_NO_INIT_REPORTS is set, make sure we don't initialize * the reports. */ hiddev->initialized = hid->quirks & HID_QUIRK_NO_INIT_REPORTS; hiddev->minor = usbhid->intf->minor; return 0; } /* * This is where hid.c calls us to disconnect a hiddev device from the * corresponding hid device (usually because the usb device has disconnected) */ static struct usb_class_driver hiddev_class; void hiddev_disconnect(struct hid_device *hid) { struct hiddev *hiddev = hid->hiddev; struct usbhid_device *usbhid = hid->driver_data; usb_deregister_dev(usbhid->intf, &hiddev_class); mutex_lock(&hiddev->existancelock); hiddev->exist = 0; if (hiddev->open) { hid_hw_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); } } |
| 7 7 7 7 1 3 1 2 1 1 1 1 6 6 6 2 3 4 3 1 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Software async crypto daemon. * * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> * * Added AEAD support to cryptd. * Authors: Tadeusz Struk (tadeusz.struk@intel.com) * Adrian Hoban <adrian.hoban@intel.com> * Gabriele Paoloni <gabriele.paoloni@intel.com> * Aidan O'Mahony (aidan.o.mahony@intel.com) * Copyright (c) 2010, Intel Corporation. */ #include <crypto/internal/hash.h> #include <crypto/internal/aead.h> #include <crypto/internal/skcipher.h> #include <crypto/cryptd.h> #include <linux/refcount.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/workqueue.h> static unsigned int cryptd_max_cpu_qlen = 1000; module_param(cryptd_max_cpu_qlen, uint, 0); MODULE_PARM_DESC(cryptd_max_cpu_qlen, "Set cryptd Max queue depth"); static struct workqueue_struct *cryptd_wq; struct cryptd_cpu_queue { local_lock_t bh_lock; struct crypto_queue queue; struct work_struct work; }; struct cryptd_queue { /* * Protected by disabling BH to allow enqueueing from softinterrupt and * dequeuing from kworker (cryptd_queue_worker()). */ struct cryptd_cpu_queue __percpu *cpu_queue; }; struct cryptd_instance_ctx { struct crypto_spawn spawn; struct cryptd_queue *queue; }; struct skcipherd_instance_ctx { struct crypto_skcipher_spawn spawn; struct cryptd_queue *queue; }; struct hashd_instance_ctx { struct crypto_shash_spawn spawn; struct cryptd_queue *queue; }; struct aead_instance_ctx { struct crypto_aead_spawn aead_spawn; struct cryptd_queue *queue; }; struct cryptd_skcipher_ctx { refcount_t refcnt; struct crypto_skcipher *child; }; struct cryptd_skcipher_request_ctx { struct skcipher_request req; }; struct cryptd_hash_ctx { refcount_t refcnt; struct crypto_shash *child; }; struct cryptd_hash_request_ctx { crypto_completion_t complete; void *data; struct shash_desc desc; }; struct cryptd_aead_ctx { refcount_t refcnt; struct crypto_aead *child; }; struct cryptd_aead_request_ctx { struct aead_request req; }; static void cryptd_queue_worker(struct work_struct *work); static int cryptd_init_queue(struct cryptd_queue *queue, unsigned int max_cpu_qlen) { int cpu; struct cryptd_cpu_queue *cpu_queue; queue->cpu_queue = alloc_percpu(struct cryptd_cpu_queue); if (!queue->cpu_queue) return -ENOMEM; for_each_possible_cpu(cpu) { cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu); crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); INIT_WORK(&cpu_queue->work, cryptd_queue_worker); local_lock_init(&cpu_queue->bh_lock); } pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen); return 0; } static void cryptd_fini_queue(struct cryptd_queue *queue) { int cpu; struct cryptd_cpu_queue *cpu_queue; for_each_possible_cpu(cpu) { cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu); BUG_ON(cpu_queue->queue.qlen); } free_percpu(queue->cpu_queue); } static int cryptd_enqueue_request(struct cryptd_queue *queue, struct crypto_async_request *request) { int err; struct cryptd_cpu_queue *cpu_queue; refcount_t *refcnt; local_bh_disable(); local_lock_nested_bh(&queue->cpu_queue->bh_lock); cpu_queue = this_cpu_ptr(queue->cpu_queue); err = crypto_enqueue_request(&cpu_queue->queue, request); refcnt = crypto_tfm_ctx(request->tfm); if (err == -ENOSPC) goto out; queue_work_on(smp_processor_id(), cryptd_wq, &cpu_queue->work); if (!refcount_read(refcnt)) goto out; refcount_inc(refcnt); out: local_unlock_nested_bh(&queue->cpu_queue->bh_lock); local_bh_enable(); return err; } /* Called in workqueue context, do one real cryption work (via * req->complete) and reschedule itself if there are more work to * do. */ static void cryptd_queue_worker(struct work_struct *work) { struct cryptd_cpu_queue *cpu_queue; struct crypto_async_request *req, *backlog; cpu_queue = container_of(work, struct cryptd_cpu_queue, work); /* * Only handle one request at a time to avoid hogging crypto workqueue. */ local_bh_disable(); __local_lock_nested_bh(&cpu_queue->bh_lock); backlog = crypto_get_backlog(&cpu_queue->queue); req = crypto_dequeue_request(&cpu_queue->queue); __local_unlock_nested_bh(&cpu_queue->bh_lock); local_bh_enable(); if (!req) return; if (backlog) crypto_request_complete(backlog, -EINPROGRESS); crypto_request_complete(req, 0); if (cpu_queue->queue.qlen) queue_work(cryptd_wq, &cpu_queue->work); } static inline struct cryptd_queue *cryptd_get_queue(struct crypto_tfm *tfm) { struct crypto_instance *inst = crypto_tfm_alg_instance(tfm); struct cryptd_instance_ctx *ictx = crypto_instance_ctx(inst); return ictx->queue; } static void cryptd_type_and_mask(struct crypto_attr_type *algt, u32 *type, u32 *mask) { /* * cryptd is allowed to wrap internal algorithms, but in that case the * resulting cryptd instance will be marked as internal as well. */ *type = algt->type & CRYPTO_ALG_INTERNAL; *mask = algt->mask & CRYPTO_ALG_INTERNAL; /* No point in cryptd wrapping an algorithm that's already async. */ *mask |= CRYPTO_ALG_ASYNC; *mask |= crypto_algt_inherited_mask(algt); } static int cryptd_init_instance(struct crypto_instance *inst, struct crypto_alg *alg) { if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "cryptd(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME); inst->alg.cra_priority = alg->cra_priority + 50; inst->alg.cra_blocksize = alg->cra_blocksize; inst->alg.cra_alignmask = alg->cra_alignmask; return 0; } static int cryptd_skcipher_setkey(struct crypto_skcipher *parent, const u8 *key, unsigned int keylen) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(parent); struct crypto_skcipher *child = ctx->child; crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) & CRYPTO_TFM_REQ_MASK); return crypto_skcipher_setkey(child, key, keylen); } static struct skcipher_request *cryptd_skcipher_prepare( struct skcipher_request *req, int err) { struct cryptd_skcipher_request_ctx *rctx = skcipher_request_ctx(req); struct skcipher_request *subreq = &rctx->req; struct cryptd_skcipher_ctx *ctx; struct crypto_skcipher *child; req->base.complete = subreq->base.complete; req->base.data = subreq->base.data; if (unlikely(err == -EINPROGRESS)) return NULL; ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); child = ctx->child; skcipher_request_set_tfm(subreq, child); skcipher_request_set_callback(subreq, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); skcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, req->iv); return subreq; } static void cryptd_skcipher_complete(struct skcipher_request *req, int err, crypto_completion_t complete) { struct cryptd_skcipher_request_ctx *rctx = skcipher_request_ctx(req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_request *subreq = &rctx->req; int refcnt = refcount_read(&ctx->refcnt); local_bh_disable(); skcipher_request_complete(req, err); local_bh_enable(); if (unlikely(err == -EINPROGRESS)) { subreq->base.complete = req->base.complete; subreq->base.data = req->base.data; req->base.complete = complete; req->base.data = req; } else if (refcnt && refcount_dec_and_test(&ctx->refcnt)) crypto_free_skcipher(tfm); } static void cryptd_skcipher_encrypt(void *data, int err) { struct skcipher_request *req = data; struct skcipher_request *subreq; subreq = cryptd_skcipher_prepare(req, err); if (likely(subreq)) err = crypto_skcipher_encrypt(subreq); cryptd_skcipher_complete(req, err, cryptd_skcipher_encrypt); } static void cryptd_skcipher_decrypt(void *data, int err) { struct skcipher_request *req = data; struct skcipher_request *subreq; subreq = cryptd_skcipher_prepare(req, err); if (likely(subreq)) err = crypto_skcipher_decrypt(subreq); cryptd_skcipher_complete(req, err, cryptd_skcipher_decrypt); } static int cryptd_skcipher_enqueue(struct skcipher_request *req, crypto_completion_t compl) { struct cryptd_skcipher_request_ctx *rctx = skcipher_request_ctx(req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_request *subreq = &rctx->req; struct cryptd_queue *queue; queue = cryptd_get_queue(crypto_skcipher_tfm(tfm)); subreq->base.complete = req->base.complete; subreq->base.data = req->base.data; req->base.complete = compl; req->base.data = req; return cryptd_enqueue_request(queue, &req->base); } static int cryptd_skcipher_encrypt_enqueue(struct skcipher_request *req) { return cryptd_skcipher_enqueue(req, cryptd_skcipher_encrypt); } static int cryptd_skcipher_decrypt_enqueue(struct skcipher_request *req) { return cryptd_skcipher_enqueue(req, cryptd_skcipher_decrypt); } static int cryptd_skcipher_init_tfm(struct crypto_skcipher *tfm) { struct skcipher_instance *inst = skcipher_alg_instance(tfm); struct skcipherd_instance_ctx *ictx = skcipher_instance_ctx(inst); struct crypto_skcipher_spawn *spawn = &ictx->spawn; struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct crypto_skcipher *cipher; cipher = crypto_spawn_skcipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; crypto_skcipher_set_reqsize( tfm, sizeof(struct cryptd_skcipher_request_ctx) + crypto_skcipher_reqsize(cipher)); return 0; } static void cryptd_skcipher_exit_tfm(struct crypto_skcipher *tfm) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); crypto_free_skcipher(ctx->child); } static void cryptd_skcipher_free(struct skcipher_instance *inst) { struct skcipherd_instance_ctx *ctx = skcipher_instance_ctx(inst); crypto_drop_skcipher(&ctx->spawn); kfree(inst); } static int cryptd_create_skcipher(struct crypto_template *tmpl, struct rtattr **tb, struct crypto_attr_type *algt, struct cryptd_queue *queue) { struct skcipherd_instance_ctx *ctx; struct skcipher_instance *inst; struct skcipher_alg_common *alg; u32 type; u32 mask; int err; cryptd_type_and_mask(algt, &type, &mask); inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL); if (!inst) return -ENOMEM; ctx = skcipher_instance_ctx(inst); ctx->queue = queue; err = crypto_grab_skcipher(&ctx->spawn, skcipher_crypto_instance(inst), crypto_attr_alg_name(tb[1]), type, mask); if (err) goto err_free_inst; alg = crypto_spawn_skcipher_alg_common(&ctx->spawn); err = cryptd_init_instance(skcipher_crypto_instance(inst), &alg->base); if (err) goto err_free_inst; inst->alg.base.cra_flags |= CRYPTO_ALG_ASYNC | (alg->base.cra_flags & CRYPTO_ALG_INTERNAL); inst->alg.ivsize = alg->ivsize; inst->alg.chunksize = alg->chunksize; inst->alg.min_keysize = alg->min_keysize; inst->alg.max_keysize = alg->max_keysize; inst->alg.base.cra_ctxsize = sizeof(struct cryptd_skcipher_ctx); inst->alg.init = cryptd_skcipher_init_tfm; inst->alg.exit = cryptd_skcipher_exit_tfm; inst->alg.setkey = cryptd_skcipher_setkey; inst->alg.encrypt = cryptd_skcipher_encrypt_enqueue; inst->alg.decrypt = cryptd_skcipher_decrypt_enqueue; inst->free = cryptd_skcipher_free; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: cryptd_skcipher_free(inst); } return err; } static int cryptd_hash_init_tfm(struct crypto_ahash *tfm) { struct ahash_instance *inst = ahash_alg_instance(tfm); struct hashd_instance_ctx *ictx = ahash_instance_ctx(inst); struct crypto_shash_spawn *spawn = &ictx->spawn; struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); struct crypto_shash *hash; hash = crypto_spawn_shash(spawn); if (IS_ERR(hash)) return PTR_ERR(hash); ctx->child = hash; crypto_ahash_set_reqsize(tfm, sizeof(struct cryptd_hash_request_ctx) + crypto_shash_descsize(hash)); return 0; } static int cryptd_hash_clone_tfm(struct crypto_ahash *ntfm, struct crypto_ahash *tfm) { struct cryptd_hash_ctx *nctx = crypto_ahash_ctx(ntfm); struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); struct crypto_shash *hash; hash = crypto_clone_shash(ctx->child); if (IS_ERR(hash)) return PTR_ERR(hash); nctx->child = hash; return 0; } static void cryptd_hash_exit_tfm(struct crypto_ahash *tfm) { struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); crypto_free_shash(ctx->child); } static int cryptd_hash_setkey(struct crypto_ahash *parent, const u8 *key, unsigned int keylen) { struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(parent); struct crypto_shash *child = ctx->child; crypto_shash_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_shash_set_flags(child, crypto_ahash_get_flags(parent) & CRYPTO_TFM_REQ_MASK); return crypto_shash_setkey(child, key, keylen); } static int cryptd_hash_enqueue(struct ahash_request *req, crypto_completion_t compl) { struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req); struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct cryptd_queue *queue = cryptd_get_queue(crypto_ahash_tfm(tfm)); rctx->complete = req->base.complete; rctx->data = req->base.data; req->base.complete = compl; req->base.data = req; return cryptd_enqueue_request(queue, &req->base); } static struct shash_desc *cryptd_hash_prepare(struct ahash_request *req, int err) { struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req); req->base.complete = rctx->complete; req->base.data = rctx->data; if (unlikely(err == -EINPROGRESS)) return NULL; return &rctx->desc; } static void cryptd_hash_complete(struct ahash_request *req, int err, crypto_completion_t complete) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); int refcnt = refcount_read(&ctx->refcnt); local_bh_disable(); ahash_request_complete(req, err); local_bh_enable(); if (err == -EINPROGRESS) { req->base.complete = complete; req->base.data = req; } else if (refcnt && refcount_dec_and_test(&ctx->refcnt)) crypto_free_ahash(tfm); } static void cryptd_hash_init(void *data, int err) { struct ahash_request *req = data; struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); struct crypto_shash *child = ctx->child; struct shash_desc *desc; desc = cryptd_hash_prepare(req, err); if (unlikely(!desc)) goto out; desc->tfm = child; err = crypto_shash_init(desc); out: cryptd_hash_complete(req, err, cryptd_hash_init); } static int cryptd_hash_init_enqueue(struct ahash_request *req) { return cryptd_hash_enqueue(req, cryptd_hash_init); } static void cryptd_hash_update(void *data, int err) { struct ahash_request *req = data; struct shash_desc *desc; desc = cryptd_hash_prepare(req, err); if (likely(desc)) err = shash_ahash_update(req, desc); cryptd_hash_complete(req, err, cryptd_hash_update); } static int cryptd_hash_update_enqueue(struct ahash_request *req) { return cryptd_hash_enqueue(req, cryptd_hash_update); } static void cryptd_hash_final(void *data, int err) { struct ahash_request *req = data; struct shash_desc *desc; desc = cryptd_hash_prepare(req, err); if (likely(desc)) err = crypto_shash_final(desc, req->result); cryptd_hash_complete(req, err, cryptd_hash_final); } static int cryptd_hash_final_enqueue(struct ahash_request *req) { return cryptd_hash_enqueue(req, cryptd_hash_final); } static void cryptd_hash_finup(void *data, int err) { struct ahash_request *req = data; struct shash_desc *desc; desc = cryptd_hash_prepare(req, err); if (likely(desc)) err = shash_ahash_finup(req, desc); cryptd_hash_complete(req, err, cryptd_hash_finup); } static int cryptd_hash_finup_enqueue(struct ahash_request *req) { return cryptd_hash_enqueue(req, cryptd_hash_finup); } static void cryptd_hash_digest(void *data, int err) { struct ahash_request *req = data; struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); struct crypto_shash *child = ctx->child; struct shash_desc *desc; desc = cryptd_hash_prepare(req, err); if (unlikely(!desc)) goto out; desc->tfm = child; err = shash_ahash_digest(req, desc); out: cryptd_hash_complete(req, err, cryptd_hash_digest); } static int cryptd_hash_digest_enqueue(struct ahash_request *req) { return cryptd_hash_enqueue(req, cryptd_hash_digest); } static int cryptd_hash_export(struct ahash_request *req, void *out) { struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req); return crypto_shash_export(&rctx->desc, out); } static int cryptd_hash_import(struct ahash_request *req, const void *in) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm); struct shash_desc *desc = cryptd_shash_desc(req); desc->tfm = ctx->child; return crypto_shash_import(desc, in); } static void cryptd_hash_free(struct ahash_instance *inst) { struct hashd_instance_ctx *ctx = ahash_instance_ctx(inst); crypto_drop_shash(&ctx->spawn); kfree(inst); } static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb, struct crypto_attr_type *algt, struct cryptd_queue *queue) { struct hashd_instance_ctx *ctx; struct ahash_instance *inst; struct shash_alg *alg; u32 type; u32 mask; int err; cryptd_type_and_mask(algt, &type, &mask); inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL); if (!inst) return -ENOMEM; ctx = ahash_instance_ctx(inst); ctx->queue = queue; err = crypto_grab_shash(&ctx->spawn, ahash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), type, mask); if (err) goto err_free_inst; alg = crypto_spawn_shash_alg(&ctx->spawn); err = cryptd_init_instance(ahash_crypto_instance(inst), &alg->base); if (err) goto err_free_inst; inst->alg.halg.base.cra_flags |= CRYPTO_ALG_ASYNC | (alg->base.cra_flags & (CRYPTO_ALG_INTERNAL| CRYPTO_ALG_OPTIONAL_KEY)); inst->alg.halg.digestsize = alg->digestsize; inst->alg.halg.statesize = alg->statesize; inst->alg.halg.base.cra_ctxsize = sizeof(struct cryptd_hash_ctx); inst->alg.init_tfm = cryptd_hash_init_tfm; inst->alg.clone_tfm = cryptd_hash_clone_tfm; inst->alg.exit_tfm = cryptd_hash_exit_tfm; inst->alg.init = cryptd_hash_init_enqueue; inst->alg.update = cryptd_hash_update_enqueue; inst->alg.final = cryptd_hash_final_enqueue; inst->alg.finup = cryptd_hash_finup_enqueue; inst->alg.export = cryptd_hash_export; inst->alg.import = cryptd_hash_import; if (crypto_shash_alg_has_setkey(alg)) inst->alg.setkey = cryptd_hash_setkey; inst->alg.digest = cryptd_hash_digest_enqueue; inst->free = cryptd_hash_free; err = ahash_register_instance(tmpl, inst); if (err) { err_free_inst: cryptd_hash_free(inst); } return err; } static int cryptd_aead_setkey(struct crypto_aead *parent, const u8 *key, unsigned int keylen) { struct cryptd_aead_ctx *ctx = crypto_aead_ctx(parent); struct crypto_aead *child = ctx->child; return crypto_aead_setkey(child, key, keylen); } static int cryptd_aead_setauthsize(struct crypto_aead *parent, unsigned int authsize) { struct cryptd_aead_ctx *ctx = crypto_aead_ctx(parent); struct crypto_aead *child = ctx->child; return crypto_aead_setauthsize(child, authsize); } static void cryptd_aead_crypt(struct aead_request *req, struct crypto_aead *child, int err, int (*crypt)(struct aead_request *req), crypto_completion_t compl) { struct cryptd_aead_request_ctx *rctx; struct aead_request *subreq; struct cryptd_aead_ctx *ctx; struct crypto_aead *tfm; int refcnt; rctx = aead_request_ctx(req); subreq = &rctx->req; req->base.complete = subreq->base.complete; req->base.data = subreq->base.data; tfm = crypto_aead_reqtfm(req); if (unlikely(err == -EINPROGRESS)) goto out; aead_request_set_tfm(subreq, child); aead_request_set_callback(subreq, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, req->iv); aead_request_set_ad(subreq, req->assoclen); err = crypt(subreq); out: ctx = crypto_aead_ctx(tfm); refcnt = refcount_read(&ctx->refcnt); local_bh_disable(); aead_request_complete(req, err); local_bh_enable(); if (err == -EINPROGRESS) { subreq->base.complete = req->base.complete; subreq->base.data = req->base.data; req->base.complete = compl; req->base.data = req; } else if (refcnt && refcount_dec_and_test(&ctx->refcnt)) crypto_free_aead(tfm); } static void cryptd_aead_encrypt(void *data, int err) { struct aead_request *req = data; struct cryptd_aead_ctx *ctx; struct crypto_aead *child; ctx = crypto_aead_ctx(crypto_aead_reqtfm(req)); child = ctx->child; cryptd_aead_crypt(req, child, err, crypto_aead_alg(child)->encrypt, cryptd_aead_encrypt); } static void cryptd_aead_decrypt(void *data, int err) { struct aead_request *req = data; struct cryptd_aead_ctx *ctx; struct crypto_aead *child; ctx = crypto_aead_ctx(crypto_aead_reqtfm(req)); child = ctx->child; cryptd_aead_crypt(req, child, err, crypto_aead_alg(child)->decrypt, cryptd_aead_decrypt); } static int cryptd_aead_enqueue(struct aead_request *req, crypto_completion_t compl) { struct cryptd_aead_request_ctx *rctx = aead_request_ctx(req); struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct cryptd_queue *queue = cryptd_get_queue(crypto_aead_tfm(tfm)); struct aead_request *subreq = &rctx->req; subreq->base.complete = req->base.complete; subreq->base.data = req->base.data; req->base.complete = compl; req->base.data = req; return cryptd_enqueue_request(queue, &req->base); } static int cryptd_aead_encrypt_enqueue(struct aead_request *req) { return cryptd_aead_enqueue(req, cryptd_aead_encrypt ); } static int cryptd_aead_decrypt_enqueue(struct aead_request *req) { return cryptd_aead_enqueue(req, cryptd_aead_decrypt ); } static int cryptd_aead_init_tfm(struct crypto_aead *tfm) { struct aead_instance *inst = aead_alg_instance(tfm); struct aead_instance_ctx *ictx = aead_instance_ctx(inst); struct crypto_aead_spawn *spawn = &ictx->aead_spawn; struct cryptd_aead_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_aead *cipher; cipher = crypto_spawn_aead(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; crypto_aead_set_reqsize( tfm, sizeof(struct cryptd_aead_request_ctx) + crypto_aead_reqsize(cipher)); return 0; } static void cryptd_aead_exit_tfm(struct crypto_aead *tfm) { struct cryptd_aead_ctx *ctx = crypto_aead_ctx(tfm); crypto_free_aead(ctx->child); } static void cryptd_aead_free(struct aead_instance *inst) { struct aead_instance_ctx *ctx = aead_instance_ctx(inst); crypto_drop_aead(&ctx->aead_spawn); kfree(inst); } static int cryptd_create_aead(struct crypto_template *tmpl, struct rtattr **tb, struct crypto_attr_type *algt, struct cryptd_queue *queue) { struct aead_instance_ctx *ctx; struct aead_instance *inst; struct aead_alg *alg; u32 type; u32 mask; int err; cryptd_type_and_mask(algt, &type, &mask); inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL); if (!inst) return -ENOMEM; ctx = aead_instance_ctx(inst); ctx->queue = queue; err = crypto_grab_aead(&ctx->aead_spawn, aead_crypto_instance(inst), crypto_attr_alg_name(tb[1]), type, mask); if (err) goto err_free_inst; alg = crypto_spawn_aead_alg(&ctx->aead_spawn); err = cryptd_init_instance(aead_crypto_instance(inst), &alg->base); if (err) goto err_free_inst; inst->alg.base.cra_flags |= CRYPTO_ALG_ASYNC | (alg->base.cra_flags & CRYPTO_ALG_INTERNAL); inst->alg.base.cra_ctxsize = sizeof(struct cryptd_aead_ctx); inst->alg.ivsize = crypto_aead_alg_ivsize(alg); inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg); inst->alg.init = cryptd_aead_init_tfm; inst->alg.exit = cryptd_aead_exit_tfm; inst->alg.setkey = cryptd_aead_setkey; inst->alg.setauthsize = cryptd_aead_setauthsize; inst->alg.encrypt = cryptd_aead_encrypt_enqueue; inst->alg.decrypt = cryptd_aead_decrypt_enqueue; inst->free = cryptd_aead_free; err = aead_register_instance(tmpl, inst); if (err) { err_free_inst: cryptd_aead_free(inst); } return err; } static struct cryptd_queue queue; static int cryptd_create(struct crypto_template *tmpl, struct rtattr **tb) { struct crypto_attr_type *algt; algt = crypto_get_attr_type(tb); if (IS_ERR(algt)) return PTR_ERR(algt); switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) { case CRYPTO_ALG_TYPE_LSKCIPHER: return cryptd_create_skcipher(tmpl, tb, algt, &queue); case CRYPTO_ALG_TYPE_HASH: return cryptd_create_hash(tmpl, tb, algt, &queue); case CRYPTO_ALG_TYPE_AEAD: return cryptd_create_aead(tmpl, tb, algt, &queue); } return -EINVAL; } static struct crypto_template cryptd_tmpl = { .name = "cryptd", .create = cryptd_create, .module = THIS_MODULE, }; struct cryptd_skcipher *cryptd_alloc_skcipher(const char *alg_name, u32 type, u32 mask) { char cryptd_alg_name[CRYPTO_MAX_ALG_NAME]; struct cryptd_skcipher_ctx *ctx; struct crypto_skcipher *tfm; if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME, "cryptd(%s)", alg_name) >= CRYPTO_MAX_ALG_NAME) return ERR_PTR(-EINVAL); tfm = crypto_alloc_skcipher(cryptd_alg_name, type, mask); if (IS_ERR(tfm)) return ERR_CAST(tfm); if (tfm->base.__crt_alg->cra_module != THIS_MODULE) { crypto_free_skcipher(tfm); return ERR_PTR(-EINVAL); } ctx = crypto_skcipher_ctx(tfm); refcount_set(&ctx->refcnt, 1); return container_of(tfm, struct cryptd_skcipher, base); } EXPORT_SYMBOL_GPL(cryptd_alloc_skcipher); struct crypto_skcipher *cryptd_skcipher_child(struct cryptd_skcipher *tfm) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(&tfm->base); return ctx->child; } EXPORT_SYMBOL_GPL(cryptd_skcipher_child); bool cryptd_skcipher_queued(struct cryptd_skcipher *tfm) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(&tfm->base); return refcount_read(&ctx->refcnt) - 1; } EXPORT_SYMBOL_GPL(cryptd_skcipher_queued); void cryptd_free_skcipher(struct cryptd_skcipher *tfm) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(&tfm->base); if (refcount_dec_and_test(&ctx->refcnt)) crypto_free_skcipher(&tfm->base); } EXPORT_SYMBOL_GPL(cryptd_free_skcipher); struct cryptd_ahash *cryptd_alloc_ahash(const char *alg_name, u32 type, u32 mask) { char cryptd_alg_name[CRYPTO_MAX_ALG_NAME]; struct cryptd_hash_ctx *ctx; struct crypto_ahash *tfm; if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME, "cryptd(%s)", alg_name) >= CRYPTO_MAX_ALG_NAME) return ERR_PTR(-EINVAL); tfm = crypto_alloc_ahash(cryptd_alg_name, type, mask); if (IS_ERR(tfm)) return ERR_CAST(tfm); if (tfm->base.__crt_alg->cra_module != THIS_MODULE) { crypto_free_ahash(tfm); return ERR_PTR(-EINVAL); } ctx = crypto_ahash_ctx(tfm); refcount_set(&ctx->refcnt, 1); return __cryptd_ahash_cast(tfm); } EXPORT_SYMBOL_GPL(cryptd_alloc_ahash); struct crypto_shash *cryptd_ahash_child(struct cryptd_ahash *tfm) { struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base); return ctx->child; } EXPORT_SYMBOL_GPL(cryptd_ahash_child); struct shash_desc *cryptd_shash_desc(struct ahash_request *req) { struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req); return &rctx->desc; } EXPORT_SYMBOL_GPL(cryptd_shash_desc); bool cryptd_ahash_queued(struct cryptd_ahash *tfm) { struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base); return refcount_read(&ctx->refcnt) - 1; } EXPORT_SYMBOL_GPL(cryptd_ahash_queued); void cryptd_free_ahash(struct cryptd_ahash *tfm) { struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base); if (refcount_dec_and_test(&ctx->refcnt)) crypto_free_ahash(&tfm->base); } EXPORT_SYMBOL_GPL(cryptd_free_ahash); struct cryptd_aead *cryptd_alloc_aead(const char *alg_name, u32 type, u32 mask) { char cryptd_alg_name[CRYPTO_MAX_ALG_NAME]; struct cryptd_aead_ctx *ctx; struct crypto_aead *tfm; if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME, "cryptd(%s)", alg_name) >= CRYPTO_MAX_ALG_NAME) return ERR_PTR(-EINVAL); tfm = crypto_alloc_aead(cryptd_alg_name, type, mask); if (IS_ERR(tfm)) return ERR_CAST(tfm); if (tfm->base.__crt_alg->cra_module != THIS_MODULE) { crypto_free_aead(tfm); return ERR_PTR(-EINVAL); } ctx = crypto_aead_ctx(tfm); refcount_set(&ctx->refcnt, 1); return __cryptd_aead_cast(tfm); } EXPORT_SYMBOL_GPL(cryptd_alloc_aead); struct crypto_aead *cryptd_aead_child(struct cryptd_aead *tfm) { struct cryptd_aead_ctx *ctx; ctx = crypto_aead_ctx(&tfm->base); return ctx->child; } EXPORT_SYMBOL_GPL(cryptd_aead_child); bool cryptd_aead_queued(struct cryptd_aead *tfm) { struct cryptd_aead_ctx *ctx = crypto_aead_ctx(&tfm->base); return refcount_read(&ctx->refcnt) - 1; } EXPORT_SYMBOL_GPL(cryptd_aead_queued); void cryptd_free_aead(struct cryptd_aead *tfm) { struct cryptd_aead_ctx *ctx = crypto_aead_ctx(&tfm->base); if (refcount_dec_and_test(&ctx->refcnt)) crypto_free_aead(&tfm->base); } EXPORT_SYMBOL_GPL(cryptd_free_aead); static int __init cryptd_init(void) { int err; cryptd_wq = alloc_workqueue("cryptd", WQ_MEM_RECLAIM | WQ_CPU_INTENSIVE | WQ_PERCPU, 1); if (!cryptd_wq) return -ENOMEM; err = cryptd_init_queue(&queue, cryptd_max_cpu_qlen); if (err) goto err_destroy_wq; err = crypto_register_template(&cryptd_tmpl); if (err) goto err_fini_queue; return 0; err_fini_queue: cryptd_fini_queue(&queue); err_destroy_wq: destroy_workqueue(cryptd_wq); return err; } static void __exit cryptd_exit(void) { destroy_workqueue(cryptd_wq); cryptd_fini_queue(&queue); crypto_unregister_template(&cryptd_tmpl); } module_init(cryptd_init); module_exit(cryptd_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Software async crypto daemon"); MODULE_ALIAS_CRYPTO("cryptd"); |
| 31 18 18 21 21 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 | // SPDX-License-Identifier: GPL-2.0 /* * Coherent per-device memory handling. * Borrowed from i386 */ #include <linux/io.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> struct dma_coherent_mem { void *virt_base; dma_addr_t device_base; unsigned long pfn_base; int size; unsigned long *bitmap; spinlock_t spinlock; bool use_dev_dma_pfn_offset; }; static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev) { if (dev && dev->dma_mem) return dev->dma_mem; return NULL; } static inline dma_addr_t dma_get_device_base(struct device *dev, struct dma_coherent_mem * mem) { if (mem->use_dev_dma_pfn_offset) return phys_to_dma(dev, PFN_PHYS(mem->pfn_base)); return mem->device_base; } static struct dma_coherent_mem *dma_init_coherent_memory(phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, bool use_dma_pfn_offset) { struct dma_coherent_mem *dma_mem; int pages = size >> PAGE_SHIFT; void *mem_base; if (!size) return ERR_PTR(-EINVAL); mem_base = memremap(phys_addr, size, MEMREMAP_WC); if (!mem_base) return ERR_PTR(-EINVAL); dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); if (!dma_mem) goto out_unmap_membase; dma_mem->bitmap = bitmap_zalloc(pages, GFP_KERNEL); if (!dma_mem->bitmap) goto out_free_dma_mem; dma_mem->virt_base = mem_base; dma_mem->device_base = device_addr; dma_mem->pfn_base = PFN_DOWN(phys_addr); dma_mem->size = pages; dma_mem->use_dev_dma_pfn_offset = use_dma_pfn_offset; spin_lock_init(&dma_mem->spinlock); return dma_mem; out_free_dma_mem: kfree(dma_mem); out_unmap_membase: memunmap(mem_base); pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %zd MiB\n", &phys_addr, size / SZ_1M); return ERR_PTR(-ENOMEM); } static void _dma_release_coherent_memory(struct dma_coherent_mem *mem) { if (!mem) return; memunmap(mem->virt_base); bitmap_free(mem->bitmap); kfree(mem); } static int dma_assign_coherent_memory(struct device *dev, struct dma_coherent_mem *mem) { if (!dev) return -ENODEV; if (dev->dma_mem) return -EBUSY; dev->dma_mem = mem; return 0; } /* * Declare a region of memory to be handed out by dma_alloc_coherent() when it * is asked for coherent memory for this device. This shall only be used * from platform code, usually based on the device tree description. * * phys_addr is the CPU physical address to which the memory is currently * assigned (this will be ioremapped so the CPU can access the region). * * device_addr is the DMA address the device needs to be programmed with to * actually address this memory (this will be handed out as the dma_addr_t in * dma_alloc_coherent()). * * size is the size of the area (must be a multiple of PAGE_SIZE). * * As a simplification for the platforms, only *one* such region of memory may * be declared per device. */ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size) { struct dma_coherent_mem *mem; int ret; mem = dma_init_coherent_memory(phys_addr, device_addr, size, false); if (IS_ERR(mem)) return PTR_ERR(mem); ret = dma_assign_coherent_memory(dev, mem); if (ret) _dma_release_coherent_memory(mem); return ret; } void dma_release_coherent_memory(struct device *dev) { if (dev) { _dma_release_coherent_memory(dev->dma_mem); dev->dma_mem = NULL; } } static void *__dma_alloc_from_coherent(struct device *dev, struct dma_coherent_mem *mem, ssize_t size, dma_addr_t *dma_handle) { int order = get_order(size); unsigned long flags; int pageno; void *ret; spin_lock_irqsave(&mem->spinlock, flags); if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT))) goto err; pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); if (unlikely(pageno < 0)) goto err; /* * Memory was found in the coherent area. */ *dma_handle = dma_get_device_base(dev, mem) + ((dma_addr_t)pageno << PAGE_SHIFT); ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT); spin_unlock_irqrestore(&mem->spinlock, flags); memset(ret, 0, size); return ret; err: spin_unlock_irqrestore(&mem->spinlock, flags); return NULL; } /** * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool * @dev: device from which we allocate memory * @size: size of requested memory area * @dma_handle: This will be filled with the correct dma handle * @ret: This pointer will be filled with the virtual address * to allocated area. * * This function should be only called from per-arch dma_alloc_coherent() * to support allocation from per-device coherent memory pools. * * Returns 0 if dma_alloc_coherent should continue with allocating from * generic memory areas, or !0 if dma_alloc_coherent should return @ret. */ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret) { struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); if (!mem) return 0; *ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle); return 1; } static int __dma_release_from_coherent(struct dma_coherent_mem *mem, int order, void *vaddr) { if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; unsigned long flags; spin_lock_irqsave(&mem->spinlock, flags); bitmap_release_region(mem->bitmap, page, order); spin_unlock_irqrestore(&mem->spinlock, flags); return 1; } return 0; } /** * dma_release_from_dev_coherent() - free memory to device coherent memory pool * @dev: device from which the memory was allocated * @order: the order of pages allocated * @vaddr: virtual address of allocated pages * * This checks whether the memory was allocated from the per-device * coherent memory pool and if so, releases that memory. * * Returns 1 if we correctly released the memory, or 0 if the caller should * proceed with releasing memory from generic pools. */ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr) { struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); return __dma_release_from_coherent(mem, order, vaddr); } static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem, struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { if (mem && vaddr >= mem->virt_base && vaddr + size <= (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { unsigned long off = vma->vm_pgoff; int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; unsigned long user_count = vma_pages(vma); int count = PAGE_ALIGN(size) >> PAGE_SHIFT; *ret = -ENXIO; if (off < count && user_count <= count - off) { unsigned long pfn = mem->pfn_base + start + off; *ret = remap_pfn_range(vma, vma->vm_start, pfn, user_count << PAGE_SHIFT, vma->vm_page_prot); } return 1; } return 0; } /** * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool * @dev: device from which the memory was allocated * @vma: vm_area for the userspace memory * @vaddr: cpu address returned by dma_alloc_from_dev_coherent * @size: size of the memory buffer allocated * @ret: result from remap_pfn_range() * * This checks whether the memory was allocated from the per-device * coherent memory pool and if so, maps that memory to the provided vma. * * Returns 1 if @vaddr belongs to the device coherent pool and the caller * should return @ret, or 0 if they should proceed with mapping memory from * generic areas. */ int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret); } #ifdef CONFIG_DMA_GLOBAL_POOL static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init; void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle) { if (!dma_coherent_default_memory) return NULL; return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, dma_handle); } int dma_release_from_global_coherent(int order, void *vaddr) { if (!dma_coherent_default_memory) return 0; return __dma_release_from_coherent(dma_coherent_default_memory, order, vaddr); } int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { if (!dma_coherent_default_memory) return 0; return __dma_mmap_from_coherent(dma_coherent_default_memory, vma, vaddr, size, ret); } int dma_init_global_coherent(phys_addr_t phys_addr, size_t size) { struct dma_coherent_mem *mem; mem = dma_init_coherent_memory(phys_addr, phys_addr, size, true); if (IS_ERR(mem)) return PTR_ERR(mem); dma_coherent_default_memory = mem; pr_info("DMA: default coherent area is set\n"); return 0; } #endif /* CONFIG_DMA_GLOBAL_POOL */ /* * Support for reserved memory regions defined in device tree */ #ifdef CONFIG_OF_RESERVED_MEM #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_reserved_mem.h> #ifdef CONFIG_DMA_GLOBAL_POOL static phys_addr_t dma_reserved_default_memory_base __initdata; static phys_addr_t dma_reserved_default_memory_size __initdata; #endif static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) { struct dma_coherent_mem *mem = rmem->priv; if (!mem) { mem = dma_init_coherent_memory(rmem->base, rmem->base, rmem->size, true); if (IS_ERR(mem)) return PTR_ERR(mem); rmem->priv = mem; } /* Warn if the device potentially can't use the reserved memory */ if (mem->device_base + rmem->size - 1 > min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit)) dev_warn(dev, "reserved memory is beyond device's set DMA address range\n"); dma_assign_coherent_memory(dev, mem); return 0; } static void rmem_dma_device_release(struct reserved_mem *rmem, struct device *dev) { if (dev) dev->dma_mem = NULL; } static const struct reserved_mem_ops rmem_dma_ops = { .device_init = rmem_dma_device_init, .device_release = rmem_dma_device_release, }; static int __init rmem_dma_setup(struct reserved_mem *rmem) { unsigned long node = rmem->fdt_node; if (of_get_flat_dt_prop(node, "reusable", NULL)) return -EINVAL; #ifdef CONFIG_ARM if (!of_get_flat_dt_prop(node, "no-map", NULL)) { pr_err("Reserved memory: regions without no-map are not yet supported\n"); return -EINVAL; } #endif #ifdef CONFIG_DMA_GLOBAL_POOL if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) { WARN(dma_reserved_default_memory_size, "Reserved memory: region for default DMA coherent area is redefined\n"); dma_reserved_default_memory_base = rmem->base; dma_reserved_default_memory_size = rmem->size; } #endif rmem->ops = &rmem_dma_ops; pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n", &rmem->base, (unsigned long)rmem->size / SZ_1M); return 0; } #ifdef CONFIG_DMA_GLOBAL_POOL static int __init dma_init_reserved_memory(void) { if (!dma_reserved_default_memory_size) return -ENOMEM; return dma_init_global_coherent(dma_reserved_default_memory_base, dma_reserved_default_memory_size); } core_initcall(dma_init_reserved_memory); #endif /* CONFIG_DMA_GLOBAL_POOL */ RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup); #endif |
| 52 52 52 52 52 52 52 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 | // SPDX-License-Identifier: GPL-2.0-only /* * HT handling * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018 - 2024 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "wme.h" /** * DOC: TX A-MPDU aggregation * * Aggregation on the TX side requires setting the hardware flag * %IEEE80211_HW_AMPDU_AGGREGATION. The driver will then be handed * packets with a flag indicating A-MPDU aggregation. The driver * or device is responsible for actually aggregating the frames, * as well as deciding how many and which to aggregate. * * When TX aggregation is started by some subsystem (usually the rate * control algorithm would be appropriate) by calling the * ieee80211_start_tx_ba_session() function, the driver will be * notified via its @ampdu_action function, with the * %IEEE80211_AMPDU_TX_START action. * * In response to that, the driver is later required to call the * ieee80211_start_tx_ba_cb_irqsafe() function, which will really * start the aggregation session after the peer has also responded. * If the peer responds negatively, the session will be stopped * again right away. Note that it is possible for the aggregation * session to be stopped before the driver has indicated that it * is done setting it up, in which case it must not indicate the * setup completion. * * Also note that, since we also need to wait for a response from * the peer, the driver is notified of the completion of the * handshake by the %IEEE80211_AMPDU_TX_OPERATIONAL action to the * @ampdu_action callback. * * Similarly, when the aggregation session is stopped by the peer * or something calling ieee80211_stop_tx_ba_session(), the driver's * @ampdu_action function will be called with the action * %IEEE80211_AMPDU_TX_STOP. In this case, the call must not fail, * and the driver must later call ieee80211_stop_tx_ba_cb_irqsafe(). * Note that the sta can get destroyed before the BA tear down is * complete. */ static void ieee80211_send_addba_request(struct sta_info *sta, u16 tid, u8 dialog_token, u16 start_seq_num, u16 agg_size, u16 timeout) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u16 capab; skb = dev_alloc_skb(sizeof(*mgmt) + 2 + sizeof(struct ieee80211_addba_ext_ie) + local->hw.extra_tx_headroom); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = ieee80211_mgmt_ba(skb, sta->sta.addr, sdata); skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_req)); mgmt->u.action.category = WLAN_CATEGORY_BACK; mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ; mgmt->u.action.u.addba_req.dialog_token = dialog_token; capab = IEEE80211_ADDBA_PARAM_AMSDU_MASK; capab |= IEEE80211_ADDBA_PARAM_POLICY_MASK; capab |= u16_encode_bits(tid, IEEE80211_ADDBA_PARAM_TID_MASK); capab |= u16_encode_bits(agg_size, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK); mgmt->u.action.u.addba_req.capab = cpu_to_le16(capab); mgmt->u.action.u.addba_req.timeout = cpu_to_le16(timeout); mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4); if (sta->sta.deflink.he_cap.has_he) ieee80211_add_addbaext(skb, 0, agg_size); ieee80211_tx_skb_tid(sdata, skb, tid, -1); } void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_bar *bar; u16 bar_control = 0; skb = dev_alloc_skb(sizeof(*bar) + local->hw.extra_tx_headroom); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); bar = skb_put_zero(skb, sizeof(*bar)); bar->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); memcpy(bar->ra, ra, ETH_ALEN); memcpy(bar->ta, sdata->vif.addr, ETH_ALEN); bar_control |= (u16)IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL; bar_control |= (u16)IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA; bar_control |= (u16)(tid << IEEE80211_BAR_CTRL_TID_INFO_SHIFT); bar->control = cpu_to_le16(bar_control); bar->start_seq_num = cpu_to_le16(ssn); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_REQ_TX_STATUS; ieee80211_tx_skb_tid(sdata, skb, tid, -1); } EXPORT_SYMBOL(ieee80211_send_bar); void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) { lockdep_assert_wiphy(sta->local->hw.wiphy); lockdep_assert_held(&sta->lock); rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], tid_tx); } /* * When multiple aggregation sessions on multiple stations * are being created/destroyed simultaneously, we need to * refcount the global queue stop caused by that in order * to not get into a situation where one of the aggregation * setup or teardown re-enables queues before the other is * ready to handle that. * * These two functions take care of this issue by keeping * a global "agg_queue_stop" refcount. */ static void __acquires(agg_queue) ieee80211_stop_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; /* we do refcounting here, so don't use the queue reason refcounting */ if (atomic_inc_return(&sdata->local->agg_queue_stop[queue]) == 1) ieee80211_stop_queue_by_reason( &sdata->local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION, false); __acquire(agg_queue); } static void __releases(agg_queue) ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; if (atomic_dec_return(&sdata->local->agg_queue_stop[queue]) == 0) ieee80211_wake_queue_by_reason( &sdata->local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION, false); __release(agg_queue); } static void ieee80211_agg_stop_txq(struct sta_info *sta, int tid) { struct ieee80211_txq *txq = sta->sta.txq[tid]; struct ieee80211_sub_if_data *sdata; struct fq *fq; struct txq_info *txqi; if (!txq) return; txqi = to_txq_info(txq); sdata = vif_to_sdata(txq->vif); fq = &sdata->local->fq; /* Lock here to protect against further seqno updates on dequeue */ spin_lock_bh(&fq->lock); set_bit(IEEE80211_TXQ_STOP, &txqi->flags); spin_unlock_bh(&fq->lock); } static void ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) { struct ieee80211_txq *txq = sta->sta.txq[tid]; struct txq_info *txqi; lockdep_assert_wiphy(sta->local->hw.wiphy); if (!txq) return; txqi = to_txq_info(txq); if (enable) set_bit(IEEE80211_TXQ_AMPDU, &txqi->flags); else clear_bit(IEEE80211_TXQ_AMPDU, &txqi->flags); clear_bit(IEEE80211_TXQ_STOP, &txqi->flags); local_bh_disable(); rcu_read_lock(); schedule_and_wake_txq(sta->sdata->local, txqi); rcu_read_unlock(); local_bh_enable(); } /* * splice packets from the STA's pending to the local pending, * requires a call to ieee80211_agg_splice_finish later */ static void __acquires(agg_queue) ieee80211_agg_splice_packets(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx, u16 tid) { struct ieee80211_local *local = sdata->local; int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; unsigned long flags; ieee80211_stop_queue_agg(sdata, tid); if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates from the pending queue\n", tid)) return; if (!skb_queue_empty(&tid_tx->pending)) { spin_lock_irqsave(&local->queue_stop_reason_lock, flags); /* copy over remaining packets */ skb_queue_splice_tail_init(&tid_tx->pending, &local->pending[queue]); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } } static void __releases(agg_queue) ieee80211_agg_splice_finish(struct ieee80211_sub_if_data *sdata, u16 tid) { ieee80211_wake_queue_agg(sdata, tid); } static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; lockdep_assert_wiphy(sta->local->hw.wiphy); lockdep_assert_held(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* * When we get here, the TX path will not be lockless any more wrt. * aggregation, since the OPERATIONAL bit has long been cleared. * Thus it will block on getting the lock, if it occurs. So if we * stop the queue now, we will not get any more packets, and any * that might be being processed will wait for us here, thereby * guaranteeing that no packets go to the tid_tx pending queue any * more. */ ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); /* future packets must not find the tid_tx struct any more */ ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sta->sdata, tid); kfree_rcu(tid_tx, rcu_head); } int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_agg_stop_reason reason) { struct ieee80211_local *local = sta->local; struct tid_ampdu_tx *tid_tx; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .tid = tid, .buf_size = 0, .amsdu = false, .timeout = 0, .ssn = 0, }; int ret; lockdep_assert_wiphy(sta->local->hw.wiphy); switch (reason) { case AGG_STOP_DECLINED: case AGG_STOP_LOCAL_REQUEST: case AGG_STOP_PEER_REQUEST: params.action = IEEE80211_AMPDU_TX_STOP_CONT; break; case AGG_STOP_DESTROY_STA: params.action = IEEE80211_AMPDU_TX_STOP_FLUSH; break; default: WARN_ON_ONCE(1); return -EINVAL; } spin_lock_bh(&sta->lock); /* free struct pending for start, if present */ tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; kfree(tid_tx); sta->ampdu_mlme.tid_start_tx[tid] = NULL; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) { spin_unlock_bh(&sta->lock); return -ENOENT; } /* * if we're already stopping ignore any new requests to stop * unless we're destroying it in which case notify the driver */ if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { spin_unlock_bh(&sta->lock); if (reason != AGG_STOP_DESTROY_STA) return -EALREADY; params.action = IEEE80211_AMPDU_TX_STOP_FLUSH_CONT; ret = drv_ampdu_action(local, sta->sdata, ¶ms); WARN_ON_ONCE(ret); return 0; } if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { /* not even started yet! */ ieee80211_assign_tid_tx(sta, tid, NULL); spin_unlock_bh(&sta->lock); kfree_rcu(tid_tx, rcu_head); return 0; } set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); ieee80211_agg_stop_txq(sta, tid); spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", sta->sta.addr, tid); timer_delete_sync(&tid_tx->addba_resp_timer); timer_delete_sync(&tid_tx->session_timer); /* * After this packets are no longer handed right through * to the driver but are put onto tid_tx->pending instead, * with locking to ensure proper access. */ clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); /* * There might be a few packets being processed right now (on * another CPU) that have already gotten past the aggregation * check when it was still OPERATIONAL and consequently have * IEEE80211_TX_CTL_AMPDU set. In that case, this code might * call into the driver at the same time or even before the * TX paths calls into it, which could confuse the driver. * * Wait for all currently running TX paths to finish before * telling the driver. New packets will not go through since * the aggregation session is no longer OPERATIONAL. */ if (!local->in_reconfig) synchronize_net(); tid_tx->stop_initiator = reason == AGG_STOP_PEER_REQUEST ? WLAN_BACK_RECIPIENT : WLAN_BACK_INITIATOR; tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST; ret = drv_ampdu_action(local, sta->sdata, ¶ms); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { /* * We may have pending packets get stuck in this case... * Not bothering with a workaround for now. */ } /* * In the case of AGG_STOP_DESTROY_STA, the driver won't * necessarily call ieee80211_stop_tx_ba_cb(), so this may * seem like we can leave the tid_tx data pending forever. * This is true, in a way, but "forever" is only until the * station struct is actually destroyed. In the meantime, * leaving it around ensures that we don't transmit packets * to the driver on this TID which might confuse it. */ return 0; } /* * After sending add Block Ack request we activated a timer until * add Block Ack response will arrive from the recipient. * If this timer expires sta_addba_resp_timer_expired will be executed. */ static void sta_addba_resp_timer_expired(struct timer_list *t) { struct tid_ampdu_tx *tid_tx = timer_container_of(tid_tx, t, addba_resp_timer); struct sta_info *sta = tid_tx->sta; u8 tid = tid_tx->tid; /* check if the TID waits for addBA response */ if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { ht_dbg(sta->sdata, "timer expired on %pM tid %d not expecting addBA response\n", sta->sta.addr, tid); return; } ht_dbg(sta->sdata, "addBA response timer expired on %pM tid %d\n", sta->sta.addr, tid); ieee80211_stop_tx_ba_session(&sta->sta, tid); } static void ieee80211_send_addba_with_timeout(struct sta_info *sta, struct tid_ampdu_tx *tid_tx) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sta->local; u8 tid = tid_tx->tid; u16 buf_size; if (WARN_ON_ONCE(test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state) || test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state))) return; lockdep_assert_wiphy(sta->local->hw.wiphy); /* activate the timer for the recipient's addBA response */ mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL); ht_dbg(sdata, "activated addBA response timer on %pM tid %d\n", sta->sta.addr, tid); spin_lock_bh(&sta->lock); sta->ampdu_mlme.last_addba_req_time[tid] = jiffies; sta->ampdu_mlme.addba_req_num[tid]++; spin_unlock_bh(&sta->lock); if (sta->sta.valid_links || sta->sta.deflink.eht_cap.has_eht || ieee80211_hw_check(&local->hw, STRICT)) { buf_size = local->hw.max_tx_aggregation_subframes; } else if (sta->sta.deflink.he_cap.has_he) { buf_size = min_t(u16, local->hw.max_tx_aggregation_subframes, IEEE80211_MAX_AMPDU_BUF_HE); } else { /* * We really should use what the driver told us it will * transmit as the maximum, but certain APs (e.g. the * LinkSys WRT120N with FW v1.0.07 build 002 Jun 18 2012) * will crash when we use a lower number. */ buf_size = IEEE80211_MAX_AMPDU_BUF_HT; } /* send AddBA request */ ieee80211_send_addba_request(sta, tid, tid_tx->dialog_token, tid_tx->ssn, buf_size, tid_tx->timeout); WARN_ON(test_and_set_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)); } void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_START, .tid = tid, .buf_size = 0, .amsdu = false, .timeout = 0, }; int ret; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* * Start queuing up packets for this aggregation session. * We're going to release them once the driver is OK with * that. */ clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); /* * Make sure no packets are being processed. This ensures that * we have a valid starting sequence number and that in-flight * packets have been flushed out and no packets for this TID * will go into the driver during the ampdu_action call. */ synchronize_net(); params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); tid_tx->ssn = params.ssn; if (ret == IEEE80211_AMPDU_TX_START_DELAY_ADDBA) { return; } else if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) { /* * We didn't send the request yet, so don't need to check * here if we already got a response, just mark as driver * ready immediately. */ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state); } else if (ret) { ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", sta->sta.addr, tid); spin_lock_bh(&sta->lock); ieee80211_agg_splice_packets(sdata, tid_tx, tid); ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sdata, tid); spin_unlock_bh(&sta->lock); ieee80211_agg_start_txq(sta, tid, false); kfree_rcu(tid_tx, rcu_head); return; } ieee80211_send_addba_with_timeout(sta, tid_tx); } void ieee80211_refresh_tx_agg_session_timer(struct ieee80211_sta *pubsta, u16 tid) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct tid_ampdu_tx *tid_tx; if (WARN_ON_ONCE(tid >= IEEE80211_NUM_TIDS)) return; tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); if (!tid_tx) return; tid_tx->last_tx = jiffies; } EXPORT_SYMBOL(ieee80211_refresh_tx_agg_session_timer); /* * After accepting the AddBA Response we activated a timer, * resetting it after each frame that we send. */ static void sta_tx_agg_session_timer_expired(struct timer_list *t) { struct tid_ampdu_tx *tid_tx = timer_container_of(tid_tx, t, session_timer); struct sta_info *sta = tid_tx->sta; u8 tid = tid_tx->tid; unsigned long timeout; if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { return; } timeout = tid_tx->last_tx + TU_TO_JIFFIES(tid_tx->timeout); if (time_is_after_jiffies(timeout)) { mod_timer(&tid_tx->session_timer, timeout); return; } ht_dbg(sta->sdata, "tx session timer expired on %pM tid %d\n", sta->sta.addr, tid); ieee80211_stop_tx_ba_session(&sta->sta, tid); } int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, u16 timeout) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; int ret = 0; trace_api_start_tx_ba_session(pubsta, tid); if (WARN(sta->reserved_tid == tid, "Requested to start BA session on reserved tid=%d", tid)) return -EINVAL; if (!pubsta->valid_links && !pubsta->deflink.ht_cap.ht_supported && !pubsta->deflink.vht_cap.vht_supported && !pubsta->deflink.he_cap.has_he && !pubsta->deflink.eht_cap.has_eht && !pubsta->deflink.s1g_cap.s1g) return -EINVAL; if (WARN_ON_ONCE(!local->ops->ampdu_action)) return -EINVAL; if ((tid >= IEEE80211_NUM_TIDS) || !ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION) || ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW)) return -EINVAL; if (WARN_ON(tid >= IEEE80211_FIRST_TSPEC_TSID)) return -EINVAL; ht_dbg(sdata, "Open BA session requested for %pM tid %u\n", pubsta->addr, tid); if (sdata->vif.type != NL80211_IFTYPE_STATION && sdata->vif.type != NL80211_IFTYPE_MESH_POINT && sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_AP && sdata->vif.type != NL80211_IFTYPE_ADHOC) return -EINVAL; if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { ht_dbg(sdata, "BA sessions blocked - Denying BA session request %pM tid %d\n", sta->sta.addr, tid); return -EINVAL; } if (test_sta_flag(sta, WLAN_STA_MFP) && !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { ht_dbg(sdata, "MFP STA not authorized - deny BA session request %pM tid %d\n", sta->sta.addr, tid); return -EINVAL; } /* * 802.11n-2009 11.5.1.1: If the initiating STA is an HT STA, is a * member of an IBSS, and has no other existing Block Ack agreement * with the recipient STA, then the initiating STA shall transmit a * Probe Request frame to the recipient STA and shall not transmit an * ADDBA Request frame unless it receives a Probe Response frame * from the recipient within dot11ADDBAFailureTimeout. * * The probe request mechanism for ADDBA is currently not implemented, * but we only build up Block Ack session with HT STAs. This information * is set when we receive a bss info from a probe response or a beacon. */ if (sta->sdata->vif.type == NL80211_IFTYPE_ADHOC && !sta->sta.deflink.ht_cap.ht_supported) { ht_dbg(sdata, "BA request denied - IBSS STA %pM does not advertise HT support\n", pubsta->addr); return -EINVAL; } spin_lock_bh(&sta->lock); /* we have tried too many times, receiver does not want A-MPDU */ if (sta->ampdu_mlme.addba_req_num[tid] > HT_AGG_MAX_RETRIES) { ret = -EBUSY; goto err_unlock_sta; } /* * if we have tried more than HT_AGG_BURST_RETRIES times we * will spread our requests in time to avoid stalling connection * for too long */ if (sta->ampdu_mlme.addba_req_num[tid] > HT_AGG_BURST_RETRIES && time_before(jiffies, sta->ampdu_mlme.last_addba_req_time[tid] + HT_AGG_RETRIES_PERIOD)) { ht_dbg(sdata, "BA request denied - %d failed requests on %pM tid %u\n", sta->ampdu_mlme.addba_req_num[tid], sta->sta.addr, tid); ret = -EBUSY; goto err_unlock_sta; } tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* check if the TID is not in aggregation flow already */ if (tid_tx || sta->ampdu_mlme.tid_start_tx[tid]) { ht_dbg(sdata, "BA request denied - session is not idle on %pM tid %u\n", sta->sta.addr, tid); ret = -EAGAIN; goto err_unlock_sta; } /* prepare A-MPDU MLME for Tx aggregation */ tid_tx = kzalloc(sizeof(struct tid_ampdu_tx), GFP_ATOMIC); if (!tid_tx) { ret = -ENOMEM; goto err_unlock_sta; } skb_queue_head_init(&tid_tx->pending); __set_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); tid_tx->timeout = timeout; tid_tx->sta = sta; tid_tx->tid = tid; /* response timer */ timer_setup(&tid_tx->addba_resp_timer, sta_addba_resp_timer_expired, 0); /* tx timer */ timer_setup(&tid_tx->session_timer, sta_tx_agg_session_timer_expired, TIMER_DEFERRABLE); /* assign a dialog token */ sta->ampdu_mlme.dialog_token_allocator++; tid_tx->dialog_token = sta->ampdu_mlme.dialog_token_allocator; /* * Finally, assign it to the start array; the work item will * collect it and move it to the normal array. */ sta->ampdu_mlme.tid_start_tx[tid] = tid_tx; wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); /* this flow continues off the work */ err_unlock_sta: spin_unlock_bh(&sta->lock); return ret; } EXPORT_SYMBOL(ieee80211_start_tx_ba_session); static void ieee80211_agg_tx_operational(struct ieee80211_local *local, struct sta_info *sta, u16 tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_OPERATIONAL, .tid = tid, .timeout = 0, .ssn = 0, }; lockdep_assert_wiphy(sta->local->hw.wiphy); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); params.buf_size = tid_tx->buf_size; params.amsdu = tid_tx->amsdu; ht_dbg(sta->sdata, "Aggregation is on for %pM tid %d\n", sta->sta.addr, tid); drv_ampdu_action(local, sta->sdata, ¶ms); /* * synchronize with TX path, while splicing the TX path * should block so it won't put more packets onto pending. */ spin_lock_bh(&sta->lock); ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); /* * Now mark as operational. This will be visible * in the TX path, and lets it go lock-free in * the common case. */ set_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); ieee80211_agg_splice_finish(sta->sdata, tid); spin_unlock_bh(&sta->lock); ieee80211_agg_start_txq(sta, tid, true); } void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(sta->local->hw.wiphy); if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state))) return; if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state) || test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) return; if (!test_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)) { ieee80211_send_addba_with_timeout(sta, tid_tx); /* RESPONSE_RECEIVED state would trigger the flow again */ return; } if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); } static struct tid_ampdu_tx * ieee80211_lookup_tid_tx(struct ieee80211_sub_if_data *sdata, const u8 *ra, u16 tid, struct sta_info **sta) { struct tid_ampdu_tx *tid_tx; if (tid >= IEEE80211_NUM_TIDS) { ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", tid, IEEE80211_NUM_TIDS); return NULL; } *sta = sta_info_get_bss(sdata, ra); if (!*sta) { ht_dbg(sdata, "Could not find station: %pM\n", ra); return NULL; } tid_tx = rcu_dereference((*sta)->ampdu_mlme.tid_tx[tid]); if (WARN_ON(!tid_tx)) ht_dbg(sdata, "addBA was not requested!\n"); return tid_tx; } void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct tid_ampdu_tx *tid_tx; trace_api_start_tx_ba_cb(sdata, ra, tid); rcu_read_lock(); tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta); if (!tid_tx) goto out; set_bit(HT_AGG_STATE_START_CB, &tid_tx->state); wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); out: rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe); int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; int ret = 0; trace_api_stop_tx_ba_session(pubsta, tid); if (!local->ops->ampdu_action) return -EINVAL; if (tid >= IEEE80211_NUM_TIDS) return -EINVAL; spin_lock_bh(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) { ret = -ENOENT; goto unlock; } WARN(sta->reserved_tid == tid, "Requested to stop BA session on reserved tid=%d", tid); if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { /* already in progress stopping it */ ret = 0; goto unlock; } set_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state); wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); unlock: spin_unlock_bh(&sta->lock); return ret; } EXPORT_SYMBOL(ieee80211_stop_tx_ba_session); void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) { struct ieee80211_sub_if_data *sdata = sta->sdata; bool send_delba = false; bool start_txq = false; ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", sta->sta.addr, tid); spin_lock_bh(&sta->lock); if (!test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { ht_dbg(sdata, "unexpected callback to A-MPDU stop for %pM tid %d\n", sta->sta.addr, tid); goto unlock_sta; } if (tid_tx->stop_initiator == WLAN_BACK_INITIATOR && tid_tx->tx_stop) send_delba = true; ieee80211_remove_tid_tx(sta, tid); start_txq = true; unlock_sta: spin_unlock_bh(&sta->lock); if (start_txq) ieee80211_agg_start_txq(sta, tid, false); if (send_delba) ieee80211_send_delba(sdata, sta->sta.addr, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); } void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct tid_ampdu_tx *tid_tx; trace_api_stop_tx_ba_cb(sdata, ra, tid); rcu_read_lock(); tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta); if (!tid_tx) goto out; set_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state); wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); out: rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb_irqsafe); void ieee80211_process_addba_resp(struct ieee80211_local *local, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len) { struct tid_ampdu_tx *tid_tx; struct ieee80211_txq *txq; u16 capab, tid, buf_size; bool amsdu; lockdep_assert_wiphy(sta->local->hw.wiphy); capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK; tid = u16_get_bits(capab, IEEE80211_ADDBA_PARAM_TID_MASK); buf_size = u16_get_bits(capab, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK); ieee80211_retrieve_addba_ext_data(sta, mgmt->u.action.u.addba_resp.variable, len - offsetof(typeof(*mgmt), u.action.u.addba_resp.variable), &buf_size); buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes); txq = sta->sta.txq[tid]; if (!amsdu && txq) set_bit(IEEE80211_TXQ_NO_AMSDU, &to_txq_info(txq)->flags); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) return; if (mgmt->u.action.u.addba_resp.dialog_token != tid_tx->dialog_token) { ht_dbg(sta->sdata, "wrong addBA response token, %pM tid %d\n", sta->sta.addr, tid); return; } timer_delete_sync(&tid_tx->addba_resp_timer); ht_dbg(sta->sdata, "switched off addBA timer for %pM tid %d\n", sta->sta.addr, tid); /* * addba_resp_timer may have fired before we got here, and * caused WANT_STOP to be set. If the stop then was already * processed further, STOPPING might be set. */ if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) || test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { ht_dbg(sta->sdata, "got addBA resp for %pM tid %d but we already gave up\n", sta->sta.addr, tid); return; } /* * IEEE 802.11-2007 7.3.1.14: * In an ADDBA Response frame, when the Status Code field * is set to 0, the Buffer Size subfield is set to a value * of at least 1. */ if (le16_to_cpu(mgmt->u.action.u.addba_resp.status) == WLAN_STATUS_SUCCESS && buf_size) { if (test_and_set_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { /* ignore duplicate response */ return; } tid_tx->buf_size = buf_size; tid_tx->amsdu = amsdu; if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); sta->ampdu_mlme.addba_req_num[tid] = 0; tid_tx->timeout = le16_to_cpu(mgmt->u.action.u.addba_resp.timeout); if (tid_tx->timeout) { mod_timer(&tid_tx->session_timer, TU_TO_EXP_TIME(tid_tx->timeout)); tid_tx->last_tx = jiffies; } } else { __ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_DECLINED); } } |
| 36 13 36 36 10 36 36 13 3 9 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <net/ip.h> #include <net/tcp.h> #include <net/route.h> #include <net/dst.h> #include <net/netfilter/ipv4/nf_reject.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, __u8 protocol, int ttl); static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth); static const struct tcphdr * nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); static int nf_reject_iphdr_validate(struct sk_buff *skb) { struct iphdr *iph; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return 0; iph = ip_hdr(skb); if (iph->ihl < 5 || iph->version != 4) return 0; len = ntohs(iph->tot_len); if (skb->len < len) return 0; else if (len < (iph->ihl*4)) return 0; if (!pskb_may_pull(skb, iph->ihl*4)) return 0; return 1; } struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook) { const struct tcphdr *oth; struct sk_buff *nskb; struct iphdr *niph; struct tcphdr _oth; if (!nf_reject_iphdr_validate(oldskb)) return NULL; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); if (!oth) return NULL; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return NULL; nskb->dev = (struct net_device *)dev; skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); niph->tot_len = htons(nskb->len); ip_send_check(niph); return nskb; } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset); static bool nf_skb_is_icmp_unreach(const struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); u8 *tp, _type; int thoff; if (iph->protocol != IPPROTO_ICMP) return false; thoff = skb_network_offset(skb) + sizeof(*iph); tp = skb_header_pointer(skb, thoff + offsetof(struct icmphdr, type), sizeof(_type), &_type); if (!tp) return false; return *tp == ICMP_DEST_UNREACH; } struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook, u8 code) { struct sk_buff *nskb; struct iphdr *niph; struct icmphdr *icmph; unsigned int len; int dataoff; __wsum csum; u8 proto; if (!nf_reject_iphdr_validate(oldskb)) return NULL; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; /* don't reply to ICMP_DEST_UNREACH with ICMP_DEST_UNREACH. */ if (nf_skb_is_icmp_unreach(oldskb)) return NULL; /* RFC says return as much as we can without exceeding 576 bytes. */ len = min_t(unsigned int, 536, oldskb->len); if (!pskb_may_pull(oldskb, len)) return NULL; if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) return NULL; dataoff = ip_hdrlen(oldskb); proto = ip_hdr(oldskb)->protocol; if (!skb_csum_unnecessary(oldskb) && nf_reject_verify_csum(oldskb, dataoff, proto) && nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) return NULL; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + LL_MAX_HEADER + len, GFP_ATOMIC); if (!nskb) return NULL; nskb->dev = (struct net_device *)dev; skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); skb_reset_transport_header(nskb); icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); icmph->type = ICMP_DEST_UNREACH; icmph->code = code; skb_put_data(nskb, skb_network_header(oldskb), len); csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0); icmph->checksum = csum_fold(csum); niph->tot_len = htons(nskb->len); ip_send_check(niph); return nskb; } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach); static const struct tcphdr * nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook) { const struct tcphdr *oth; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; if (ip_hdr(oldskb)->protocol != IPPROTO_TCP) return NULL; oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb), sizeof(struct tcphdr), _oth); if (oth == NULL) return NULL; /* No RST for RST. */ if (oth->rst) return NULL; /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return NULL; return oth; } static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, __u8 protocol, int ttl) { struct iphdr *niph, *oiph = ip_hdr(oldskb); skb_reset_network_header(nskb); niph = skb_put(nskb, sizeof(struct iphdr)); niph->version = 4; niph->ihl = sizeof(struct iphdr) / 4; niph->tos = 0; niph->id = 0; niph->frag_off = htons(IP_DF); niph->protocol = protocol; niph->check = 0; niph->saddr = oiph->daddr; niph->daddr = oiph->saddr; niph->ttl = ttl; nskb->protocol = htons(ETH_P_IP); return niph; } static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth) { struct iphdr *niph = ip_hdr(nskb); struct tcphdr *tcph; skb_reset_transport_header(nskb); tcph = skb_put_zero(nskb, sizeof(struct tcphdr)); tcph->source = oth->dest; tcph->dest = oth->source; tcph->doff = sizeof(struct tcphdr) / 4; if (oth->ack) { tcph->seq = oth->ack_seq; } else { tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + oldskb->len - ip_hdrlen(oldskb) - (oth->doff << 2)); tcph->ack = 1; } tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); } static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) { struct dst_entry *dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(struct flowi)); fl.u.ip4.daddr = ip_hdr(skb_in)->saddr; nf_ip_route(dev_net(skb_in->dev), &dst, &fl, false); if (!dst) return -1; skb_dst_set(skb_in, dst); return 0; } /* Send RST reply */ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { const struct tcphdr *oth; struct sk_buff *nskb; struct tcphdr _oth; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); if (!oth) return; if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return; /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); nskb->mark = IP4_REPLY_MARK(net, oldskb->mark); skb_reserve(nskb, LL_MAX_HEADER); nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); if (ip_route_me_harder(net, sk, nskb, RTN_UNSPEC)) goto free_nskb; /* "Never happens" */ if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; nf_ct_attach(nskb, oldskb); nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on * the RST will be ours, instead of the destination's. This confuses * some routers/firewalls, and they drop the packet. So we need to * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); struct iphdr *niph = ip_hdr(nskb); struct net_device *br_indev; br_indev = nf_bridge_get_physindev(oldskb, net); if (!br_indev) goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); ip_send_check(niph); if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), oeth->h_source, oeth->h_dest, nskb->len) < 0) goto free_nskb; dev_queue_xmit(nskb); } else #endif ip_local_out(net, nskb->sk, nskb); return; free_nskb: kfree_skb(nskb); } EXPORT_SYMBOL_GPL(nf_send_reset); void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) { struct iphdr *iph = ip_hdr(skb_in); int dataoff = ip_hdrlen(skb_in); u8 proto = iph->protocol; if (iph->frag_off & htons(IP_OFFSET)) return; if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(skb_in, dataoff, proto)) { icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); return; } if (nf_ip_checksum(skb_in, hook, dataoff, proto) == 0) icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); } EXPORT_SYMBOL_GPL(nf_send_unreach); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv4 packet rejection core"); |
| 19 | 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 | /* * llc_pdu.c - access to PDU internals * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/netdevice.h> #include <net/llc_pdu.h> static void llc_pdu_decode_pdu_type(struct sk_buff *skb, u8 *type); static u8 llc_pdu_get_pf_bit(struct llc_pdu_sn *pdu); void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 pdu_type) { llc_pdu_un_hdr(skb)->ssap |= pdu_type; } /** * llc_pdu_set_pf_bit - sets poll/final bit in LLC header * @skb: Frame to set bit in * @bit_value: poll/final bit (0 or 1). * * This function sets poll/final bit in LLC header (based on type of PDU). * in I or S pdus, p/f bit is right bit of fourth byte in header. in U * pdus p/f bit is fifth bit of third byte. */ void llc_pdu_set_pf_bit(struct sk_buff *skb, u8 bit_value) { u8 pdu_type; struct llc_pdu_sn *pdu; llc_pdu_decode_pdu_type(skb, &pdu_type); pdu = llc_pdu_sn_hdr(skb); switch (pdu_type) { case LLC_PDU_TYPE_I: case LLC_PDU_TYPE_S: pdu->ctrl_2 = (pdu->ctrl_2 & 0xFE) | bit_value; break; case LLC_PDU_TYPE_U: pdu->ctrl_1 |= (pdu->ctrl_1 & 0xEF) | (bit_value << 4); break; } } /** * llc_pdu_decode_pf_bit - extracs poll/final bit from LLC header * @skb: input skb that p/f bit must be extracted from it * @pf_bit: poll/final bit (0 or 1) * * This function extracts poll/final bit from LLC header (based on type of * PDU). In I or S pdus, p/f bit is right bit of fourth byte in header. In * U pdus p/f bit is fifth bit of third byte. */ void llc_pdu_decode_pf_bit(struct sk_buff *skb, u8 *pf_bit) { u8 pdu_type; struct llc_pdu_sn *pdu; llc_pdu_decode_pdu_type(skb, &pdu_type); pdu = llc_pdu_sn_hdr(skb); switch (pdu_type) { case LLC_PDU_TYPE_I: case LLC_PDU_TYPE_S: *pf_bit = pdu->ctrl_2 & LLC_S_PF_BIT_MASK; break; case LLC_PDU_TYPE_U: *pf_bit = (pdu->ctrl_1 & LLC_U_PF_BIT_MASK) >> 4; break; } } /** * llc_pdu_init_as_disc_cmd - Builds DISC PDU * @skb: Address of the skb to build * @p_bit: The P bit to set in the PDU * * Builds a pdu frame as a DISC command. */ void llc_pdu_init_as_disc_cmd(struct sk_buff *skb, u8 p_bit) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_2_PDU_CMD_DISC; pdu->ctrl_1 |= ((p_bit & 1) << 4) & LLC_U_PF_BIT_MASK; } /** * llc_pdu_init_as_i_cmd - builds I pdu * @skb: Address of the skb to build * @p_bit: The P bit to set in the PDU * @ns: The sequence number of the data PDU * @nr: The seq. number of the expected I PDU from the remote * * Builds a pdu frame as an I command. */ void llc_pdu_init_as_i_cmd(struct sk_buff *skb, u8 p_bit, u8 ns, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_I; pdu->ctrl_2 = 0; pdu->ctrl_2 |= (p_bit & LLC_I_PF_BIT_MASK); /* p/f bit */ pdu->ctrl_1 |= (ns << 1) & 0xFE; /* set N(S) in bits 2..8 */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_rej_cmd - builds REJ PDU * @skb: Address of the skb to build * @p_bit: The P bit to set in the PDU * @nr: The seq. number of the expected I PDU from the remote * * Builds a pdu frame as a REJ command. */ void llc_pdu_init_as_rej_cmd(struct sk_buff *skb, u8 p_bit, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_S; pdu->ctrl_1 |= LLC_2_PDU_CMD_REJ; pdu->ctrl_2 = 0; pdu->ctrl_2 |= p_bit & LLC_S_PF_BIT_MASK; pdu->ctrl_1 &= 0x0F; /* setting bits 5..8 to zero(reserved) */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_rnr_cmd - builds RNR pdu * @skb: Address of the skb to build * @p_bit: The P bit to set in the PDU * @nr: The seq. number of the expected I PDU from the remote * * Builds a pdu frame as an RNR command. */ void llc_pdu_init_as_rnr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_S; pdu->ctrl_1 |= LLC_2_PDU_CMD_RNR; pdu->ctrl_2 = 0; pdu->ctrl_2 |= p_bit & LLC_S_PF_BIT_MASK; pdu->ctrl_1 &= 0x0F; /* setting bits 5..8 to zero(reserved) */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_rr_cmd - Builds RR pdu * @skb: Address of the skb to build * @p_bit: The P bit to set in the PDU * @nr: The seq. number of the expected I PDU from the remote * * Builds a pdu frame as an RR command. */ void llc_pdu_init_as_rr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_S; pdu->ctrl_1 |= LLC_2_PDU_CMD_RR; pdu->ctrl_2 = p_bit & LLC_S_PF_BIT_MASK; pdu->ctrl_1 &= 0x0F; /* setting bits 5..8 to zero(reserved) */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_sabme_cmd - builds SABME pdu * @skb: Address of the skb to build * @p_bit: The P bit to set in the PDU * * Builds a pdu frame as an SABME command. */ void llc_pdu_init_as_sabme_cmd(struct sk_buff *skb, u8 p_bit) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_2_PDU_CMD_SABME; pdu->ctrl_1 |= ((p_bit & 1) << 4) & LLC_U_PF_BIT_MASK; } /** * llc_pdu_init_as_dm_rsp - builds DM response pdu * @skb: Address of the skb to build * @f_bit: The F bit to set in the PDU * * Builds a pdu frame as a DM response. */ void llc_pdu_init_as_dm_rsp(struct sk_buff *skb, u8 f_bit) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_2_PDU_RSP_DM; pdu->ctrl_1 |= ((f_bit & 1) << 4) & LLC_U_PF_BIT_MASK; } /** * llc_pdu_init_as_frmr_rsp - builds FRMR response PDU * @skb: Address of the frame to build * @prev_pdu: The rejected PDU frame * @f_bit: The F bit to set in the PDU * @vs: tx state vari value for the data link conn at the rejecting LLC * @vr: rx state var value for the data link conn at the rejecting LLC * @vzyxw: completely described in the IEEE Std 802.2 document (Pg 55) * * Builds a pdu frame as a FRMR response. */ void llc_pdu_init_as_frmr_rsp(struct sk_buff *skb, struct llc_pdu_sn *prev_pdu, u8 f_bit, u8 vs, u8 vr, u8 vzyxw) { struct llc_frmr_info *frmr_info; u8 prev_pf = 0; u8 *ctrl; struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_2_PDU_RSP_FRMR; pdu->ctrl_1 |= ((f_bit & 1) << 4) & LLC_U_PF_BIT_MASK; frmr_info = (struct llc_frmr_info *)&pdu->ctrl_2; ctrl = (u8 *)&prev_pdu->ctrl_1; FRMR_INFO_SET_REJ_CNTRL(frmr_info,ctrl); FRMR_INFO_SET_Vs(frmr_info, vs); FRMR_INFO_SET_Vr(frmr_info, vr); prev_pf = llc_pdu_get_pf_bit(prev_pdu); FRMR_INFO_SET_C_R_BIT(frmr_info, prev_pf); FRMR_INFO_SET_INVALID_PDU_CTRL_IND(frmr_info, vzyxw); FRMR_INFO_SET_INVALID_PDU_INFO_IND(frmr_info, vzyxw); FRMR_INFO_SET_PDU_INFO_2LONG_IND(frmr_info, vzyxw); FRMR_INFO_SET_PDU_INVALID_Nr_IND(frmr_info, vzyxw); FRMR_INFO_SET_PDU_INVALID_Ns_IND(frmr_info, vzyxw); skb_put(skb, sizeof(struct llc_frmr_info)); } /** * llc_pdu_init_as_rr_rsp - builds RR response pdu * @skb: Address of the skb to build * @f_bit: The F bit to set in the PDU * @nr: The seq. number of the expected data PDU from the remote * * Builds a pdu frame as an RR response. */ void llc_pdu_init_as_rr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_S; pdu->ctrl_1 |= LLC_2_PDU_RSP_RR; pdu->ctrl_2 = 0; pdu->ctrl_2 |= f_bit & LLC_S_PF_BIT_MASK; pdu->ctrl_1 &= 0x0F; /* setting bits 5..8 to zero(reserved) */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_rej_rsp - builds REJ response pdu * @skb: Address of the skb to build * @f_bit: The F bit to set in the PDU * @nr: The seq. number of the expected data PDU from the remote * * Builds a pdu frame as a REJ response. */ void llc_pdu_init_as_rej_rsp(struct sk_buff *skb, u8 f_bit, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_S; pdu->ctrl_1 |= LLC_2_PDU_RSP_REJ; pdu->ctrl_2 = 0; pdu->ctrl_2 |= f_bit & LLC_S_PF_BIT_MASK; pdu->ctrl_1 &= 0x0F; /* setting bits 5..8 to zero(reserved) */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_rnr_rsp - builds RNR response pdu * @skb: Address of the frame to build * @f_bit: The F bit to set in the PDU * @nr: The seq. number of the expected data PDU from the remote * * Builds a pdu frame as an RNR response. */ void llc_pdu_init_as_rnr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_S; pdu->ctrl_1 |= LLC_2_PDU_RSP_RNR; pdu->ctrl_2 = 0; pdu->ctrl_2 |= f_bit & LLC_S_PF_BIT_MASK; pdu->ctrl_1 &= 0x0F; /* setting bits 5..8 to zero(reserved) */ pdu->ctrl_2 |= (nr << 1) & 0xFE; /* set N(R) in bits 10..16 */ } /** * llc_pdu_init_as_ua_rsp - builds UA response pdu * @skb: Address of the frame to build * @f_bit: The F bit to set in the PDU * * Builds a pdu frame as a UA response. */ void llc_pdu_init_as_ua_rsp(struct sk_buff *skb, u8 f_bit) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_2_PDU_RSP_UA; pdu->ctrl_1 |= ((f_bit & 1) << 4) & LLC_U_PF_BIT_MASK; } /** * llc_pdu_decode_pdu_type - designates PDU type * @skb: input skb that type of it must be designated. * @type: type of PDU (output argument). * * This function designates type of PDU (I, S or U). */ static void llc_pdu_decode_pdu_type(struct sk_buff *skb, u8 *type) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); if (pdu->ctrl_1 & 1) { if ((pdu->ctrl_1 & LLC_PDU_TYPE_U) == LLC_PDU_TYPE_U) *type = LLC_PDU_TYPE_U; else *type = LLC_PDU_TYPE_S; } else *type = LLC_PDU_TYPE_I; } /** * llc_pdu_get_pf_bit - extracts p/f bit of input PDU * @pdu: pointer to LLC header. * * This function extracts p/f bit of input PDU. at first examines type of * PDU and then extracts p/f bit. Returns the p/f bit. */ static u8 llc_pdu_get_pf_bit(struct llc_pdu_sn *pdu) { u8 pdu_type; u8 pf_bit = 0; if (pdu->ctrl_1 & 1) { if ((pdu->ctrl_1 & LLC_PDU_TYPE_U) == LLC_PDU_TYPE_U) pdu_type = LLC_PDU_TYPE_U; else pdu_type = LLC_PDU_TYPE_S; } else pdu_type = LLC_PDU_TYPE_I; switch (pdu_type) { case LLC_PDU_TYPE_I: case LLC_PDU_TYPE_S: pf_bit = pdu->ctrl_2 & LLC_S_PF_BIT_MASK; break; case LLC_PDU_TYPE_U: pf_bit = (pdu->ctrl_1 & LLC_U_PF_BIT_MASK) >> 4; break; } return pf_bit; } |
| 6 6 6 6 6 6 6 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * Common Blowfish algorithm parts shared between the c and assembler * implementations. * * Blowfish Cipher Algorithm, by Bruce Schneier. * http://www.counterpane.com/blowfish.html * * Adapted from Kerneli implementation. * * Copyright (c) Herbert Valerio Riedel <hvr@hvrlab.org> * Copyright (c) Kyle McMartin <kyle@debian.org> * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> */ #include <crypto/algapi.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <linux/types.h> #include <crypto/blowfish.h> static const u32 bf_pbox[16 + 2] = { 0x243f6a88, 0x85a308d3, 0x13198a2e, 0x03707344, 0xa4093822, 0x299f31d0, 0x082efa98, 0xec4e6c89, 0x452821e6, 0x38d01377, 0xbe5466cf, 0x34e90c6c, 0xc0ac29b7, 0xc97c50dd, 0x3f84d5b5, 0xb5470917, 0x9216d5d9, 0x8979fb1b, }; static const u32 bf_sbox[256 * 4] = { 0xd1310ba6, 0x98dfb5ac, 0x2ffd72db, 0xd01adfb7, 0xb8e1afed, 0x6a267e96, 0xba7c9045, 0xf12c7f99, 0x24a19947, 0xb3916cf7, 0x0801f2e2, 0x858efc16, 0x636920d8, 0x71574e69, 0xa458fea3, 0xf4933d7e, 0x0d95748f, 0x728eb658, 0x718bcd58, 0x82154aee, 0x7b54a41d, 0xc25a59b5, 0x9c30d539, 0x2af26013, 0xc5d1b023, 0x286085f0, 0xca417918, 0xb8db38ef, 0x8e79dcb0, 0x603a180e, 0x6c9e0e8b, 0xb01e8a3e, 0xd71577c1, 0xbd314b27, 0x78af2fda, 0x55605c60, 0xe65525f3, 0xaa55ab94, 0x57489862, 0x63e81440, 0x55ca396a, 0x2aab10b6, 0xb4cc5c34, 0x1141e8ce, 0xa15486af, 0x7c72e993, 0xb3ee1411, 0x636fbc2a, 0x2ba9c55d, 0x741831f6, 0xce5c3e16, 0x9b87931e, 0xafd6ba33, 0x6c24cf5c, 0x7a325381, 0x28958677, 0x3b8f4898, 0x6b4bb9af, 0xc4bfe81b, 0x66282193, 0x61d809cc, 0xfb21a991, 0x487cac60, 0x5dec8032, 0xef845d5d, 0xe98575b1, 0xdc262302, 0xeb651b88, 0x23893e81, 0xd396acc5, 0x0f6d6ff3, 0x83f44239, 0x2e0b4482, 0xa4842004, 0x69c8f04a, 0x9e1f9b5e, 0x21c66842, 0xf6e96c9a, 0x670c9c61, 0xabd388f0, 0x6a51a0d2, 0xd8542f68, 0x960fa728, 0xab5133a3, 0x6eef0b6c, 0x137a3be4, 0xba3bf050, 0x7efb2a98, 0xa1f1651d, 0x39af0176, 0x66ca593e, 0x82430e88, 0x8cee8619, 0x456f9fb4, 0x7d84a5c3, 0x3b8b5ebe, 0xe06f75d8, 0x85c12073, 0x401a449f, 0x56c16aa6, 0x4ed3aa62, 0x363f7706, 0x1bfedf72, 0x429b023d, 0x37d0d724, 0xd00a1248, 0xdb0fead3, 0x49f1c09b, 0x075372c9, 0x80991b7b, 0x25d479d8, 0xf6e8def7, 0xe3fe501a, 0xb6794c3b, 0x976ce0bd, 0x04c006ba, 0xc1a94fb6, 0x409f60c4, 0x5e5c9ec2, 0x196a2463, 0x68fb6faf, 0x3e6c53b5, 0x1339b2eb, 0x3b52ec6f, 0x6dfc511f, 0x9b30952c, 0xcc814544, 0xaf5ebd09, 0xbee3d004, 0xde334afd, 0x660f2807, 0x192e4bb3, 0xc0cba857, 0x45c8740f, 0xd20b5f39, 0xb9d3fbdb, 0x5579c0bd, 0x1a60320a, 0xd6a100c6, 0x402c7279, 0x679f25fe, 0xfb1fa3cc, 0x8ea5e9f8, 0xdb3222f8, 0x3c7516df, 0xfd616b15, 0x2f501ec8, 0xad0552ab, 0x323db5fa, 0xfd238760, 0x53317b48, 0x3e00df82, 0x9e5c57bb, 0xca6f8ca0, 0x1a87562e, 0xdf1769db, 0xd542a8f6, 0x287effc3, 0xac6732c6, 0x8c4f5573, 0x695b27b0, 0xbbca58c8, 0xe1ffa35d, 0xb8f011a0, 0x10fa3d98, 0xfd2183b8, 0x4afcb56c, 0x2dd1d35b, 0x9a53e479, 0xb6f84565, 0xd28e49bc, 0x4bfb9790, 0xe1ddf2da, 0xa4cb7e33, 0x62fb1341, 0xcee4c6e8, 0xef20cada, 0x36774c01, 0xd07e9efe, 0x2bf11fb4, 0x95dbda4d, 0xae909198, 0xeaad8e71, 0x6b93d5a0, 0xd08ed1d0, 0xafc725e0, 0x8e3c5b2f, 0x8e7594b7, 0x8ff6e2fb, 0xf2122b64, 0x8888b812, 0x900df01c, 0x4fad5ea0, 0x688fc31c, 0xd1cff191, 0xb3a8c1ad, 0x2f2f2218, 0xbe0e1777, 0xea752dfe, 0x8b021fa1, 0xe5a0cc0f, 0xb56f74e8, 0x18acf3d6, 0xce89e299, 0xb4a84fe0, 0xfd13e0b7, 0x7cc43b81, 0xd2ada8d9, 0x165fa266, 0x80957705, 0x93cc7314, 0x211a1477, 0xe6ad2065, 0x77b5fa86, 0xc75442f5, 0xfb9d35cf, 0xebcdaf0c, 0x7b3e89a0, 0xd6411bd3, 0xae1e7e49, 0x00250e2d, 0x2071b35e, 0x226800bb, 0x57b8e0af, 0x2464369b, 0xf009b91e, 0x5563911d, 0x59dfa6aa, 0x78c14389, 0xd95a537f, 0x207d5ba2, 0x02e5b9c5, 0x83260376, 0x6295cfa9, 0x11c81968, 0x4e734a41, 0xb3472dca, 0x7b14a94a, 0x1b510052, 0x9a532915, 0xd60f573f, 0xbc9bc6e4, 0x2b60a476, 0x81e67400, 0x08ba6fb5, 0x571be91f, 0xf296ec6b, 0x2a0dd915, 0xb6636521, 0xe7b9f9b6, 0xff34052e, 0xc5855664, 0x53b02d5d, 0xa99f8fa1, 0x08ba4799, 0x6e85076a, 0x4b7a70e9, 0xb5b32944, 0xdb75092e, 0xc4192623, 0xad6ea6b0, 0x49a7df7d, 0x9cee60b8, 0x8fedb266, 0xecaa8c71, 0x699a17ff, 0x5664526c, 0xc2b19ee1, 0x193602a5, 0x75094c29, 0xa0591340, 0xe4183a3e, 0x3f54989a, 0x5b429d65, 0x6b8fe4d6, 0x99f73fd6, 0xa1d29c07, 0xefe830f5, 0x4d2d38e6, 0xf0255dc1, 0x4cdd2086, 0x8470eb26, 0x6382e9c6, 0x021ecc5e, 0x09686b3f, 0x3ebaefc9, 0x3c971814, 0x6b6a70a1, 0x687f3584, 0x52a0e286, 0xb79c5305, 0xaa500737, 0x3e07841c, 0x7fdeae5c, 0x8e7d44ec, 0x5716f2b8, 0xb03ada37, 0xf0500c0d, 0xf01c1f04, 0x0200b3ff, 0xae0cf51a, 0x3cb574b2, 0x25837a58, 0xdc0921bd, 0xd19113f9, 0x7ca92ff6, 0x94324773, 0x22f54701, 0x3ae5e581, 0x37c2dadc, 0xc8b57634, 0x9af3dda7, 0xa9446146, 0x0fd0030e, 0xecc8c73e, 0xa4751e41, 0xe238cd99, 0x3bea0e2f, 0x3280bba1, 0x183eb331, 0x4e548b38, 0x4f6db908, 0x6f420d03, 0xf60a04bf, 0x2cb81290, 0x24977c79, 0x5679b072, 0xbcaf89af, 0xde9a771f, 0xd9930810, 0xb38bae12, 0xdccf3f2e, 0x5512721f, 0x2e6b7124, 0x501adde6, 0x9f84cd87, 0x7a584718, 0x7408da17, 0xbc9f9abc, 0xe94b7d8c, 0xec7aec3a, 0xdb851dfa, 0x63094366, 0xc464c3d2, 0xef1c1847, 0x3215d908, 0xdd433b37, 0x24c2ba16, 0x12a14d43, 0x2a65c451, 0x50940002, 0x133ae4dd, 0x71dff89e, 0x10314e55, 0x81ac77d6, 0x5f11199b, 0x043556f1, 0xd7a3c76b, 0x3c11183b, 0x5924a509, 0xf28fe6ed, 0x97f1fbfa, 0x9ebabf2c, 0x1e153c6e, 0x86e34570, 0xeae96fb1, 0x860e5e0a, 0x5a3e2ab3, 0x771fe71c, 0x4e3d06fa, 0x2965dcb9, 0x99e71d0f, 0x803e89d6, 0x5266c825, 0x2e4cc978, 0x9c10b36a, 0xc6150eba, 0x94e2ea78, 0xa5fc3c53, 0x1e0a2df4, 0xf2f74ea7, 0x361d2b3d, 0x1939260f, 0x19c27960, 0x5223a708, 0xf71312b6, 0xebadfe6e, 0xeac31f66, 0xe3bc4595, 0xa67bc883, 0xb17f37d1, 0x018cff28, 0xc332ddef, 0xbe6c5aa5, 0x65582185, 0x68ab9802, 0xeecea50f, 0xdb2f953b, 0x2aef7dad, 0x5b6e2f84, 0x1521b628, 0x29076170, 0xecdd4775, 0x619f1510, 0x13cca830, 0xeb61bd96, 0x0334fe1e, 0xaa0363cf, 0xb5735c90, 0x4c70a239, 0xd59e9e0b, 0xcbaade14, 0xeecc86bc, 0x60622ca7, 0x9cab5cab, 0xb2f3846e, 0x648b1eaf, 0x19bdf0ca, 0xa02369b9, 0x655abb50, 0x40685a32, 0x3c2ab4b3, 0x319ee9d5, 0xc021b8f7, 0x9b540b19, 0x875fa099, 0x95f7997e, 0x623d7da8, 0xf837889a, 0x97e32d77, 0x11ed935f, 0x16681281, 0x0e358829, 0xc7e61fd6, 0x96dedfa1, 0x7858ba99, 0x57f584a5, 0x1b227263, 0x9b83c3ff, 0x1ac24696, 0xcdb30aeb, 0x532e3054, 0x8fd948e4, 0x6dbc3128, 0x58ebf2ef, 0x34c6ffea, 0xfe28ed61, 0xee7c3c73, 0x5d4a14d9, 0xe864b7e3, 0x42105d14, 0x203e13e0, 0x45eee2b6, 0xa3aaabea, 0xdb6c4f15, 0xfacb4fd0, 0xc742f442, 0xef6abbb5, 0x654f3b1d, 0x41cd2105, 0xd81e799e, 0x86854dc7, 0xe44b476a, 0x3d816250, 0xcf62a1f2, 0x5b8d2646, 0xfc8883a0, 0xc1c7b6a3, 0x7f1524c3, 0x69cb7492, 0x47848a0b, 0x5692b285, 0x095bbf00, 0xad19489d, 0x1462b174, 0x23820e00, 0x58428d2a, 0x0c55f5ea, 0x1dadf43e, 0x233f7061, 0x3372f092, 0x8d937e41, 0xd65fecf1, 0x6c223bdb, 0x7cde3759, 0xcbee7460, 0x4085f2a7, 0xce77326e, 0xa6078084, 0x19f8509e, 0xe8efd855, 0x61d99735, 0xa969a7aa, 0xc50c06c2, 0x5a04abfc, 0x800bcadc, 0x9e447a2e, 0xc3453484, 0xfdd56705, 0x0e1e9ec9, 0xdb73dbd3, 0x105588cd, 0x675fda79, 0xe3674340, 0xc5c43465, 0x713e38d8, 0x3d28f89e, 0xf16dff20, 0x153e21e7, 0x8fb03d4a, 0xe6e39f2b, 0xdb83adf7, 0xe93d5a68, 0x948140f7, 0xf64c261c, 0x94692934, 0x411520f7, 0x7602d4f7, 0xbcf46b2e, 0xd4a20068, 0xd4082471, 0x3320f46a, 0x43b7d4b7, 0x500061af, 0x1e39f62e, 0x97244546, 0x14214f74, 0xbf8b8840, 0x4d95fc1d, 0x96b591af, 0x70f4ddd3, 0x66a02f45, 0xbfbc09ec, 0x03bd9785, 0x7fac6dd0, 0x31cb8504, 0x96eb27b3, 0x55fd3941, 0xda2547e6, 0xabca0a9a, 0x28507825, 0x530429f4, 0x0a2c86da, 0xe9b66dfb, 0x68dc1462, 0xd7486900, 0x680ec0a4, 0x27a18dee, 0x4f3ffea2, 0xe887ad8c, 0xb58ce006, 0x7af4d6b6, 0xaace1e7c, 0xd3375fec, 0xce78a399, 0x406b2a42, 0x20fe9e35, 0xd9f385b9, 0xee39d7ab, 0x3b124e8b, 0x1dc9faf7, 0x4b6d1856, 0x26a36631, 0xeae397b2, 0x3a6efa74, 0xdd5b4332, 0x6841e7f7, 0xca7820fb, 0xfb0af54e, 0xd8feb397, 0x454056ac, 0xba489527, 0x55533a3a, 0x20838d87, 0xfe6ba9b7, 0xd096954b, 0x55a867bc, 0xa1159a58, 0xcca92963, 0x99e1db33, 0xa62a4a56, 0x3f3125f9, 0x5ef47e1c, 0x9029317c, 0xfdf8e802, 0x04272f70, 0x80bb155c, 0x05282ce3, 0x95c11548, 0xe4c66d22, 0x48c1133f, 0xc70f86dc, 0x07f9c9ee, 0x41041f0f, 0x404779a4, 0x5d886e17, 0x325f51eb, 0xd59bc0d1, 0xf2bcc18f, 0x41113564, 0x257b7834, 0x602a9c60, 0xdff8e8a3, 0x1f636c1b, 0x0e12b4c2, 0x02e1329e, 0xaf664fd1, 0xcad18115, 0x6b2395e0, 0x333e92e1, 0x3b240b62, 0xeebeb922, 0x85b2a20e, 0xe6ba0d99, 0xde720c8c, 0x2da2f728, 0xd0127845, 0x95b794fd, 0x647d0862, 0xe7ccf5f0, 0x5449a36f, 0x877d48fa, 0xc39dfd27, 0xf33e8d1e, 0x0a476341, 0x992eff74, 0x3a6f6eab, 0xf4f8fd37, 0xa812dc60, 0xa1ebddf8, 0x991be14c, 0xdb6e6b0d, 0xc67b5510, 0x6d672c37, 0x2765d43b, 0xdcd0e804, 0xf1290dc7, 0xcc00ffa3, 0xb5390f92, 0x690fed0b, 0x667b9ffb, 0xcedb7d9c, 0xa091cf0b, 0xd9155ea3, 0xbb132f88, 0x515bad24, 0x7b9479bf, 0x763bd6eb, 0x37392eb3, 0xcc115979, 0x8026e297, 0xf42e312d, 0x6842ada7, 0xc66a2b3b, 0x12754ccc, 0x782ef11c, 0x6a124237, 0xb79251e7, 0x06a1bbe6, 0x4bfb6350, 0x1a6b1018, 0x11caedfa, 0x3d25bdd8, 0xe2e1c3c9, 0x44421659, 0x0a121386, 0xd90cec6e, 0xd5abea2a, 0x64af674e, 0xda86a85f, 0xbebfe988, 0x64e4c3fe, 0x9dbc8057, 0xf0f7c086, 0x60787bf8, 0x6003604d, 0xd1fd8346, 0xf6381fb0, 0x7745ae04, 0xd736fccc, 0x83426b33, 0xf01eab71, 0xb0804187, 0x3c005e5f, 0x77a057be, 0xbde8ae24, 0x55464299, 0xbf582e61, 0x4e58f48f, 0xf2ddfda2, 0xf474ef38, 0x8789bdc2, 0x5366f9c3, 0xc8b38e74, 0xb475f255, 0x46fcd9b9, 0x7aeb2661, 0x8b1ddf84, 0x846a0e79, 0x915f95e2, 0x466e598e, 0x20b45770, 0x8cd55591, 0xc902de4c, 0xb90bace1, 0xbb8205d0, 0x11a86248, 0x7574a99e, 0xb77f19b6, 0xe0a9dc09, 0x662d09a1, 0xc4324633, 0xe85a1f02, 0x09f0be8c, 0x4a99a025, 0x1d6efe10, 0x1ab93d1d, 0x0ba5a4df, 0xa186f20f, 0x2868f169, 0xdcb7da83, 0x573906fe, 0xa1e2ce9b, 0x4fcd7f52, 0x50115e01, 0xa70683fa, 0xa002b5c4, 0x0de6d027, 0x9af88c27, 0x773f8641, 0xc3604c06, 0x61a806b5, 0xf0177a28, 0xc0f586e0, 0x006058aa, 0x30dc7d62, 0x11e69ed7, 0x2338ea63, 0x53c2dd94, 0xc2c21634, 0xbbcbee56, 0x90bcb6de, 0xebfc7da1, 0xce591d76, 0x6f05e409, 0x4b7c0188, 0x39720a3d, 0x7c927c24, 0x86e3725f, 0x724d9db9, 0x1ac15bb4, 0xd39eb8fc, 0xed545578, 0x08fca5b5, 0xd83d7cd3, 0x4dad0fc4, 0x1e50ef5e, 0xb161e6f8, 0xa28514d9, 0x6c51133c, 0x6fd5c7e7, 0x56e14ec4, 0x362abfce, 0xddc6c837, 0xd79a3234, 0x92638212, 0x670efa8e, 0x406000e0, 0x3a39ce37, 0xd3faf5cf, 0xabc27737, 0x5ac52d1b, 0x5cb0679e, 0x4fa33742, 0xd3822740, 0x99bc9bbe, 0xd5118e9d, 0xbf0f7315, 0xd62d1c7e, 0xc700c47b, 0xb78c1b6b, 0x21a19045, 0xb26eb1be, 0x6a366eb4, 0x5748ab2f, 0xbc946e79, 0xc6a376d2, 0x6549c2c8, 0x530ff8ee, 0x468dde7d, 0xd5730a1d, 0x4cd04dc6, 0x2939bbdb, 0xa9ba4650, 0xac9526e8, 0xbe5ee304, 0xa1fad5f0, 0x6a2d519a, 0x63ef8ce2, 0x9a86ee22, 0xc089c2b8, 0x43242ef6, 0xa51e03aa, 0x9cf2d0a4, 0x83c061ba, 0x9be96a4d, 0x8fe51550, 0xba645bd6, 0x2826a2f9, 0xa73a3ae1, 0x4ba99586, 0xef5562e9, 0xc72fefd3, 0xf752f7da, 0x3f046f69, 0x77fa0a59, 0x80e4a915, 0x87b08601, 0x9b09e6ad, 0x3b3ee593, 0xe990fd5a, 0x9e34d797, 0x2cf0b7d9, 0x022b8b51, 0x96d5ac3a, 0x017da67d, 0xd1cf3ed6, 0x7c7d2d28, 0x1f9f25cf, 0xadf2b89b, 0x5ad6b472, 0x5a88f54c, 0xe029ac71, 0xe019a5e6, 0x47b0acfd, 0xed93fa9b, 0xe8d3c48d, 0x283b57cc, 0xf8d56629, 0x79132e28, 0x785f0191, 0xed756055, 0xf7960e44, 0xe3d35e8c, 0x15056dd4, 0x88f46dba, 0x03a16125, 0x0564f0bd, 0xc3eb9e15, 0x3c9057a2, 0x97271aec, 0xa93a072a, 0x1b3f6d9b, 0x1e6321f5, 0xf59c66fb, 0x26dcf319, 0x7533d928, 0xb155fdf5, 0x03563482, 0x8aba3cbb, 0x28517711, 0xc20ad9f8, 0xabcc5167, 0xccad925f, 0x4de81751, 0x3830dc8e, 0x379d5862, 0x9320f991, 0xea7a90c2, 0xfb3e7bce, 0x5121ce64, 0x774fbe32, 0xa8b6e37e, 0xc3293d46, 0x48de5369, 0x6413e680, 0xa2ae0810, 0xdd6db224, 0x69852dfd, 0x09072166, 0xb39a460a, 0x6445c0dd, 0x586cdecf, 0x1c20c8ae, 0x5bbef7dd, 0x1b588d40, 0xccd2017f, 0x6bb4e3bb, 0xdda26a7e, 0x3a59ff45, 0x3e350a44, 0xbcb4cdd5, 0x72eacea8, 0xfa6484bb, 0x8d6612ae, 0xbf3c6f47, 0xd29be463, 0x542f5d9e, 0xaec2771b, 0xf64e6370, 0x740e0d8d, 0xe75b1357, 0xf8721671, 0xaf537d5d, 0x4040cb08, 0x4eb4e2cc, 0x34d2466a, 0x0115af84, 0xe1b00428, 0x95983a1d, 0x06b89fb4, 0xce6ea048, 0x6f3f3b82, 0x3520ab82, 0x011a1d4b, 0x277227f8, 0x611560b1, 0xe7933fdc, 0xbb3a792b, 0x344525bd, 0xa08839e1, 0x51ce794b, 0x2f32c9b7, 0xa01fbac9, 0xe01cc87e, 0xbcc7d1f6, 0xcf0111c3, 0xa1e8aac7, 0x1a908749, 0xd44fbd9a, 0xd0dadecb, 0xd50ada38, 0x0339c32a, 0xc6913667, 0x8df9317c, 0xe0b12b4f, 0xf79e59b7, 0x43f5bb3a, 0xf2d519ff, 0x27d9459c, 0xbf97222c, 0x15e6fc2a, 0x0f91fc71, 0x9b941525, 0xfae59361, 0xceb69ceb, 0xc2a86459, 0x12baa8d1, 0xb6c1075e, 0xe3056a0c, 0x10d25065, 0xcb03a442, 0xe0ec6e0e, 0x1698db3b, 0x4c98a0be, 0x3278e964, 0x9f1f9532, 0xe0d392df, 0xd3a0342b, 0x8971f21e, 0x1b0a7441, 0x4ba3348c, 0xc5be7120, 0xc37632d8, 0xdf359f8d, 0x9b992f2e, 0xe60b6f47, 0x0fe3f11d, 0xe54cda54, 0x1edad891, 0xce6279cf, 0xcd3e7e6f, 0x1618b166, 0xfd2c1d05, 0x848fd2c5, 0xf6fb2299, 0xf523f357, 0xa6327623, 0x93a83531, 0x56cccd02, 0xacf08162, 0x5a75ebb5, 0x6e163697, 0x88d273cc, 0xde966292, 0x81b949d0, 0x4c50901b, 0x71c65614, 0xe6c6c7bd, 0x327a140a, 0x45e1d006, 0xc3f27b9a, 0xc9aa53fd, 0x62a80f00, 0xbb25bfe2, 0x35bdd2f6, 0x71126905, 0xb2040222, 0xb6cbcf7c, 0xcd769c2b, 0x53113ec0, 0x1640e3d3, 0x38abbd60, 0x2547adf0, 0xba38209c, 0xf746ce76, 0x77afa1c5, 0x20756060, 0x85cbfe4e, 0x8ae88dd8, 0x7aaaf9b0, 0x4cf9aa7e, 0x1948c25c, 0x02fb8a8c, 0x01c36ae4, 0xd6ebe1f9, 0x90d4f869, 0xa65cdea0, 0x3f09252d, 0xc208e69f, 0xb74e6132, 0xce77e25b, 0x578fdfe3, 0x3ac372e6, }; /* * Round loop unrolling macros, S is a pointer to a S-Box array * organized in 4 unsigned longs at a row. */ #define GET32_3(x) (((x) & 0xff)) #define GET32_2(x) (((x) >> (8)) & (0xff)) #define GET32_1(x) (((x) >> (16)) & (0xff)) #define GET32_0(x) (((x) >> (24)) & (0xff)) #define bf_F(x) (((S[GET32_0(x)] + S[256 + GET32_1(x)]) ^ \ S[512 + GET32_2(x)]) + S[768 + GET32_3(x)]) #define ROUND(a, b, n) ({ b ^= P[n]; a ^= bf_F(b); }) /* * The blowfish encipher, processes 64-bit blocks. * NOTE: This function MUSTN'T respect endianess */ static void encrypt_block(struct bf_ctx *bctx, u32 *dst, u32 *src) { const u32 *P = bctx->p; const u32 *S = bctx->s; u32 yl = src[0]; u32 yr = src[1]; ROUND(yr, yl, 0); ROUND(yl, yr, 1); ROUND(yr, yl, 2); ROUND(yl, yr, 3); ROUND(yr, yl, 4); ROUND(yl, yr, 5); ROUND(yr, yl, 6); ROUND(yl, yr, 7); ROUND(yr, yl, 8); ROUND(yl, yr, 9); ROUND(yr, yl, 10); ROUND(yl, yr, 11); ROUND(yr, yl, 12); ROUND(yl, yr, 13); ROUND(yr, yl, 14); ROUND(yl, yr, 15); yl ^= P[16]; yr ^= P[17]; dst[0] = yr; dst[1] = yl; } /* * Calculates the blowfish S and P boxes for encryption and decryption. */ int blowfish_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen) { struct bf_ctx *ctx = crypto_tfm_ctx(tfm); u32 *P = ctx->p; u32 *S = ctx->s; short i, j, count; u32 data[2], temp; /* Copy the initialization s-boxes */ for (i = 0, count = 0; i < 256; i++) for (j = 0; j < 4; j++, count++) S[count] = bf_sbox[count]; /* Set the p-boxes */ for (i = 0; i < 16 + 2; i++) P[i] = bf_pbox[i]; /* Actual subkey generation */ for (j = 0, i = 0; i < 16 + 2; i++) { temp = (((u32)key[j] << 24) | ((u32)key[(j + 1) % keylen] << 16) | ((u32)key[(j + 2) % keylen] << 8) | ((u32)key[(j + 3) % keylen])); P[i] = P[i] ^ temp; j = (j + 4) % keylen; } data[0] = 0x00000000; data[1] = 0x00000000; for (i = 0; i < 16 + 2; i += 2) { encrypt_block((struct bf_ctx *)ctx, data, data); P[i] = data[0]; P[i + 1] = data[1]; } for (i = 0; i < 4; i++) { for (j = 0, count = i * 256; j < 256; j += 2, count += 2) { encrypt_block((struct bf_ctx *)ctx, data, data); S[count] = data[0]; S[count + 1] = data[1]; } } /* Bruce says not to bother with the weak key check. */ return 0; } EXPORT_SYMBOL_GPL(blowfish_setkey); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Blowfish Cipher common functions"); |
| 18 18 589 592 589 587 592 587 587 586 585 587 431 432 432 431 430 587 585 583 585 584 584 42 585 587 584 586 584 2 2 9 1 8 3 1 2 1 1 53 50 3 50 1 49 1 48 9 47 3 45 45 30 2 2 2 45 5 45 4 45 4 3 45 6 45 45 45 53 13 13 2 13 6 3 13 20 20 19 19 4 4 18 3 2 16 1 15 14 14 54 7 7 47 54 6 54 7 54 3 53 51 51 80 80 80 80 80 80 80 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 Forwarding Information Base: policy rules. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Thomas Graf <tgraf@suug.ch> * * Fixes: * Rani Assaf : local_rule cannot be deleted * Marc Boucher : routing by fwmark */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/inetdevice.h> #include <linux/init.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/fib_rules.h> #include <linux/indirect_call_wrapper.h> struct fib4_rule { struct fib_rule common; u8 dst_len; u8 src_len; dscp_t dscp; dscp_t dscp_mask; u8 dscp_full:1; /* DSCP or TOS selector */ __be32 src; __be32 srcmask; __be32 dst; __be32 dstmask; #ifdef CONFIG_IP_ROUTE_CLASSID u32 tclassid; #endif }; static bool fib4_rule_matchall(const struct fib_rule *rule) { struct fib4_rule *r = container_of(rule, struct fib4_rule, common); if (r->dst_len || r->src_len || r->dscp) return false; return fib_rule_matchall(rule); } bool fib4_rule_default(const struct fib_rule *rule) { if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || rule->l3mdev) return false; if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN && rule->table != RT_TABLE_DEFAULT) return false; return true; } EXPORT_SYMBOL_GPL(fib4_rule_default); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, AF_INET, extack); } unsigned int fib4_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, AF_INET); } int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_lookup_arg arg = { .result = res, .flags = flags, }; int err; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi4_to_flowi(flp)); err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg); #ifdef CONFIG_IP_ROUTE_CLASSID if (arg.rule) res->tclassid = ((struct fib4_rule *)arg.rule)->tclassid; else res->tclassid = 0; #endif if (err == -ESRCH) err = -ENETUNREACH; return err; } EXPORT_SYMBOL_GPL(__fib_lookup); INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { int err = -EAGAIN; struct fib_table *tbl; u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } rcu_read_lock(); tb_id = fib_rule_get_table(rule, arg); tbl = fib_get_table(rule->fr_net, tb_id); if (tbl) err = fib_table_lookup(tbl, &flp->u.ip4, (struct fib_result *)arg->result, arg->flags); rcu_read_unlock(); return err; } INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule, int flags, struct fib_lookup_arg *arg) { struct fib_result *result = arg->result; struct net_device *dev = NULL; if (result->fi) { struct fib_nh_common *nhc = fib_info_nhc(result->fi, 0); dev = nhc->nhc_dev; } /* do not accept result if the route does * not meet the required prefix length */ if (result->prefixlen <= rule->suppress_prefixlen) goto suppress_route; /* do not accept result if the route uses a device * belonging to a forbidden interface group */ if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) goto suppress_route; return false; suppress_route: if (!(arg->flags & FIB_LOOKUP_NOREF)) fib_info_put(result->fi); return true; } INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib4_rule *r = (struct fib4_rule *) rule; struct flowi4 *fl4 = &fl->u.ip4; __be32 daddr = fl4->daddr; __be32 saddr = fl4->saddr; if (((saddr ^ r->src) & r->srcmask) || ((daddr ^ r->dst) & r->dstmask)) return 0; /* When DSCP selector is used we need to match on the entire DSCP field * in the flow information structure. When TOS selector is used we need * to mask the upper three DSCP bits prior to matching to maintain * legacy behavior. */ if (r->dscp_full && (r->dscp ^ fl4->flowi4_dscp) & r->dscp_mask) return 0; else if (!r->dscp_full && r->dscp && !fib_dscp_masked_match(r->dscp, fl4)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) return 0; if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask, fl4->fl4_sport)) return 0; if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask, fl4->fl4_dport)) return 0; return 1; } static struct fib_table *fib_empty_table(struct net *net) { u32 id = 1; while (1) { if (!fib_get_table(net, id)) return fib_new_table(net, id); if (id++ == RT_TABLE_MAX) break; } return NULL; } static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4, struct netlink_ext_ack *extack) { if (rule4->dscp) { NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP"); return -EINVAL; } rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); rule4->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK); rule4->dscp_full = true; return 0; } static int fib4_nl2rule_dscp_mask(const struct nlattr *nla, struct fib4_rule *rule4, struct netlink_ext_ack *extack) { dscp_t dscp_mask; if (!rule4->dscp_full) { NL_SET_ERR_MSG_ATTR(extack, nla, "Cannot specify DSCP mask without DSCP value"); return -EINVAL; } dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); if (rule4->dscp & ~dscp_mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask"); return -EINVAL; } rule4->dscp_mask = dscp_mask; return 0; } static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct fib4_rule *rule4 = (struct fib4_rule *)rule; struct net *net = rule->fr_net; int err = -EINVAL; if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) { NL_SET_ERR_MSG(extack, "Flow label cannot be specified for IPv4 FIB rules"); goto errout; } if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); goto errout; } /* IPv4 currently doesn't handle high order DSCP bits correctly */ if (frh->tos & ~IPTOS_TOS_MASK) { NL_SET_ERR_MSG(extack, "Invalid tos"); goto errout; } rule4->dscp = inet_dsfield_to_dscp(frh->tos); if (tb[FRA_DSCP] && fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0) goto errout; if (tb[FRA_DSCP_MASK] && fib4_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule4, extack) < 0) goto errout; /* split local/main if they are not already split */ err = fib_unmerge(net); if (err) goto errout; if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) { if (rule->action == FR_ACT_TO_TBL) { struct fib_table *table; table = fib_empty_table(net); if (!table) { err = -ENOBUFS; goto errout; } rule->table = table->tb_id; } } if (frh->src_len) rule4->src = nla_get_in_addr(tb[FRA_SRC]); if (frh->dst_len) rule4->dst = nla_get_in_addr(tb[FRA_DST]); #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW]) { rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); if (rule4->tclassid) atomic_inc(&net->ipv4.fib_num_tclassid_users); } #endif if (fib_rule_requires_fldissect(rule)) net->ipv4.fib_rules_require_fldissect++; rule4->src_len = frh->src_len; rule4->srcmask = inet_make_mask(rule4->src_len); rule4->dst_len = frh->dst_len; rule4->dstmask = inet_make_mask(rule4->dst_len); net->ipv4.fib_has_custom_rules = true; err = 0; errout: return err; } static int fib4_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; int err; /* split local/main if they are not already split */ err = fib_unmerge(net); if (err) goto errout; #ifdef CONFIG_IP_ROUTE_CLASSID if (((struct fib4_rule *)rule)->tclassid) atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif net->ipv4.fib_has_custom_rules = true; if (net->ipv4.fib_rules_require_fldissect && fib_rule_requires_fldissect(rule)) net->ipv4.fib_rules_require_fldissect--; errout: return err; } static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { struct fib4_rule *rule4 = (struct fib4_rule *) rule; if (frh->src_len && (rule4->src_len != frh->src_len)) return 0; if (frh->dst_len && (rule4->dst_len != frh->dst_len)) return 0; if (frh->tos && (rule4->dscp_full || inet_dscp_to_dsfield(rule4->dscp) != frh->tos)) return 0; if (tb[FRA_DSCP]) { dscp_t dscp; dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2); if (!rule4->dscp_full || rule4->dscp != dscp) return 0; } if (tb[FRA_DSCP_MASK]) { dscp_t dscp_mask; dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2); if (!rule4->dscp_full || rule4->dscp_mask != dscp_mask) return 0; } #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) return 0; #endif if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC]))) return 0; if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST]))) return 0; return 1; } static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { struct fib4_rule *rule4 = (struct fib4_rule *) rule; frh->dst_len = rule4->dst_len; frh->src_len = rule4->src_len; if (rule4->dscp_full) { frh->tos = 0; if (nla_put_u8(skb, FRA_DSCP, inet_dscp_to_dsfield(rule4->dscp) >> 2) || nla_put_u8(skb, FRA_DSCP_MASK, inet_dscp_to_dsfield(rule4->dscp_mask) >> 2)) goto nla_put_failure; } else { frh->tos = inet_dscp_to_dsfield(rule4->dscp); } if ((rule4->dst_len && nla_put_in_addr(skb, FRA_DST, rule4->dst)) || (rule4->src_len && nla_put_in_addr(skb, FRA_SRC, rule4->src))) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rule4->tclassid && nla_put_u32(skb, FRA_FLOW, rule4->tclassid)) goto nla_put_failure; #endif return 0; nla_put_failure: return -ENOBUFS; } static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(4) /* dst */ + nla_total_size(4) /* src */ + nla_total_size(4) /* flow */ + nla_total_size(1) /* dscp */ + nla_total_size(1); /* dscp mask */ } static void fib4_rule_flush_cache(struct fib_rules_ops *ops) { rt_cache_flush(ops->fro_net); } static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .family = AF_INET, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, .suppress = fib4_rule_suppress, .match = fib4_rule_match, .configure = fib4_rule_configure, .delete = fib4_rule_delete, .compare = fib4_rule_compare, .fill = fib4_rule_fill, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, .owner = THIS_MODULE, }; static int fib_default_rules_init(struct fib_rules_ops *ops) { int err; err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT); if (err < 0) return err; return 0; } int __net_init fib4_rules_init(struct net *net) { int err; struct fib_rules_ops *ops; ops = fib_rules_register(&fib4_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); err = fib_default_rules_init(ops); if (err < 0) goto fail; net->ipv4.rules_ops = ops; net->ipv4.fib_has_custom_rules = false; net->ipv4.fib_rules_require_fldissect = 0; return 0; fail: /* also cleans all rules already added */ fib_rules_unregister(ops); return err; } void __net_exit fib4_rules_exit(struct net *net) { fib_rules_unregister(net->ipv4.rules_ops); } |
| 6 4 6 6 6 6 6 6 3 3 5 5 5 5 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 Syncookies implementation for the Linux kernel * * Authors: * Glenn Griffin <ggriffin.kernel@gmail.com> * * Based on IPv4 implementation by Andi Kleen * linux/net/ipv4/syncookies.c */ #include <linux/tcp.h> #include <linux/random.h> #include <linux/siphash.h> #include <linux/kernel.h> #include <net/secure_seq.h> #include <net/ipv6.h> #include <net/tcp.h> #include <net/tcp_ecn.h> #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) static siphash_aligned_key_t syncookie6_secret[2]; /* RFC 2460, Section 8.3: * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] * * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows * using higher values than ipv4 tcp syncookies. * The other values are chosen based on ethernet (1500 and 9k MTU), plus * one that accounts for common encap (PPPoe) overhead. Table must be sorted. */ static __u16 const msstab[] = { 1280 - 60, /* IPV6_MIN_MTU - 60 */ 1480 - 60, 1500 - 60, 9000 - 60, }; static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, u32 count, int c) { const struct { struct in6_addr saddr; struct in6_addr daddr; u32 count; __be16 sport; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *saddr, .daddr = *daddr, .count = count, .sport = sport, .dport = dport }; net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret)); return siphash(&combined, offsetofend(typeof(combined), dport), &syncookie6_secret[c]); } static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq, __u32 data) { u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) & COOKIEMASK)); } static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq) { __u32 diff, count = tcp_cookie_time(); cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - cookie_hash(saddr, daddr, sport, dport, count - diff, 1)) & COOKIEMASK; } u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, __u16 *mssp) { int mssind; const __u16 mss = *mssp; for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) if (mss >= msstab[mssind]) break; *mssp = msstab[mssind]; return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source, th->dest, ntohl(th->seq), mssind); } EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); return __cookie_v6_init_sequence(iph, th, mssp); } int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th) { __u32 cookie = ntohl(th->ack_seq) - 1; __u32 seq = ntohl(th->seq) - 1; __u32 mssind; mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } EXPORT_SYMBOL_GPL(__cookie_v6_check); static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tcp_opt; u32 tsoff = 0; int mss; if (tcp_synq_no_recent_overflow(sk)) goto out; mss = __cookie_v6_check(ipv6_hdr(skb), tcp_hdr(skb)); if (!mss) { __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED); goto out; } __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV); /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { tsoff = secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); tcp_opt.rcv_tsecr -= tsoff; } if (!cookie_timestamp_decode(net, &tcp_opt)) goto out; return cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb, &tcp_opt, mss, tsoff); out: return ERR_PTR(-EINVAL); } struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct inet_request_sock *ireq; struct net *net = sock_net(sk); struct request_sock *req; struct dst_entry *dst; struct sock *ret = sk; __u8 rcv_wscale; int full_space; SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; if (cookie_bpf_ok(skb)) { req = cookie_bpf_check(sk, skb); } else { req = cookie_tcp_check(net, sk, skb); if (IS_ERR(req)) goto out; } if (!req) { SKB_DR_SET(reason, NO_SOCKET); goto out_drop; } ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; if (security_inet_conn_request(sk, skb, req)) { SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; } if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { refcount_inc(&skb->users); ireq->pktopts = skb; } /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); tcp_ao_syncookie(sk, skb, req, AF_INET6); /* * We need to lookup the dst_entry to get the correct window size. * This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten * me if there is a preferred way. */ { struct in6_addr *final_p, final; struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowi6_oif = ireq->ir_iif; fl6.flowi6_mark = ireq->ir_mark; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; fl6.flowi6_uid = sk_uid(sk); security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); if (IS_ERR(dst)) { SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; } } req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) req->rsk_window_clamp = full_space; tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); /* req->syncookie is set true only if ACK is validated * by BPF kfunc, then, rcv_wscale is already configured. */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, dst); tcp_rsk(req)->accecn_ok = ireq->ecn_ok && cookie_accecn_ok(th); ret = tcp_get_cookie_sock(sk, skb, req, dst); if (!ret) { SKB_DR_SET(reason, NO_SOCKET); goto out_drop; } out: return ret; out_free: reqsk_free(req); out_drop: sk_skb_reason_drop(sk, skb, reason); return NULL; } |
| 47 19 47 13 1 42 42 42 42 42 42 13 13 42 1 42 42 42 42 42 42 42 22 22 29 26 22 42 42 23 23 23 41 36 24 42 7 42 7 4 36 6 42 14 41 1 48 48 47 47 47 47 47 47 47 42 5 18 47 2 45 40 43 47 42 42 14 42 14 43 19 47 49 49 3 49 47 48 1 48 5 47 47 47 47 6 47 47 42 42 43 49 5 43 1 43 47 47 47 47 6 47 47 47 47 49 47 2 47 47 47 47 49 47 47 47 47 47 9 52 50 51 50 51 51 50 48 48 48 51 50 1 49 49 50 50 50 50 1 49 2 49 49 49 49 7 49 49 50 49 50 61 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 | // 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 (size < USB_DT_SS_EP_COMP_SIZE) { dev_notice(ddev, "invalid SuperSpeed endpoint companion descriptor " "of length %d, skipping\n", size); return; } if (desc->bDescriptorType != USB_DT_SS_ENDPOINT_COMP) { 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 = usb_endpoint_num(d); 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 (udev->speed == USB_SPEED_HIGH && bcdUSB == 0x0220 && !le16_to_cpu(d->wMaxPacketSize) && usb_endpoint_is_isoc_in(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; } |
| 698 698 139 140 39 39 4 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 | // SPDX-License-Identifier: GPL-2.0-or-later /* * cn_proc.c - process events connector * * Copyright (C) Matt Helsley, IBM Corp. 2005 * Based on cn_fork.c by Guillaume Thouvenin <guillaume.thouvenin@bull.net> * Original copyright notice follows: * Copyright (C) 2005 BULL SA. */ #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/init.h> #include <linux/connector.h> #include <linux/gfp.h> #include <linux/ptrace.h> #include <linux/atomic.h> #include <linux/pid_namespace.h> #include <linux/cn_proc.h> #include <linux/local_lock.h> /* * Size of a cn_msg followed by a proc_event structure. Since the * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we * add one 4-byte word to the size here, and then start the actual * cn_msg structure 4 bytes into the stack buffer. The result is that * the immediately following proc_event structure is aligned to 8 bytes. */ #define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4) /* See comment above; we test our assumption about sizeof struct cn_msg here. */ static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer) { BUILD_BUG_ON(sizeof(struct cn_msg) != 20); return (struct cn_msg *)(buffer + 4); } static atomic_t proc_event_num_listeners = ATOMIC_INIT(0); static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; /* local_event.count is used as the sequence number of the netlink message */ struct local_event { local_lock_t lock; __u32 count; }; static DEFINE_PER_CPU(struct local_event, local_event) = { .lock = INIT_LOCAL_LOCK(lock), }; static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data) { __u32 what, exit_code, *ptr; enum proc_cn_mcast_op mc_op; uintptr_t val; if (!dsk || !dsk->sk_user_data || !data) return 0; ptr = (__u32 *)data; what = *ptr++; exit_code = *ptr; val = ((struct proc_input *)(dsk->sk_user_data))->event_type; mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op; if (mc_op == PROC_CN_MCAST_IGNORE) return 1; if ((__u32)val == PROC_EVENT_ALL) return 0; /* * Drop packet if we have to report only non-zero exit status * (PROC_EVENT_NONZERO_EXIT) and exit status is 0 */ if (((__u32)val & PROC_EVENT_NONZERO_EXIT) && (what == PROC_EVENT_EXIT)) { if (exit_code) return 0; } if ((__u32)val & what) return 0; return 1; } static inline void send_msg(struct cn_msg *msg) { __u32 filter_data[2]; local_lock(&local_event.lock); msg->seq = __this_cpu_inc_return(local_event.count) - 1; ((struct proc_event *)msg->data)->cpu = smp_processor_id(); /* * local_lock() disables preemption during send to ensure the messages * are ordered according to their sequence numbers. * * If cn_netlink_send() fails, the data is not sent. */ filter_data[0] = ((struct proc_event *)msg->data)->what; if (filter_data[0] == PROC_EVENT_EXIT) { filter_data[1] = ((struct proc_event *)msg->data)->event_data.exit.exit_code; } else { filter_data[1] = 0; } cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT, cn_filter, (void *)filter_data); local_unlock(&local_event.lock); } void proc_fork_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); struct task_struct *parent; if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_FORK; rcu_read_lock(); parent = rcu_dereference(task->real_parent); ev->event_data.fork.parent_pid = parent->pid; ev->event_data.fork.parent_tgid = parent->tgid; rcu_read_unlock(); ev->event_data.fork.child_pid = task->pid; ev->event_data.fork.child_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_exec_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; ev->event_data.exec.process_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_id_connector(struct task_struct *task, int which_id) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); const struct cred *cred; if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->what = which_id; ev->event_data.id.process_pid = task->pid; ev->event_data.id.process_tgid = task->tgid; rcu_read_lock(); cred = __task_cred(task); if (which_id == PROC_EVENT_UID) { ev->event_data.id.r.ruid = from_kuid_munged(&init_user_ns, cred->uid); ev->event_data.id.e.euid = from_kuid_munged(&init_user_ns, cred->euid); } else if (which_id == PROC_EVENT_GID) { ev->event_data.id.r.rgid = from_kgid_munged(&init_user_ns, cred->gid); ev->event_data.id.e.egid = from_kgid_munged(&init_user_ns, cred->egid); } else { rcu_read_unlock(); return; } rcu_read_unlock(); ev->timestamp_ns = ktime_get_ns(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_sid_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; ev->event_data.sid.process_tgid = task->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_ptrace_connector(struct task_struct *task, int ptrace_id) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; ev->event_data.ptrace.process_tgid = task->tgid; if (ptrace_id == PTRACE_ATTACH) { ev->event_data.ptrace.tracer_pid = current->pid; ev->event_data.ptrace.tracer_tgid = current->tgid; } else if (ptrace_id == PTRACE_DETACH) { ev->event_data.ptrace.tracer_pid = 0; ev->event_data.ptrace.tracer_tgid = 0; } else return; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_comm_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; ev->event_data.comm.process_tgid = task->tgid; get_task_comm(ev->event_data.comm.comm, task); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_coredump_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; rcu_read_lock(); if (pid_alive(task)) { parent = rcu_dereference(task->real_parent); ev->event_data.coredump.parent_pid = parent->pid; ev->event_data.coredump.parent_tgid = parent->tgid; } rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } void proc_exit_connector(struct task_struct *task) { struct cn_msg *msg; struct proc_event *ev; struct task_struct *parent; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; ev->event_data.exit.process_tgid = task->tgid; ev->event_data.exit.exit_code = task->exit_code; ev->event_data.exit.exit_signal = task->exit_signal; rcu_read_lock(); if (pid_alive(task)) { parent = rcu_dereference(task->real_parent); ev->event_data.exit.parent_pid = parent->pid; ev->event_data.exit.parent_tgid = parent->tgid; } rcu_read_unlock(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } /* * Send an acknowledgement message to userspace * * Use 0 for success, EFOO otherwise. * Note: this is the negative of conventional kernel error * values because it's not being returned via syscall return * mechanisms. */ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) { struct cn_msg *msg; struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8); if (atomic_read(&proc_event_num_listeners) < 1) return; msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; ev->timestamp_ns = ktime_get_ns(); ev->cpu = -1; ev->what = PROC_EVENT_NONE; ev->event_data.ack.err = err; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); msg->flags = 0; /* not used */ send_msg(msg); } /** * cn_proc_mcast_ctl * @msg: message sent from userspace via the connector * @nsp: NETLINK_CB of the client's socket buffer */ static void cn_proc_mcast_ctl(struct cn_msg *msg, struct netlink_skb_parms *nsp) { enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0; struct proc_input *pinput = NULL; enum proc_cn_event ev_type = 0; int err = 0, initial = 0; struct sock *sk = NULL; /* * Events are reported with respect to the initial pid * and user namespaces so ignore requestors from * other namespaces. */ if ((current_user_ns() != &init_user_ns) || !task_is_in_init_pid_ns(current)) return; if (msg->len == sizeof(*pinput)) { pinput = (struct proc_input *)msg->data; mc_op = pinput->mcast_op; ev_type = pinput->event_type; } else if (msg->len == sizeof(mc_op)) { mc_op = *((enum proc_cn_mcast_op *)msg->data); ev_type = PROC_EVENT_ALL; } else { return; } ev_type = valid_event((enum proc_cn_event)ev_type); if (ev_type == PROC_EVENT_NONE) ev_type = PROC_EVENT_ALL; if (nsp->sk) { sk = nsp->sk; if (sk->sk_user_data == NULL) { sk->sk_user_data = kzalloc(sizeof(struct proc_input), GFP_KERNEL); if (sk->sk_user_data == NULL) { err = ENOMEM; goto out; } initial = 1; } else { prev_mc_op = ((struct proc_input *)(sk->sk_user_data))->mcast_op; } ((struct proc_input *)(sk->sk_user_data))->event_type = ev_type; ((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op; } switch (mc_op) { case PROC_CN_MCAST_LISTEN: if (initial || (prev_mc_op != PROC_CN_MCAST_LISTEN)) atomic_inc(&proc_event_num_listeners); break; case PROC_CN_MCAST_IGNORE: if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE)) atomic_dec(&proc_event_num_listeners); ((struct proc_input *)(sk->sk_user_data))->event_type = PROC_EVENT_NONE; break; default: err = EINVAL; break; } out: cn_proc_ack(err, msg->seq, msg->ack); } /* * cn_proc_init - initialization entry point * * Adds the connector callback to the connector driver. */ static int __init cn_proc_init(void) { int err = cn_add_callback(&cn_proc_event_id, "cn_proc", &cn_proc_mcast_ctl); if (err) { pr_warn("cn_proc failed to register\n"); return err; } return 0; } device_initcall(cn_proc_init); |
| 3 22 22 22 22 4 4 27 27 27 3 4 29 4 24 25 4 3 347 346 344 344 18 18 18 18 18 18 27 27 27 27 27 3 3 3 3 3 27 18 27 29 29 29 29 28 28 28 29 29 29 29 29 28 29 29 29 25 2975 2977 2972 2974 2976 2974 2981 2975 2975 2979 2982 2980 2977 2979 2967 28 29 29 29 1 22 22 22 22 22 22 1 21 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 18 18 18 18 18 18 18 18 18 18 17 18 18 18 18 18 18 29 28 29 29 29 29 29 29 29 29 22 22 27 27 27 27 27 3 3 3 29 2 29 29 29 29 29 29 27 28 29 29 27 27 25 27 26 24 27 27 2 22 22 18 18 21 3 3 3 3 3 3 3 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002 Andi Kleen, SuSE Labs. * Thanks to Ben LaHaise for precious feedback. */ #include <linux/highmem.h> #include <linux/memblock.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/debugfs.h> #include <linux/pfn.h> #include <linux/percpu.h> #include <linux/gfp.h> #include <linux/pci.h> #include <linux/vmalloc.h> #include <linux/libnvdimm.h> #include <linux/vmstat.h> #include <linux/kernel.h> #include <linux/cc_platform.h> #include <linux/set_memory.h> #include <linux/memregion.h> #include <asm/e820/api.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/setup.h> #include <linux/uaccess.h> #include <asm/pgalloc.h> #include <asm/proto.h> #include <asm/memtype.h> #include "../mm_internal.h" /* * The current flushing context - we pass it instead of 5 arguments: */ struct cpa_data { unsigned long *vaddr; pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; unsigned long numpages; unsigned long curpage; unsigned long pfn; unsigned int flags; unsigned int force_split : 1, force_static_prot : 1, force_flush_all : 1; struct page **pages; }; enum cpa_warn { CPA_CONFLICT, CPA_PROTECT, CPA_DETECT, }; static const int cpa_warn_level = CPA_PROTECT; /* * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings) * using cpa_lock. So that we don't allow any other cpu, with stale large tlb * entries change the page attribute in parallel to some other cpu * splitting a large page entry along with changing the attribute. */ static DEFINE_SPINLOCK(cpa_lock); #define CPA_FLUSHTLB 1 #define CPA_ARRAY 2 #define CPA_PAGES_ARRAY 4 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */ #define CPA_COLLAPSE 16 /* try to collapse large pages */ static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm) { return __pgprot(cachemode2protval(pcm)); } #ifdef CONFIG_PROC_FS static unsigned long direct_pages_count[PG_LEVEL_NUM]; void update_page_count(int level, unsigned long pages) { /* Protect against CPA */ spin_lock(&pgd_lock); direct_pages_count[level] += pages; spin_unlock(&pgd_lock); } static void split_page_count(int level) { if (direct_pages_count[level] == 0) return; direct_pages_count[level]--; if (system_state == SYSTEM_RUNNING) { if (level == PG_LEVEL_2M) count_vm_event(DIRECT_MAP_LEVEL2_SPLIT); else if (level == PG_LEVEL_1G) count_vm_event(DIRECT_MAP_LEVEL3_SPLIT); } direct_pages_count[level - 1] += PTRS_PER_PTE; } static void collapse_page_count(int level) { direct_pages_count[level]++; if (system_state == SYSTEM_RUNNING) { if (level == PG_LEVEL_2M) count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE); else if (level == PG_LEVEL_1G) count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE); } direct_pages_count[level - 1] -= PTRS_PER_PTE; } void arch_report_meminfo(struct seq_file *m) { seq_printf(m, "DirectMap4k: %8lu kB\n", direct_pages_count[PG_LEVEL_4K] << 2); #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) seq_printf(m, "DirectMap2M: %8lu kB\n", direct_pages_count[PG_LEVEL_2M] << 11); #else seq_printf(m, "DirectMap4M: %8lu kB\n", direct_pages_count[PG_LEVEL_2M] << 12); #endif if (direct_gbpages) seq_printf(m, "DirectMap1G: %8lu kB\n", direct_pages_count[PG_LEVEL_1G] << 20); } #else static inline void split_page_count(int level) { } static inline void collapse_page_count(int level) { } #endif #ifdef CONFIG_X86_CPA_STATISTICS static unsigned long cpa_1g_checked; static unsigned long cpa_1g_sameprot; static unsigned long cpa_1g_preserved; static unsigned long cpa_2m_checked; static unsigned long cpa_2m_sameprot; static unsigned long cpa_2m_preserved; static unsigned long cpa_4k_install; static inline void cpa_inc_1g_checked(void) { cpa_1g_checked++; } static inline void cpa_inc_2m_checked(void) { cpa_2m_checked++; } static inline void cpa_inc_4k_install(void) { data_race(cpa_4k_install++); } static inline void cpa_inc_lp_sameprot(int level) { if (level == PG_LEVEL_1G) cpa_1g_sameprot++; else cpa_2m_sameprot++; } static inline void cpa_inc_lp_preserved(int level) { if (level == PG_LEVEL_1G) cpa_1g_preserved++; else cpa_2m_preserved++; } static int cpastats_show(struct seq_file *m, void *p) { seq_printf(m, "1G pages checked: %16lu\n", cpa_1g_checked); seq_printf(m, "1G pages sameprot: %16lu\n", cpa_1g_sameprot); seq_printf(m, "1G pages preserved: %16lu\n", cpa_1g_preserved); seq_printf(m, "2M pages checked: %16lu\n", cpa_2m_checked); seq_printf(m, "2M pages sameprot: %16lu\n", cpa_2m_sameprot); seq_printf(m, "2M pages preserved: %16lu\n", cpa_2m_preserved); seq_printf(m, "4K pages set-checked: %16lu\n", cpa_4k_install); return 0; } static int cpastats_open(struct inode *inode, struct file *file) { return single_open(file, cpastats_show, NULL); } static const struct file_operations cpastats_fops = { .open = cpastats_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; static int __init cpa_stats_init(void) { debugfs_create_file("cpa_stats", S_IRUSR, arch_debugfs_dir, NULL, &cpastats_fops); return 0; } late_initcall(cpa_stats_init); #else static inline void cpa_inc_1g_checked(void) { } static inline void cpa_inc_2m_checked(void) { } static inline void cpa_inc_4k_install(void) { } static inline void cpa_inc_lp_sameprot(int level) { } static inline void cpa_inc_lp_preserved(int level) { } #endif static inline int within(unsigned long addr, unsigned long start, unsigned long end) { return addr >= start && addr < end; } #ifdef CONFIG_X86_64 static inline int within_inclusive(unsigned long addr, unsigned long start, unsigned long end) { return addr >= start && addr <= end; } /* * The kernel image is mapped into two places in the virtual address space * (addresses without KASLR, of course): * * 1. The kernel direct map (0xffff880000000000) * 2. The "high kernel map" (0xffffffff81000000) * * We actually execute out of #2. If we get the address of a kernel symbol, it * points to #2, but almost all physical-to-virtual translations point to #1. * * This is so that we can have both a directmap of all physical memory *and* * take full advantage of the limited (s32) immediate addressing range (2G) * of x86_64. * * See Documentation/arch/x86/x86_64/mm.rst for more detail. */ static inline unsigned long highmap_start_pfn(void) { return __pa_symbol(_text) >> PAGE_SHIFT; } static inline unsigned long highmap_end_pfn(void) { /* Do not reference physical address outside the kernel. */ return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; } static bool __cpa_pfn_in_highmap(unsigned long pfn) { /* * Kernel text has an alias mapping at a high address, known * here as "highmap". */ return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn()); } #else static bool __cpa_pfn_in_highmap(unsigned long pfn) { /* There is no highmap on 32-bit */ return false; } #endif /* * See set_mce_nospec(). * * Machine check recovery code needs to change cache mode of poisoned pages to * UC to avoid speculative access logging another error. But passing the * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a * speculative access. So we cheat and flip the top bit of the address. This * works fine for the code that updates the page tables. But at the end of the * process we need to flush the TLB and cache and the non-canonical address * causes a #GP fault when used by the INVLPG and CLFLUSH instructions. * * But in the common case we already have a canonical address. This code * will fix the top bit if needed and is a no-op otherwise. */ static inline unsigned long fix_addr(unsigned long addr) { #ifdef CONFIG_X86_64 return (long)(addr << 1) >> 1; #else return addr; #endif } static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx) { if (cpa->flags & CPA_PAGES_ARRAY) { struct page *page = cpa->pages[idx]; if (unlikely(PageHighMem(page))) return 0; return (unsigned long)page_address(page); } if (cpa->flags & CPA_ARRAY) return cpa->vaddr[idx]; return *cpa->vaddr + idx * PAGE_SIZE; } /* * Flushing functions */ static void clflush_cache_range_opt(void *vaddr, unsigned int size) { const unsigned long clflush_size = boot_cpu_data.x86_clflush_size; void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1)); void *vend = vaddr + size; if (p >= vend) return; for (; p < vend; p += clflush_size) clflushopt(p); } /** * clflush_cache_range - flush a cache range with clflush * @vaddr: virtual start address * @size: number of bytes to flush * * CLFLUSHOPT is an unordered instruction which needs fencing with MFENCE or * SFENCE to avoid ordering issues. */ void clflush_cache_range(void *vaddr, unsigned int size) { mb(); clflush_cache_range_opt(vaddr, size); mb(); } EXPORT_SYMBOL_GPL(clflush_cache_range); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_invalidate_pmem(void *addr, size_t size) { clflush_cache_range(addr, size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif #ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION bool cpu_cache_has_invalidate_memregion(void) { return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR); } EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, "DEVMEM"); int cpu_cache_invalidate_memregion(int res_desc) { if (WARN_ON_ONCE(!cpu_cache_has_invalidate_memregion())) return -ENXIO; wbinvd_on_all_cpus(); return 0; } EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, "DEVMEM"); #endif static void __cpa_flush_all(void *arg) { unsigned long cache = (unsigned long)arg; /* * Flush all to work around Errata in early athlons regarding * large page flushing. */ __flush_tlb_all(); if (cache && boot_cpu_data.x86 >= 4) wbinvd(); } static void cpa_flush_all(unsigned long cache) { BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); on_each_cpu(__cpa_flush_all, (void *) cache, 1); } static int collapse_large_pages(unsigned long addr, struct list_head *pgtables); static void cpa_collapse_large_pages(struct cpa_data *cpa) { unsigned long start, addr, end; struct ptdesc *ptdesc, *tmp; LIST_HEAD(pgtables); int collapsed = 0; int i; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { for (i = 0; i < cpa->numpages; i++) collapsed += collapse_large_pages(__cpa_addr(cpa, i), &pgtables); } else { addr = __cpa_addr(cpa, 0); start = addr & PMD_MASK; end = addr + PAGE_SIZE * cpa->numpages; for (addr = start; within(addr, start, end); addr += PMD_SIZE) collapsed += collapse_large_pages(addr, &pgtables); } if (!collapsed) return; flush_tlb_all(); list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) { list_del(&ptdesc->pt_list); __free_page(ptdesc_page(ptdesc)); } } static void cpa_flush(struct cpa_data *cpa, int cache) { unsigned long start, end; unsigned int i; BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) { cpa_flush_all(cache); goto collapse_large_pages; } start = fix_addr(__cpa_addr(cpa, 0)); end = start + cpa->numpages * PAGE_SIZE; if (cpa->force_flush_all) end = TLB_FLUSH_ALL; flush_tlb_kernel_range(start, end); if (!cache) goto collapse_large_pages; mb(); for (i = 0; i < cpa->numpages; i++) { unsigned long addr = __cpa_addr(cpa, i); unsigned int level; pte_t *pte = lookup_address(addr, &level); /* * Only flush present addresses: */ if (pte && (pte_val(*pte) & _PAGE_PRESENT)) clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE); } mb(); collapse_large_pages: if (cpa->flags & CPA_COLLAPSE) cpa_collapse_large_pages(cpa); } static bool overlaps(unsigned long r1_start, unsigned long r1_end, unsigned long r2_start, unsigned long r2_end) { return (r1_start <= r2_end && r1_end >= r2_start) || (r2_start <= r1_end && r2_end >= r1_start); } #ifdef CONFIG_PCI_BIOS /* * The BIOS area between 640k and 1Mb needs to be executable for PCI BIOS * based config access (CONFIG_PCI_GOBIOS) support. */ #define BIOS_PFN PFN_DOWN(BIOS_BEGIN) #define BIOS_PFN_END PFN_DOWN(BIOS_END - 1) static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn) { if (pcibios_enabled && overlaps(spfn, epfn, BIOS_PFN, BIOS_PFN_END)) return _PAGE_NX; return 0; } #else static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn) { return 0; } #endif /* * The .rodata section needs to be read-only. Using the pfn catches all * aliases. This also includes __ro_after_init, so do not enforce until * kernel_set_to_readonly is true. */ static pgprotval_t protect_rodata(unsigned long spfn, unsigned long epfn) { unsigned long epfn_ro, spfn_ro = PFN_DOWN(__pa_symbol(__start_rodata)); /* * Note: __end_rodata is at page aligned and not inclusive, so * subtract 1 to get the last enforced PFN in the rodata area. */ epfn_ro = PFN_DOWN(__pa_symbol(__end_rodata)) - 1; if (kernel_set_to_readonly && overlaps(spfn, epfn, spfn_ro, epfn_ro)) return _PAGE_RW; return 0; } /* * Protect kernel text against becoming non executable by forbidding * _PAGE_NX. This protects only the high kernel mapping (_text -> _etext) * out of which the kernel actually executes. Do not protect the low * mapping. * * This does not cover __inittext since that is gone after boot. */ static pgprotval_t protect_kernel_text(unsigned long start, unsigned long end) { unsigned long t_end = (unsigned long)_etext - 1; unsigned long t_start = (unsigned long)_text; if (overlaps(start, end, t_start, t_end)) return _PAGE_NX; return 0; } #if defined(CONFIG_X86_64) /* * Once the kernel maps the text as RO (kernel_set_to_readonly is set), * kernel text mappings for the large page aligned text, rodata sections * will be always read-only. For the kernel identity mappings covering the * holes caused by this alignment can be anything that user asks. * * This will preserve the large page mappings for kernel text/data at no * extra cost. */ static pgprotval_t protect_kernel_text_ro(unsigned long start, unsigned long end) { unsigned long t_end = (unsigned long)__end_rodata_hpage_align - 1; unsigned long t_start = (unsigned long)_text; unsigned int level; if (!kernel_set_to_readonly || !overlaps(start, end, t_start, t_end)) return 0; /* * Don't enforce the !RW mapping for the kernel text mapping, if * the current mapping is already using small page mapping. No * need to work hard to preserve large page mappings in this case. * * This also fixes the Linux Xen paravirt guest boot failure caused * by unexpected read-only mappings for kernel identity * mappings. In this paravirt guest case, the kernel text mapping * and the kernel identity mapping share the same page-table pages, * so the protections for kernel text and identity mappings have to * be the same. */ if (lookup_address(start, &level) && (level != PG_LEVEL_4K)) return _PAGE_RW; return 0; } #else static pgprotval_t protect_kernel_text_ro(unsigned long start, unsigned long end) { return 0; } #endif static inline bool conflicts(pgprot_t prot, pgprotval_t val) { return (pgprot_val(prot) & ~val) != pgprot_val(prot); } static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val, unsigned long start, unsigned long end, unsigned long pfn, const char *txt) { static const char *lvltxt[] = { [CPA_CONFLICT] = "conflict", [CPA_PROTECT] = "protect", [CPA_DETECT] = "detect", }; if (warnlvl > cpa_warn_level || !conflicts(prot, val)) return; pr_warn("CPA %8s %10s: 0x%016lx - 0x%016lx PFN %lx req %016llx prevent %016llx\n", lvltxt[warnlvl], txt, start, end, pfn, (unsigned long long)pgprot_val(prot), (unsigned long long)val); } /* * Certain areas of memory on x86 require very specific protection flags, * for example the BIOS area or kernel text. Callers don't always get this * right (again, ioremap() on BIOS memory is not uncommon) so this function * checks and fixes these known static required protection bits. */ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, unsigned long pfn, unsigned long npg, unsigned long lpsize, int warnlvl) { pgprotval_t forbidden, res; unsigned long end; /* * There is no point in checking RW/NX conflicts when the requested * mapping is setting the page !PRESENT. */ if (!(pgprot_val(prot) & _PAGE_PRESENT)) return prot; /* Operate on the virtual address */ end = start + npg * PAGE_SIZE - 1; res = protect_kernel_text(start, end); check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX"); forbidden = res; /* * Special case to preserve a large page. If the change spawns the * full large page mapping then there is no point to split it * up. Happens with ftrace and is going to be removed once ftrace * switched to text_poke(). */ if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) { res = protect_kernel_text_ro(start, end); check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO"); forbidden |= res; } /* Check the PFN directly */ res = protect_pci_bios(pfn, pfn + npg - 1); check_conflict(warnlvl, prot, res, start, end, pfn, "PCIBIOS NX"); forbidden |= res; res = protect_rodata(pfn, pfn + npg - 1); check_conflict(warnlvl, prot, res, start, end, pfn, "Rodata RO"); forbidden |= res; return __pgprot(pgprot_val(prot) & ~forbidden); } /* * Validate strict W^X semantics. */ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start, unsigned long pfn, unsigned long npg, bool nx, bool rw) { unsigned long end; /* * 32-bit has some unfixable W+X issues, like EFI code * and writeable data being in the same page. Disable * detection and enforcement there. */ if (IS_ENABLED(CONFIG_X86_32)) return new; /* Only verify when NX is supported: */ if (!(__supported_pte_mask & _PAGE_NX)) return new; if (!((pgprot_val(old) ^ pgprot_val(new)) & (_PAGE_RW | _PAGE_NX))) return new; if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW) return new; /* Non-leaf translation entries can disable writing or execution. */ if (!rw || nx) return new; end = start + npg * PAGE_SIZE - 1; WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n", (unsigned long long)pgprot_val(old), (unsigned long long)pgprot_val(new), start, end, pfn); /* * For now, allow all permission change attempts by returning the * attempted permissions. This can 'return old' to actively * refuse the permission change at a later time. */ return new; } /* * Lookup the page table entry for a virtual address in a specific pgd. * Return a pointer to the entry (or NULL if the entry does not exist), * the level of the entry, and the effective NX and RW bits of all * page table levels. */ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, unsigned int *level, bool *nx, bool *rw) { p4d_t *p4d; pud_t *pud; pmd_t *pmd; *level = PG_LEVEL_256T; *nx = false; *rw = true; if (pgd_none(*pgd)) return NULL; *level = PG_LEVEL_512G; *nx |= pgd_flags(*pgd) & _PAGE_NX; *rw &= pgd_flags(*pgd) & _PAGE_RW; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return NULL; if (p4d_leaf(*p4d) || !p4d_present(*p4d)) return (pte_t *)p4d; *level = PG_LEVEL_1G; *nx |= p4d_flags(*p4d) & _PAGE_NX; *rw &= p4d_flags(*p4d) & _PAGE_RW; pud = pud_offset(p4d, address); if (pud_none(*pud)) return NULL; if (pud_leaf(*pud) || !pud_present(*pud)) return (pte_t *)pud; *level = PG_LEVEL_2M; *nx |= pud_flags(*pud) & _PAGE_NX; *rw &= pud_flags(*pud) & _PAGE_RW; pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) return NULL; if (pmd_leaf(*pmd) || !pmd_present(*pmd)) return (pte_t *)pmd; *level = PG_LEVEL_4K; *nx |= pmd_flags(*pmd) & _PAGE_NX; *rw &= pmd_flags(*pmd) & _PAGE_RW; return pte_offset_kernel(pmd, address); } /* * Lookup the page table entry for a virtual address in a specific pgd. * Return a pointer to the entry and the level of the mapping. */ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level) { bool nx, rw; return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw); } /* * Lookup the page table entry for a virtual address. Return a pointer * to the entry and the level of the mapping. * * Note: the function returns p4d, pud or pmd either when the entry is marked * large or when the present bit is not set. Otherwise it returns NULL. */ pte_t *lookup_address(unsigned long address, unsigned int *level) { return lookup_address_in_pgd(pgd_offset_k(address), address, level); } EXPORT_SYMBOL_GPL(lookup_address); static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level, bool *nx, bool *rw) { pgd_t *pgd; if (!cpa->pgd) pgd = pgd_offset_k(address); else pgd = cpa->pgd + pgd_index(address); return lookup_address_in_pgd_attr(pgd, address, level, nx, rw); } /* * Lookup the PMD entry for a virtual address. Return a pointer to the entry * or NULL if not present. */ pmd_t *lookup_pmd_address(unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(address); if (pgd_none(*pgd)) return NULL; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d) || p4d_leaf(*p4d) || !p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, address); if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud)) return NULL; return pmd_offset(pud, address); } /* * This is necessary because __pa() does not work on some * kinds of memory, like vmalloc() or the alloc_remap() * areas on 32-bit NUMA systems. The percpu areas can * end up in this kind of memory, for instance. * * Note that as long as the PTEs are well-formed with correct PFNs, this * works without checking the PRESENT bit in the leaf PTE. This is unlike * the similar vmalloc_to_page() and derivatives. Callers may depend on * this behavior. * * This could be optimized, but it is only used in paths that are not perf * sensitive, and keeping it unoptimized should increase the testing coverage * for the more obscure platforms. */ phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; phys_addr_t phys_addr; unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); /* * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t * before being left-shifted PAGE_SHIFT bits -- this trick is to * make 32-PAE kernel work correctly. */ switch (level) { case PG_LEVEL_1G: phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_MASK; break; case PG_LEVEL_2M: phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_MASK; break; default: phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } return (phys_addr_t)(phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); /* * Set the new pmd in all the pgds we know about: */ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) { /* change init_mm */ set_pte_atomic(kpte, pte); #ifdef CONFIG_X86_32 { struct page *page; list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = (pgd_t *)page_address(page) + pgd_index(address); p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); set_pte_atomic((pte_t *)pmd, pte); } } #endif } static pgprot_t pgprot_clear_protnone_bits(pgprot_t prot) { /* * _PAGE_GLOBAL means "global page" for present PTEs. * But, it is also used to indicate _PAGE_PROTNONE * for non-present PTEs. * * This ensures that a _PAGE_GLOBAL PTE going from * present to non-present is not confused as * _PAGE_PROTNONE. */ if (!(pgprot_val(prot) & _PAGE_PRESENT)) pgprot_val(prot) &= ~_PAGE_GLOBAL; return prot; } static int __should_split_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn; pgprot_t old_prot, new_prot, req_prot, chk_prot; pte_t new_pte, *tmp; enum pg_level level; bool nx, rw; /* * Check for races, another CPU might have split this page * up already: */ tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) return 1; switch (level) { case PG_LEVEL_2M: old_prot = pmd_pgprot(*(pmd_t *)kpte); old_pfn = pmd_pfn(*(pmd_t *)kpte); cpa_inc_2m_checked(); break; case PG_LEVEL_1G: old_prot = pud_pgprot(*(pud_t *)kpte); old_pfn = pud_pfn(*(pud_t *)kpte); cpa_inc_1g_checked(); break; default: return -EINVAL; } psize = page_level_size(level); pmask = page_level_mask(level); /* * Calculate the number of pages, which fit into this large * page starting at address: */ lpaddr = (address + psize) & pmask; numpages = (lpaddr - address) >> PAGE_SHIFT; if (numpages < cpa->numpages) cpa->numpages = numpages; /* * We are safe now. Check whether the new pgprot is the same: * Convert protection attributes to 4k-format, as cpa->mask* are set * up accordingly. */ /* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */ req_prot = pgprot_large_2_4k(old_prot); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); /* * req_prot is in format of 4k pages. It must be converted to large * page format: the caching mode includes the PAT bit located at * different bit positions in the two formats. */ req_prot = pgprot_4k_2_large(req_prot); req_prot = pgprot_clear_protnone_bits(req_prot); if (pgprot_val(req_prot) & _PAGE_PRESENT) pgprot_val(req_prot) |= _PAGE_PSE; /* * old_pfn points to the large page base pfn. So we need to add the * offset of the virtual address: */ pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; /* * Calculate the large page base address and the number of 4K pages * in the large page */ lpaddr = address & pmask; numpages = psize >> PAGE_SHIFT; /* * Sanity check that the existing mapping is correct versus the static * protections. static_protections() guards against !PRESENT, so no * extra conditional required here. */ chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages, psize, CPA_CONFLICT); if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) { /* * Split the large page and tell the split code to * enforce static protections. */ cpa->force_static_prot = 1; return 1; } /* * Optimization: If the requested pgprot is the same as the current * pgprot, then the large page can be preserved and no updates are * required independent of alignment and length of the requested * range. The above already established that the current pgprot is * correct, which in consequence makes the requested pgprot correct * as well if it is the same. The static protection scan below will * not come to a different conclusion. */ if (pgprot_val(req_prot) == pgprot_val(old_prot)) { cpa_inc_lp_sameprot(level); return 0; } /* * If the requested range does not cover the full page, split it up */ if (address != lpaddr || cpa->numpages != numpages) return 1; /* * Check whether the requested pgprot is conflicting with a static * protection requirement in the large page. */ new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, psize, CPA_DETECT); new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages, nx, rw); /* * If there is a conflict, split the large page. * * There used to be a 4k wise evaluation trying really hard to * preserve the large pages, but experimentation has shown, that this * does not help at all. There might be corner cases which would * preserve one large page occasionally, but it's really not worth the * extra code and cycles for the common case. */ if (pgprot_val(req_prot) != pgprot_val(new_prot)) return 1; /* All checks passed. Update the large page mapping. */ new_pte = pfn_pte(old_pfn, new_prot); __set_pmd_pte(kpte, address, new_pte); cpa->flags |= CPA_FLUSHTLB; cpa_inc_lp_preserved(level); return 0; } static int should_split_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { int do_split; if (cpa->force_split) return 1; spin_lock(&pgd_lock); do_split = __should_split_large_page(kpte, address, cpa); spin_unlock(&pgd_lock); return do_split; } static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn, pgprot_t ref_prot, unsigned long address, unsigned long size) { unsigned int npg = PFN_DOWN(size); pgprot_t prot; /* * If should_split_large_page() discovered an inconsistent mapping, * remove the invalid protection in the split mapping. */ if (!cpa->force_static_prot) goto set; /* Hand in lpsize = 0 to enforce the protection mechanism */ prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT); if (pgprot_val(prot) == pgprot_val(ref_prot)) goto set; /* * If this is splitting a PMD, fix it up. PUD splits cannot be * fixed trivially as that would require to rescan the newly * installed PMD mappings after returning from split_large_page() * so an eventual further split can allocate the necessary PTE * pages. Warn for now and revisit it in case this actually * happens. */ if (size == PAGE_SIZE) ref_prot = prot; else pr_warn_once("CPA: Cannot fixup static protections for PUD split\n"); set: set_pte(pte, pfn_pte(pfn, ref_prot)); } static int __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, struct page *base) { unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1; pte_t *pbase = (pte_t *)page_address(base); unsigned int i, level; pgprot_t ref_prot; bool nx, rw; pte_t *tmp; spin_lock(&pgd_lock); /* * Check for races, another CPU might have split this page * up for us already: */ tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) { spin_unlock(&pgd_lock); return 1; } paravirt_alloc_pte(&init_mm, page_to_pfn(base)); switch (level) { case PG_LEVEL_2M: ref_prot = pmd_pgprot(*(pmd_t *)kpte); /* * Clear PSE (aka _PAGE_PAT) and move * PAT bit to correct position. */ ref_prot = pgprot_large_2_4k(ref_prot); ref_pfn = pmd_pfn(*(pmd_t *)kpte); lpaddr = address & PMD_MASK; lpinc = PAGE_SIZE; break; case PG_LEVEL_1G: ref_prot = pud_pgprot(*(pud_t *)kpte); ref_pfn = pud_pfn(*(pud_t *)kpte); pfninc = PMD_SIZE >> PAGE_SHIFT; lpaddr = address & PUD_MASK; lpinc = PMD_SIZE; /* * Clear the PSE flags if the PRESENT flag is not set * otherwise pmd_present() will return true even on a non * present pmd. */ if (!(pgprot_val(ref_prot) & _PAGE_PRESENT)) pgprot_val(ref_prot) &= ~_PAGE_PSE; break; default: spin_unlock(&pgd_lock); return 1; } ref_prot = pgprot_clear_protnone_bits(ref_prot); /* * Get the target pfn from the original entry: */ pfn = ref_pfn; for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc, lpaddr += lpinc) split_set_pte(cpa, pbase + i, pfn, ref_prot, lpaddr, lpinc); if (virt_addr_valid(address)) { unsigned long pfn = PFN_DOWN(__pa(address)); if (pfn_range_is_mapped(pfn, pfn + 1)) split_page_count(level); } /* * Install the new, split up pagetable. * * We use the standard kernel pagetable protections for the new * pagetable protections, the actual ptes set above control the * primary protection behavior: */ __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE))); /* * Do a global flush tlb after splitting the large page * and before we do the actual change page attribute in the PTE. * * Without this, we violate the TLB application note, that says: * "The TLBs may contain both ordinary and large-page * translations for a 4-KByte range of linear addresses. This * may occur if software modifies the paging structures so that * the page size used for the address range changes. If the two * translations differ with respect to page frame or attributes * (e.g., permissions), processor behavior is undefined and may * be implementation-specific." * * We do this global tlb flush inside the cpa_lock, so that we * don't allow any other cpu, with stale tlb entries change the * page attribute in parallel, that also falls into the * just split large page entry. */ flush_tlb_all(); spin_unlock(&pgd_lock); return 0; } static int split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address) { struct page *base; if (!debug_pagealloc_enabled()) spin_unlock(&cpa_lock); base = alloc_pages(GFP_KERNEL, 0); if (!debug_pagealloc_enabled()) spin_lock(&cpa_lock); if (!base) return -ENOMEM; if (__split_large_page(cpa, kpte, address, base)) __free_page(base); return 0; } static int collapse_pmd_page(pmd_t *pmd, unsigned long addr, struct list_head *pgtables) { pmd_t _pmd, old_pmd; pte_t *pte, first; unsigned long pfn; pgprot_t pgprot; int i = 0; if (!cpu_feature_enabled(X86_FEATURE_PSE)) return 0; addr &= PMD_MASK; pte = pte_offset_kernel(pmd, addr); first = *pte; pfn = pte_pfn(first); /* Make sure alignment is suitable */ if (PFN_PHYS(pfn) & ~PMD_MASK) return 0; /* The page is 4k intentionally */ if (pte_flags(first) & _PAGE_KERNEL_4K) return 0; /* Check that the rest of PTEs are compatible with the first one */ for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) { pte_t entry = *pte; if (!pte_present(entry)) return 0; if (pte_flags(entry) != pte_flags(first)) return 0; if (pte_pfn(entry) != pte_pfn(first) + i) return 0; } old_pmd = *pmd; /* Success: set up a large page */ pgprot = pgprot_4k_2_large(pte_pgprot(first)); pgprot_val(pgprot) |= _PAGE_PSE; _pmd = pfn_pmd(pfn, pgprot); set_pmd(pmd, _pmd); /* Queue the page table to be freed after TLB flush */ list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables); if (IS_ENABLED(CONFIG_X86_32)) { struct page *page; /* Update all PGD tables to use the same large page */ list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); /* Something is wrong if entries doesn't match */ if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd))) continue; set_pmd(pmd, _pmd); } } if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1)) collapse_page_count(PG_LEVEL_2M); return 1; } static int collapse_pud_page(pud_t *pud, unsigned long addr, struct list_head *pgtables) { unsigned long pfn; pmd_t *pmd, first; int i; if (!direct_gbpages) return 0; addr &= PUD_MASK; pmd = pmd_offset(pud, addr); first = *pmd; /* * To restore PUD page all PMD entries must be large and * have suitable alignment */ pfn = pmd_pfn(first); if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK)) return 0; /* * To restore PUD page, all following PMDs must be compatible with the * first one. */ for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) { pmd_t entry = *pmd; if (!pmd_present(entry) || !pmd_leaf(entry)) return 0; if (pmd_flags(entry) != pmd_flags(first)) return 0; if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE) return 0; } /* Restore PUD page and queue page table to be freed after TLB flush */ list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables); set_pud(pud, pfn_pud(pfn, pmd_pgprot(first))); if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1)) collapse_page_count(PG_LEVEL_1G); return 1; } /* * Collapse PMD and PUD pages in the kernel mapping around the address where * possible. * * Caller must flush TLB and free page tables queued on the list before * touching the new entries. CPU must not see TLB entries of different size * with different attributes. */ static int collapse_large_pages(unsigned long addr, struct list_head *pgtables) { int collapsed = 0; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; addr &= PMD_MASK; spin_lock(&pgd_lock); pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) goto out; p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) goto out; pud = pud_offset(p4d, addr); if (!pud_present(*pud) || pud_leaf(*pud)) goto out; pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; collapsed = collapse_pmd_page(pmd, addr, pgtables); if (collapsed) collapsed += collapse_pud_page(pud, addr, pgtables); out: spin_unlock(&pgd_lock); return collapsed; } static bool try_to_free_pte_page(pte_t *pte) { int i; for (i = 0; i < PTRS_PER_PTE; i++) if (!pte_none(pte[i])) return false; free_page((unsigned long)pte); return true; } static bool try_to_free_pmd_page(pmd_t *pmd) { int i; for (i = 0; i < PTRS_PER_PMD; i++) if (!pmd_none(pmd[i])) return false; free_page((unsigned long)pmd); return true; } static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) { pte_t *pte = pte_offset_kernel(pmd, start); while (start < end) { set_pte(pte, __pte(0)); start += PAGE_SIZE; pte++; } if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) { pmd_clear(pmd); return true; } return false; } static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, unsigned long start, unsigned long end) { if (unmap_pte_range(pmd, start, end)) if (try_to_free_pmd_page(pud_pgtable(*pud))) pud_clear(pud); } static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) { pmd_t *pmd = pmd_offset(pud, start); /* * Not on a 2MB page boundary? */ if (start & (PMD_SIZE - 1)) { unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; unsigned long pre_end = min_t(unsigned long, end, next_page); __unmap_pmd_range(pud, pmd, start, pre_end); start = pre_end; pmd++; } /* * Try to unmap in 2M chunks. */ while (end - start >= PMD_SIZE) { if (pmd_leaf(*pmd)) pmd_clear(pmd); else __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); start += PMD_SIZE; pmd++; } /* * 4K leftovers? */ if (start < end) return __unmap_pmd_range(pud, pmd, start, end); /* * Try again to free the PMD page if haven't succeeded above. */ if (!pud_none(*pud)) if (try_to_free_pmd_page(pud_pgtable(*pud))) pud_clear(pud); } static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) { pud_t *pud = pud_offset(p4d, start); /* * Not on a GB page boundary? */ if (start & (PUD_SIZE - 1)) { unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; unsigned long pre_end = min_t(unsigned long, end, next_page); unmap_pmd_range(pud, start, pre_end); start = pre_end; pud++; } /* * Try to unmap in 1G chunks? */ while (end - start >= PUD_SIZE) { if (pud_leaf(*pud)) pud_clear(pud); else unmap_pmd_range(pud, start, start + PUD_SIZE); start += PUD_SIZE; pud++; } /* * 2M leftovers? */ if (start < end) unmap_pmd_range(pud, start, end); /* * No need to try to free the PUD page because we'll free it in * populate_pgd's error path */ } static int alloc_pte_page(pmd_t *pmd) { pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL); if (!pte) return -1; set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); return 0; } static int alloc_pmd_page(pud_t *pud) { pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL); if (!pmd) return -1; set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); return 0; } static void populate_pte(struct cpa_data *cpa, unsigned long start, unsigned long end, unsigned num_pages, pmd_t *pmd, pgprot_t pgprot) { pte_t *pte; pte = pte_offset_kernel(pmd, start); pgprot = pgprot_clear_protnone_bits(pgprot); while (num_pages-- && start < end) { set_pte(pte, pfn_pte(cpa->pfn, pgprot)); start += PAGE_SIZE; cpa->pfn++; pte++; } } static long populate_pmd(struct cpa_data *cpa, unsigned long start, unsigned long end, unsigned num_pages, pud_t *pud, pgprot_t pgprot) { long cur_pages = 0; pmd_t *pmd; pgprot_t pmd_pgprot; /* * Not on a 2M boundary? */ if (start & (PMD_SIZE - 1)) { unsigned long pre_end = start + (num_pages << PAGE_SHIFT); unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; pre_end = min_t(unsigned long, pre_end, next_page); cur_pages = (pre_end - start) >> PAGE_SHIFT; cur_pages = min_t(unsigned int, num_pages, cur_pages); /* * Need a PTE page? */ pmd = pmd_offset(pud, start); if (pmd_none(*pmd)) if (alloc_pte_page(pmd)) return -1; populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot); start = pre_end; } /* * We mapped them all? */ if (num_pages == cur_pages) return cur_pages; pmd_pgprot = pgprot_4k_2_large(pgprot); while (end - start >= PMD_SIZE) { /* * We cannot use a 1G page so allocate a PMD page if needed. */ if (pud_none(*pud)) if (alloc_pmd_page(pud)) return -1; pmd = pmd_offset(pud, start); set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn, canon_pgprot(pmd_pgprot)))); start += PMD_SIZE; cpa->pfn += PMD_SIZE >> PAGE_SHIFT; cur_pages += PMD_SIZE >> PAGE_SHIFT; } /* * Map trailing 4K pages. */ if (start < end) { pmd = pmd_offset(pud, start); if (pmd_none(*pmd)) if (alloc_pte_page(pmd)) return -1; populate_pte(cpa, start, end, num_pages - cur_pages, pmd, pgprot); } return num_pages; } static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d, pgprot_t pgprot) { pud_t *pud; unsigned long end; long cur_pages = 0; pgprot_t pud_pgprot; end = start + (cpa->numpages << PAGE_SHIFT); /* * Not on a Gb page boundary? => map everything up to it with * smaller pages. */ if (start & (PUD_SIZE - 1)) { unsigned long pre_end; unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; pre_end = min_t(unsigned long, end, next_page); cur_pages = (pre_end - start) >> PAGE_SHIFT; cur_pages = min_t(int, (int)cpa->numpages, cur_pages); pud = pud_offset(p4d, start); /* * Need a PMD page? */ if (pud_none(*pud)) if (alloc_pmd_page(pud)) return -1; cur_pages = populate_pmd(cpa, start, pre_end, cur_pages, pud, pgprot); if (cur_pages < 0) return cur_pages; start = pre_end; } /* We mapped them all? */ if (cpa->numpages == cur_pages) return cur_pages; pud = pud_offset(p4d, start); pud_pgprot = pgprot_4k_2_large(pgprot); /* * Map everything starting from the Gb boundary, possibly with 1G pages */ while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn, canon_pgprot(pud_pgprot)))); start += PUD_SIZE; cpa->pfn += PUD_SIZE >> PAGE_SHIFT; cur_pages += PUD_SIZE >> PAGE_SHIFT; pud++; } /* Map trailing leftover */ if (start < end) { long tmp; pud = pud_offset(p4d, start); if (pud_none(*pud)) if (alloc_pmd_page(pud)) return -1; tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages, pud, pgprot); if (tmp < 0) return cur_pages; cur_pages += tmp; } return cur_pages; } /* * Restrictions for kernel page table do not necessarily apply when mapping in * an alternate PGD. */ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) { pgprot_t pgprot = __pgprot(_KERNPG_TABLE); pud_t *pud = NULL; /* shut up gcc */ p4d_t *p4d; pgd_t *pgd_entry; long ret; pgd_entry = cpa->pgd + pgd_index(addr); if (pgd_none(*pgd_entry)) { p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); if (!p4d) return -1; set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE)); } /* * Allocate a PUD page and hand it down for mapping. */ p4d = p4d_offset(pgd_entry, addr); if (p4d_none(*p4d)) { pud = (pud_t *)get_zeroed_page(GFP_KERNEL); if (!pud) return -1; set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); } pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(pgprot) |= pgprot_val(cpa->mask_set); ret = populate_pud(cpa, addr, p4d, pgprot); if (ret < 0) { /* * Leave the PUD page in place in case some other CPU or thread * already found it, but remove any useless entries we just * added to it. */ unmap_pud_range(p4d, addr, addr + (cpa->numpages << PAGE_SHIFT)); return ret; } cpa->numpages = ret; return 0; } static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, int primary) { if (cpa->pgd) { /* * Right now, we only execute this code path when mapping * the EFI virtual memory map regions, no other users * provide a ->pgd value. This may change in the future. */ return populate_pgd(cpa, vaddr); } /* * Ignore all non primary paths. */ if (!primary) { cpa->numpages = 1; return 0; } /* * Ignore the NULL PTE for kernel identity mapping, as it is expected * to have holes. * Also set numpages to '1' indicating that we processed cpa req for * one virtual address page and its pfn. TBD: numpages can be set based * on the initial value and the level returned by lookup_address(). */ if (within(vaddr, PAGE_OFFSET, PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) { cpa->numpages = 1; cpa->pfn = __pa(vaddr) >> PAGE_SHIFT; return 0; } else if (__cpa_pfn_in_highmap(cpa->pfn)) { /* Faults in the highmap are OK, so do not warn: */ return -EFAULT; } else { WARN(1, KERN_WARNING "CPA: called for zero pte. " "vaddr = %lx cpa->vaddr = %lx\n", vaddr, *cpa->vaddr); return -EFAULT; } } static int __change_page_attr(struct cpa_data *cpa, int primary) { unsigned long address; int do_split, err; unsigned int level; pte_t *kpte, old_pte; bool nx, rw; address = __cpa_addr(cpa, cpa->curpage); repeat: kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (!kpte) return __cpa_process_fault(cpa, address, primary); old_pte = *kpte; if (pte_none(old_pte)) return __cpa_process_fault(cpa, address, primary); if (level == PG_LEVEL_4K) { pte_t new_pte; pgprot_t old_prot = pte_pgprot(old_pte); pgprot_t new_prot = pte_pgprot(old_pte); unsigned long pfn = pte_pfn(old_pte); pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); cpa_inc_4k_install(); /* Hand in lpsize = 0 to enforce the protection mechanism */ new_prot = static_protections(new_prot, address, pfn, 1, 0, CPA_PROTECT); new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1, nx, rw); new_prot = pgprot_clear_protnone_bits(new_prot); /* * We need to keep the pfn from the existing PTE, * after all we're only going to change its attributes * not the memory it points to */ new_pte = pfn_pte(pfn, new_prot); cpa->pfn = pfn; /* * Do we really change anything ? */ if (pte_val(old_pte) != pte_val(new_pte)) { set_pte_atomic(kpte, new_pte); cpa->flags |= CPA_FLUSHTLB; } cpa->numpages = 1; return 0; } /* * Check, whether we can keep the large page intact * and just change the pte: */ do_split = should_split_large_page(kpte, address, cpa); /* * When the range fits into the existing large page, * return. cp->numpages and cpa->tlbflush have been updated in * try_large_page: */ if (do_split <= 0) return do_split; /* * We have to split the large page: */ err = split_large_page(cpa, kpte, address); if (!err) goto repeat; return err; } static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary); /* * Check the directmap and "high kernel map" 'aliases'. */ static int cpa_process_alias(struct cpa_data *cpa) { struct cpa_data alias_cpa; unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT); unsigned long vaddr; int ret; if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1)) return 0; /* * No need to redo, when the primary call touched the direct * mapping already: */ vaddr = __cpa_addr(cpa, cpa->curpage); if (!(within(vaddr, PAGE_OFFSET, PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) { alias_cpa = *cpa; alias_cpa.vaddr = &laddr; alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; /* Directmap always has NX set, do not modify. */ if (__supported_pte_mask & _PAGE_NX) { alias_cpa.mask_clr.pgprot &= ~_PAGE_NX; alias_cpa.mask_set.pgprot &= ~_PAGE_NX; } cpa->force_flush_all = 1; ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; } #ifdef CONFIG_X86_64 /* * If the primary call didn't touch the high mapping already * and the physical address is inside the kernel map, we need * to touch the high mapped kernel as well: */ if (!within(vaddr, (unsigned long)_text, _brk_end) && __cpa_pfn_in_highmap(cpa->pfn)) { unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; alias_cpa = *cpa; alias_cpa.vaddr = &temp_cpa_vaddr; alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; /* * [_text, _brk_end) also covers data, do not modify NX except * in cases where the highmap is the primary target. */ if (__supported_pte_mask & _PAGE_NX) { alias_cpa.mask_clr.pgprot &= ~_PAGE_NX; alias_cpa.mask_set.pgprot &= ~_PAGE_NX; } cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. */ __change_page_attr_set_clr(&alias_cpa, 0); } #endif return 0; } static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary) { unsigned long numpages = cpa->numpages; unsigned long rempages = numpages; int ret = 0; /* * No changes, easy! */ if (!(pgprot_val(cpa->mask_set) | pgprot_val(cpa->mask_clr)) && !cpa->force_split) return ret; while (rempages) { /* * Store the remaining nr of pages for the large page * preservation check. */ cpa->numpages = rempages; /* for array changes, we can't use large page */ if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY)) cpa->numpages = 1; if (!debug_pagealloc_enabled()) spin_lock(&cpa_lock); ret = __change_page_attr(cpa, primary); if (!debug_pagealloc_enabled()) spin_unlock(&cpa_lock); if (ret) goto out; if (primary && !(cpa->flags & CPA_NO_CHECK_ALIAS)) { ret = cpa_process_alias(cpa); if (ret) goto out; } /* * Adjust the number of pages with the result of the * CPA operation. Either a large page has been * preserved or a single page update happened. */ BUG_ON(cpa->numpages > rempages || !cpa->numpages); rempages -= cpa->numpages; cpa->curpage += cpa->numpages; } out: /* Restore the original numpages */ cpa->numpages = numpages; return ret; } static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, struct page **pages) { struct cpa_data cpa; int ret, cache; memset(&cpa, 0, sizeof(cpa)); /* * Check, if we are requested to set a not supported * feature. Clearing non-supported features is OK. */ mask_set = canon_pgprot(mask_set); if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split) return 0; /* Ensure we are PAGE_SIZE aligned */ if (in_flag & CPA_ARRAY) { int i; for (i = 0; i < numpages; i++) { if (addr[i] & ~PAGE_MASK) { addr[i] &= PAGE_MASK; WARN_ON_ONCE(1); } } } else if (!(in_flag & CPA_PAGES_ARRAY)) { /* * in_flag of CPA_PAGES_ARRAY implies it is aligned. * No need to check in that case */ if (*addr & ~PAGE_MASK) { *addr &= PAGE_MASK; /* * People should not be passing in unaligned addresses: */ WARN_ON_ONCE(1); } } /* Must avoid aliasing mappings in the highmem code */ kmap_flush_unused(); vm_unmap_aliases(); cpa.vaddr = addr; cpa.pages = pages; cpa.numpages = numpages; cpa.mask_set = mask_set; cpa.mask_clr = mask_clr; cpa.flags = in_flag; cpa.curpage = 0; cpa.force_split = force_split; ret = __change_page_attr_set_clr(&cpa, 1); /* * Check whether we really changed something: */ if (!(cpa.flags & CPA_FLUSHTLB)) goto out; /* * No need to flush, when we did not set any of the caching * attributes: */ cache = !!pgprot2cachemode(mask_set); /* * On error; flush everything to be sure. */ if (ret) { cpa_flush_all(cache); goto out; } cpa_flush(&cpa, cache); out: return ret; } static inline int change_page_attr_set(unsigned long *addr, int numpages, pgprot_t mask, int array) { return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0, (array ? CPA_ARRAY : 0), NULL); } static inline int change_page_attr_clear(unsigned long *addr, int numpages, pgprot_t mask, int array) { return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0, (array ? CPA_ARRAY : 0), NULL); } static inline int cpa_set_pages_array(struct page **pages, int numpages, pgprot_t mask) { return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0, CPA_PAGES_ARRAY, pages); } static inline int cpa_clear_pages_array(struct page **pages, int numpages, pgprot_t mask) { return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0, CPA_PAGES_ARRAY, pages); } /* * __set_memory_prot is an internal helper for callers that have been passed * a pgprot_t value from upper layers and a reservation has already been taken. * If you want to set the pgprot to a specific page protocol, use the * set_memory_xx() functions. */ int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot) { return change_page_attr_set_clr(&addr, numpages, prot, __pgprot(~pgprot_val(prot)), 0, 0, NULL); } int _set_memory_uc(unsigned long addr, int numpages) { /* * for now UC MINUS. see comments in ioremap() * If you really need strong UC use ioremap_uc(), but note * that you cannot override IO areas with set_memory_*() as * these helpers cannot work with IO memory. */ return change_page_attr_set(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), 0); } int set_memory_uc(unsigned long addr, int numpages) { int ret; /* * for now UC MINUS. see comments in ioremap() */ ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_UC_MINUS, NULL); if (ret) goto out_err; ret = _set_memory_uc(addr, numpages); if (ret) goto out_free; return 0; out_free: memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); out_err: return ret; } EXPORT_SYMBOL(set_memory_uc); int _set_memory_wc(unsigned long addr, int numpages) { int ret; ret = change_page_attr_set(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), 0); if (!ret) { ret = change_page_attr_set_clr(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_WC), __pgprot(_PAGE_CACHE_MASK), 0, 0, NULL); } return ret; } int set_memory_wc(unsigned long addr, int numpages) { int ret; ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_WC, NULL); if (ret) return ret; ret = _set_memory_wc(addr, numpages); if (ret) memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return ret; } EXPORT_SYMBOL(set_memory_wc); int _set_memory_wt(unsigned long addr, int numpages) { return change_page_attr_set(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0); } int _set_memory_wb(unsigned long addr, int numpages) { /* WB cache mode is hard wired to all cache attribute bits being 0 */ return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_CACHE_MASK), 0); } int set_memory_wb(unsigned long addr, int numpages) { int ret; ret = _set_memory_wb(addr, numpages); if (ret) return ret; memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return 0; } EXPORT_SYMBOL(set_memory_wb); /* Prevent speculative access to a page by marking it not-present */ #ifdef CONFIG_X86_64 int set_mce_nospec(unsigned long pfn) { unsigned long decoy_addr; int rc; /* SGX pages are not in the 1:1 map */ if (arch_is_platform_page(pfn << PAGE_SHIFT)) return 0; /* * We would like to just call: * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address * that looks just like the one we want, but has bit 63 flipped. * This relies on set_memory_XX() properly sanitizing any __pa() * results with __PHYSICAL_MASK or PTE_PFN_MASK. */ decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); rc = set_memory_np(decoy_addr, 1); if (rc) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); return rc; } EXPORT_SYMBOL_GPL(set_mce_nospec); /* Restore full speculative operation to the pfn. */ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); return set_memory_p(addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ int set_memory_x(unsigned long addr, int numpages) { if (!(__supported_pte_mask & _PAGE_NX)) return 0; return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0); } int set_memory_nx(unsigned long addr, int numpages) { if (!(__supported_pte_mask & _PAGE_NX)) return 0; return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0); } int set_memory_ro(unsigned long addr, int numpages) { return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW | _PAGE_DIRTY), 0); } int set_memory_rox(unsigned long addr, int numpages) { pgprot_t clr = __pgprot(_PAGE_RW | _PAGE_DIRTY); if (__supported_pte_mask & _PAGE_NX) clr.pgprot |= _PAGE_NX; return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0, CPA_COLLAPSE, NULL); } int set_memory_rw(unsigned long addr, int numpages) { return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0); } int set_memory_np(unsigned long addr, int numpages) { return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); } int set_memory_np_noalias(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), __pgprot(_PAGE_PRESENT), 0, CPA_NO_CHECK_ALIAS, NULL); } int set_memory_p(unsigned long addr, int numpages) { return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); } int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(_PAGE_KERNEL_4K), __pgprot(0), 1, 0, NULL); } int set_memory_nonglobal(unsigned long addr, int numpages) { return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_GLOBAL), 0); } int set_memory_global(unsigned long addr, int numpages) { return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_GLOBAL), 0); } /* * __set_memory_enc_pgtable() is used for the hypervisors that get * informed about "encryption" status via page tables. */ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) { pgprot_t empty = __pgprot(0); struct cpa_data cpa; int ret; /* Should not be working on unaligned addresses */ if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr)) addr &= PAGE_MASK; memset(&cpa, 0, sizeof(cpa)); cpa.vaddr = &addr; cpa.numpages = numpages; cpa.mask_set = enc ? pgprot_encrypted(empty) : pgprot_decrypted(empty); cpa.mask_clr = enc ? pgprot_decrypted(empty) : pgprot_encrypted(empty); cpa.pgd = init_mm.pgd; /* Must avoid aliasing mappings in the highmem code */ kmap_flush_unused(); vm_unmap_aliases(); /* Flush the caches as needed before changing the encryption attribute. */ if (x86_platform.guest.enc_tlb_flush_required(enc)) cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required()); /* Notify hypervisor that we are about to set/clr encryption attribute. */ ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc); if (ret) goto vmm_fail; ret = __change_page_attr_set_clr(&cpa, 1); /* * After changing the encryption attribute, we need to flush TLBs again * in case any speculative TLB caching occurred (but no need to flush * caches again). We could just use cpa_flush_all(), but in case TLB * flushing gets optimized in the cpa_flush() path use the same logic * as above. */ cpa_flush(&cpa, 0); if (ret) return ret; /* Notify hypervisor that we have successfully set/clr encryption attribute. */ ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc); if (ret) goto vmm_fail; return 0; vmm_fail: WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n", (void *)addr, numpages, enc ? "private" : "shared", ret); return ret; } /* * The lock serializes conversions between private and shared memory. * * It is taken for read on conversion. A write lock guarantees that no * concurrent conversions are in progress. */ static DECLARE_RWSEM(mem_enc_lock); /* * Stop new private<->shared conversions. * * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete. * The lock is not released to prevent new conversions from being started. */ bool set_memory_enc_stop_conversion(void) { /* * In a crash scenario, sleep is not allowed. Try to take the lock. * Failure indicates that there is a race with the conversion. */ if (oops_in_progress) return down_write_trylock(&mem_enc_lock); down_write(&mem_enc_lock); return true; } static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) { int ret = 0; if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { if (!down_read_trylock(&mem_enc_lock)) return -EBUSY; ret = __set_memory_enc_pgtable(addr, numpages, enc); up_read(&mem_enc_lock); } return ret; } int set_memory_encrypted(unsigned long addr, int numpages) { return __set_memory_enc_dec(addr, numpages, true); } EXPORT_SYMBOL_GPL(set_memory_encrypted); int set_memory_decrypted(unsigned long addr, int numpages) { return __set_memory_enc_dec(addr, numpages, false); } EXPORT_SYMBOL_GPL(set_memory_decrypted); int set_pages_uc(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); return set_memory_uc(addr, numpages); } EXPORT_SYMBOL(set_pages_uc); static int _set_pages_array(struct page **pages, int numpages, enum page_cache_mode new_type) { unsigned long start; unsigned long end; enum page_cache_mode set_type; int i; int free_idx; int ret; for (i = 0; i < numpages; i++) { if (PageHighMem(pages[i])) continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; if (memtype_reserve(start, end, new_type, NULL)) goto err_out; } /* If WC, set to UC- first and then WC */ set_type = (new_type == _PAGE_CACHE_MODE_WC) ? _PAGE_CACHE_MODE_UC_MINUS : new_type; ret = cpa_set_pages_array(pages, numpages, cachemode2pgprot(set_type)); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(NULL, numpages, cachemode2pgprot( _PAGE_CACHE_MODE_WC), __pgprot(_PAGE_CACHE_MASK), 0, CPA_PAGES_ARRAY, pages); if (ret) goto err_out; return 0; /* Success */ err_out: free_idx = i; for (i = 0; i < free_idx; i++) { if (PageHighMem(pages[i])) continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; memtype_free(start, end); } return -EINVAL; } int set_pages_array_uc(struct page **pages, int numpages) { return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_UC_MINUS); } EXPORT_SYMBOL(set_pages_array_uc); int set_pages_array_wc(struct page **pages, int numpages) { return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WC); } EXPORT_SYMBOL(set_pages_array_wc); int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); return set_memory_wb(addr, numpages); } EXPORT_SYMBOL(set_pages_wb); int set_pages_array_wb(struct page **pages, int numpages) { int retval; unsigned long start; unsigned long end; int i; /* WB cache mode is hard wired to all cache attribute bits being 0 */ retval = cpa_clear_pages_array(pages, numpages, __pgprot(_PAGE_CACHE_MASK)); if (retval) return retval; for (i = 0; i < numpages; i++) { if (PageHighMem(pages[i])) continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; memtype_free(start, end); } return 0; } EXPORT_SYMBOL(set_pages_array_wb); int set_pages_ro(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); return set_memory_ro(addr, numpages); } int set_pages_rw(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); return set_memory_rw(addr, numpages); } static int __set_pages_p(struct page *page, int numpages) { unsigned long tempaddr = (unsigned long) page_address(page); struct cpa_data cpa = { .vaddr = &tempaddr, .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW), .mask_clr = __pgprot(0), .flags = CPA_NO_CHECK_ALIAS }; /* * No alias checking needed for setting present flag. otherwise, * we may need to break large pages for 64-bit kernel text * mappings (this adds to complexity if we want to do this from * atomic context especially). Let's keep it simple! */ return __change_page_attr_set_clr(&cpa, 1); } static int __set_pages_np(struct page *page, int numpages) { unsigned long tempaddr = (unsigned long) page_address(page); struct cpa_data cpa = { .vaddr = &tempaddr, .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), .flags = CPA_NO_CHECK_ALIAS }; /* * No alias checking needed for setting not present flag. otherwise, * we may need to break large pages for 64-bit kernel text * mappings (this adds to complexity if we want to do this from * atomic context especially). Let's keep it simple! */ return __change_page_attr_set_clr(&cpa, 1); } int set_direct_map_invalid_noflush(struct page *page) { return __set_pages_np(page, 1); } int set_direct_map_default_noflush(struct page *page) { return __set_pages_p(page, 1); } int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) { if (valid) return __set_pages_p(page, nr); return __set_pages_np(page, nr); } #ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { if (PageHighMem(page)) return; if (!enable) { debug_check_no_locks_freed(page_address(page), numpages * PAGE_SIZE); } /* * The return value is ignored as the calls cannot fail. * Large pages for identity mappings are not used at boot time * and hence no memory allocations during large page split. */ if (enable) __set_pages_p(page, numpages); else __set_pages_np(page, numpages); /* * We should perform an IPI and flush all tlbs, * but that can deadlock->flush only current cpu. * Preemption needs to be disabled around __flush_tlb_all() due to * CR3 reload in __native_flush_tlb(). */ preempt_disable(); __flush_tlb_all(); preempt_enable(); arch_flush_lazy_mmu_mode(); } #endif /* CONFIG_DEBUG_PAGEALLOC */ bool kernel_page_present(struct page *page) { unsigned int level; pte_t *pte; if (PageHighMem(page)) return false; pte = lookup_address((unsigned long)page_address(page), &level); return (pte_val(*pte) & _PAGE_PRESENT); } int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, unsigned numpages, unsigned long page_flags) { int retval = -EINVAL; struct cpa_data cpa = { .vaddr = &address, .pfn = pfn, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)), .flags = CPA_NO_CHECK_ALIAS, }; WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP"); if (!(__supported_pte_mask & _PAGE_NX)) goto out; if (!(page_flags & _PAGE_ENC)) cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); retval = __change_page_attr_set_clr(&cpa, 1); __flush_tlb_all(); out: return retval; } /* * __flush_tlb_all() flushes mappings only on current CPU and hence this * function shouldn't be used in an SMP environment. Presently, it's used only * during boot (way before smp_init()) by EFI subsystem and hence is ok. */ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, unsigned long numpages) { int retval; /* * The typical sequence for unmapping is to find a pte through * lookup_address_in_pgd() (ideally, it should never return NULL because * the address is already mapped) and change its protections. As pfn is * the *target* of a mapping, it's not useful while unmapping. */ struct cpa_data cpa = { .vaddr = &address, .pfn = 0, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), .flags = CPA_NO_CHECK_ALIAS, }; WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP"); retval = __change_page_attr_set_clr(&cpa, 1); __flush_tlb_all(); return retval; } /* * The testcases use internal knowledge of the implementation that shouldn't * be exposed to the rest of the kernel. Include these directly here. */ #ifdef CONFIG_CPA_DEBUG #include "cpa-test.c" #endif |
| 8 77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/eventfd.h * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_EVENTFD_H #define _LINUX_EVENTFD_H #include <linux/wait.h> #include <linux/err.h> #include <linux/percpu-defs.h> #include <linux/percpu.h> #include <linux/sched.h> #include <uapi/linux/eventfd.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from eventfd, in order to leave a free define-space for * shared O_* flags. */ #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) struct eventfd_ctx; struct file; #ifdef CONFIG_EVENTFD void eventfd_ctx_put(struct eventfd_ctx *ctx); struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); static inline bool eventfd_signal_allowed(void) { return !current->in_eventfd; } #else /* CONFIG_EVENTFD */ /* * Ugly ugly ugly error layer to support modules that uses eventfd but * pretend to work in !CONFIG_EVENTFD configurations. Namely, AIO. */ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd) { return ERR_PTR(-ENOSYS); } static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask) { } static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) { } static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt) { return -ENOSYS; } static inline bool eventfd_signal_allowed(void) { return true; } static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { } #endif static inline void eventfd_signal(struct eventfd_ctx *ctx) { eventfd_signal_mask(ctx, 0); } #endif /* _LINUX_EVENTFD_H */ |
| 3 1 2 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* Masquerade. Simple mapping which alters range to a local IP address (depending on route). */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_masquerade.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: automatic-address SNAT"); /* FIXME: Multiple targets. --RR */ static int masquerade_tg_check(const struct xt_tgchk_param *par) { const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) { pr_debug("bad MAP_IPS.\n"); return -EINVAL; } if (mr->rangesize != 1) { pr_debug("bad rangesize %u\n", mr->rangesize); return -EINVAL; } return nf_ct_netns_get(par->net, par->family); } static unsigned int masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_nat_range2 range; const struct nf_nat_ipv4_multi_range_compat *mr; mr = par->targinfo; range.flags = mr->range[0].flags; range.min_proto = mr->range[0].min; range.max_proto = mr->range[0].max; return nf_nat_masquerade_ipv4(skb, xt_hooknum(par), &range, xt_out(par)); } static void masquerade_tg_destroy(const struct xt_tgdtor_param *par) { nf_ct_netns_put(par->net, par->family); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) { return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par)); } static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) { const struct nf_nat_range2 *range = par->targinfo; if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; return nf_ct_netns_get(par->net, par->family); } #endif static struct xt_target masquerade_tg_reg[] __read_mostly = { { #if IS_ENABLED(CONFIG_IPV6) .name = "MASQUERADE", .family = NFPROTO_IPV6, .target = masquerade_tg6, .targetsize = sizeof(struct nf_nat_range), .table = "nat", .hooks = 1 << NF_INET_POST_ROUTING, .checkentry = masquerade_tg6_checkentry, .destroy = masquerade_tg_destroy, .me = THIS_MODULE, }, { #endif .name = "MASQUERADE", .family = NFPROTO_IPV4, .target = masquerade_tg, .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = 1 << NF_INET_POST_ROUTING, .checkentry = masquerade_tg_check, .destroy = masquerade_tg_destroy, .me = THIS_MODULE, } }; static int __init masquerade_tg_init(void) { int ret; ret = xt_register_targets(masquerade_tg_reg, ARRAY_SIZE(masquerade_tg_reg)); if (ret) return ret; ret = nf_nat_masquerade_inet_register_notifiers(); if (ret) { xt_unregister_targets(masquerade_tg_reg, ARRAY_SIZE(masquerade_tg_reg)); return ret; } return ret; } static void __exit masquerade_tg_exit(void) { xt_unregister_targets(masquerade_tg_reg, ARRAY_SIZE(masquerade_tg_reg)); nf_nat_masquerade_inet_unregister_notifiers(); } module_init(masquerade_tg_init); module_exit(masquerade_tg_exit); #if IS_ENABLED(CONFIG_IPV6) MODULE_ALIAS("ip6t_MASQUERADE"); #endif MODULE_ALIAS("ipt_MASQUERADE"); |
| 2 589 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SUSPEND_H #define _LINUX_SUSPEND_H #include <linux/swap.h> #include <linux/notifier.h> #include <linux/init.h> #include <linux/pm.h> #include <linux/mm.h> #include <linux/freezer.h> #include <asm/errno.h> #ifdef CONFIG_VT extern void pm_set_vt_switch(int); #else static inline void pm_set_vt_switch(int do_switch) { } #endif #ifdef CONFIG_VT_CONSOLE_SLEEP extern void pm_prepare_console(void); extern void pm_restore_console(void); #else static inline void pm_prepare_console(void) { } static inline void pm_restore_console(void) { } #endif typedef int __bitwise suspend_state_t; #define PM_SUSPEND_ON ((__force suspend_state_t) 0) #define PM_SUSPEND_TO_IDLE ((__force suspend_state_t) 1) #define PM_SUSPEND_STANDBY ((__force suspend_state_t) 2) #define PM_SUSPEND_MEM ((__force suspend_state_t) 3) #define PM_SUSPEND_MIN PM_SUSPEND_TO_IDLE #define PM_SUSPEND_MAX ((__force suspend_state_t) 4) /** * struct platform_suspend_ops - Callbacks for managing platform dependent * system sleep states. * * @valid: Callback to determine if given system sleep state is supported by * the platform. * Valid (ie. supported) states are advertised in /sys/power/state. Note * that it still may be impossible to enter given system sleep state if the * conditions aren't right. * There is the %suspend_valid_only_mem function available that can be * assigned to this if the platform only supports mem sleep. * * @begin: Initialise a transition to given system sleep state. * @begin() is executed right prior to suspending devices. The information * conveyed to the platform code by @begin() should be disregarded by it as * soon as @end() is executed. If @begin() fails (ie. returns nonzero), * @prepare(), @enter() and @finish() will not be called by the PM core. * This callback is optional. However, if it is implemented, the argument * passed to @enter() is redundant and should be ignored. * * @prepare: Prepare the platform for entering the system sleep state indicated * by @begin(). * @prepare() is called right after devices have been suspended (ie. the * appropriate .suspend() method has been executed for each device) and * before device drivers' late suspend callbacks are executed. It returns * 0 on success or a negative error code otherwise, in which case the * system cannot enter the desired sleep state (@prepare_late(), @enter(), * and @wake() will not be called in that case). * * @prepare_late: Finish preparing the platform for entering the system sleep * state indicated by @begin(). * @prepare_late is called before disabling nonboot CPUs and after * device drivers' late suspend callbacks have been executed. It returns * 0 on success or a negative error code otherwise, in which case the * system cannot enter the desired sleep state (@enter() will not be * executed). * * @enter: Enter the system sleep state indicated by @begin() or represented by * the argument if @begin() is not implemented. * This callback is mandatory. It returns 0 on success or a negative * error code otherwise, in which case the system cannot enter the desired * sleep state. * * @wake: Called when the system has just left a sleep state, right after * the nonboot CPUs have been enabled and before device drivers' early * resume callbacks are executed. * This callback is optional, but should be implemented by the platforms * that implement @prepare_late(). If implemented, it is always called * after @prepare_late and @enter(), even if one of them fails. * * @finish: Finish wake-up of the platform. * @finish is called right prior to calling device drivers' regular suspend * callbacks. * This callback is optional, but should be implemented by the platforms * that implement @prepare(). If implemented, it is always called after * @enter() and @wake(), even if any of them fails. It is executed after * a failing @prepare. * * @suspend_again: Returns whether the system should suspend again (true) or * not (false). If the platform wants to poll sensors or execute some * code during suspended without invoking userspace and most of devices, * suspend_again callback is the place assuming that periodic-wakeup or * alarm-wakeup is already setup. This allows to execute some codes while * being kept suspended in the view of userland and devices. * * @end: Called by the PM core right after resuming devices, to indicate to * the platform that the system has returned to the working state or * the transition to the sleep state has been aborted. * This callback is optional, but should be implemented by the platforms * that implement @begin(). Accordingly, platforms implementing @begin() * should also provide a @end() which cleans up transitions aborted before * @enter(). * * @recover: Recover the platform from a suspend failure. * Called by the PM core if the suspending of devices fails. * This callback is optional and should only be implemented by platforms * which require special recovery actions in that situation. */ struct platform_suspend_ops { int (*valid)(suspend_state_t state); int (*begin)(suspend_state_t state); int (*prepare)(void); int (*prepare_late)(void); int (*enter)(suspend_state_t state); void (*wake)(void); void (*finish)(void); bool (*suspend_again)(void); void (*end)(void); void (*recover)(void); }; struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); int (*prepare_late)(void); void (*check)(void); bool (*wake)(void); void (*restore_early)(void); void (*restore)(void); void (*end)(void); }; #ifdef CONFIG_SUSPEND extern suspend_state_t pm_suspend_target_state; extern suspend_state_t mem_sleep_current; extern suspend_state_t mem_sleep_default; /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. */ extern void suspend_set_ops(const struct platform_suspend_ops *ops); extern int suspend_valid_only_mem(suspend_state_t state); extern unsigned int pm_suspend_global_flags; #define PM_SUSPEND_FLAG_FW_SUSPEND BIT(0) #define PM_SUSPEND_FLAG_FW_RESUME BIT(1) #define PM_SUSPEND_FLAG_NO_PLATFORM BIT(2) static inline void pm_suspend_clear_flags(void) { pm_suspend_global_flags = 0; } static inline void pm_set_suspend_via_firmware(void) { pm_suspend_global_flags |= PM_SUSPEND_FLAG_FW_SUSPEND; } static inline void pm_set_resume_via_firmware(void) { pm_suspend_global_flags |= PM_SUSPEND_FLAG_FW_RESUME; } static inline void pm_set_suspend_no_platform(void) { pm_suspend_global_flags |= PM_SUSPEND_FLAG_NO_PLATFORM; } /** * pm_suspend_via_firmware - Check if platform firmware will suspend the system. * * To be called during system-wide power management transitions to sleep states * or during the subsequent system-wide transitions back to the working state. * * Return 'true' if the platform firmware is going to be invoked at the end of * the system-wide power management transition (to a sleep state) in progress in * order to complete it, or if the platform firmware has been invoked in order * to complete the last (or preceding) transition of the system to a sleep * state. * * This matters if the caller needs or wants to carry out some special actions * depending on whether or not control will be passed to the platform firmware * subsequently (for example, the device may need to be reset before letting the * platform firmware manipulate it, which is not necessary when the platform * firmware is not going to be invoked) or when such special actions may have * been carried out during the preceding transition of the system to a sleep * state (as they may need to be taken into account). */ static inline bool pm_suspend_via_firmware(void) { return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_FW_SUSPEND); } /** * pm_resume_via_firmware - Check if platform firmware has woken up the system. * * To be called during system-wide power management transitions from sleep * states. * * Return 'true' if the platform firmware has passed control to the kernel at * the beginning of the system-wide power management transition in progress, so * the event that woke up the system from sleep has been handled by the platform * firmware. */ static inline bool pm_resume_via_firmware(void) { return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_FW_RESUME); } /** * pm_suspend_no_platform - Check if platform may change device power states. * * To be called during system-wide power management transitions to sleep states * or during the subsequent system-wide transitions back to the working state. * * Return 'true' if the power states of devices remain under full control of the * kernel throughout the system-wide suspend and resume cycle in progress (that * is, if a device is put into a certain power state during suspend, it can be * expected to remain in that state during resume). */ static inline bool pm_suspend_no_platform(void) { return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_NO_PLATFORM); } /* Suspend-to-idle state machnine. */ enum s2idle_states { S2IDLE_STATE_NONE, /* Not suspended/suspending. */ S2IDLE_STATE_ENTER, /* Enter suspend-to-idle. */ S2IDLE_STATE_WAKE, /* Wake up from suspend-to-idle. */ }; extern enum s2idle_states __read_mostly s2idle_state; static inline bool idle_should_enter_s2idle(void) { return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } extern bool pm_suspend_default_s2idle(void); extern void __init pm_states_init(void); extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); extern void s2idle_wake(void); /** * arch_suspend_disable_irqs - disable IRQs for suspend * * Disables IRQs (in the default case). This is a weak symbol in the common * code and thus allows architectures to override it if more needs to be * done. Not called for suspend to disk. */ extern void arch_suspend_disable_irqs(void); /** * arch_suspend_enable_irqs - enable IRQs after suspend * * Enables IRQs (in the default case). This is a weak symbol in the common * code and thus allows architectures to override it if more needs to be * done. Not called for suspend to disk. */ extern void arch_suspend_enable_irqs(void); extern int pm_suspend(suspend_state_t state); extern bool sync_on_suspend_enabled; #else /* !CONFIG_SUSPEND */ #define suspend_valid_only_mem NULL #define pm_suspend_target_state (PM_SUSPEND_ON) static inline void pm_suspend_clear_flags(void) {} static inline void pm_set_suspend_via_firmware(void) {} static inline void pm_set_resume_via_firmware(void) {} static inline bool pm_suspend_via_firmware(void) { return false; } static inline bool pm_resume_via_firmware(void) { return false; } static inline bool pm_suspend_no_platform(void) { return false; } static inline bool pm_suspend_default_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } static inline bool sync_on_suspend_enabled(void) { return true; } static inline bool idle_should_enter_s2idle(void) { return false; } static inline void __init pm_states_init(void) {} static inline void s2idle_set_ops(const struct platform_s2idle_ops *ops) {} static inline void s2idle_wake(void) {} #endif /* !CONFIG_SUSPEND */ static inline bool pm_suspend_in_progress(void) { return pm_suspend_target_state != PM_SUSPEND_ON; } /* struct pbe is used for creating lists of pages that should be restored * atomically during the resume from disk, because the page frames they have * occupied before the suspend are in use. */ struct pbe { void *address; /* address of the copy */ void *orig_address; /* original address of a page */ struct pbe *next; }; /** * struct platform_hibernation_ops - hibernation platform support * * The methods in this structure allow a platform to carry out special * operations required by it during a hibernation transition. * * All the methods below, except for @recover(), must be implemented. * * @begin: Tell the platform driver that we're starting hibernation. * Called right after shrinking memory and before freezing devices. * * @end: Called by the PM core right after resuming devices, to indicate to * the platform that the system has returned to the working state. * * @pre_snapshot: Prepare the platform for creating the hibernation image. * Called right after devices have been frozen and before the nonboot * CPUs are disabled (runs with IRQs on). * * @finish: Restore the previous state of the platform after the hibernation * image has been created *or* put the platform into the normal operation * mode after the hibernation (the same method is executed in both cases). * Called right after the nonboot CPUs have been enabled and before * thawing devices (runs with IRQs on). * * @prepare: Prepare the platform for entering the low power state. * Called right after the hibernation image has been saved and before * devices are prepared for entering the low power state. * * @enter: Put the system into the low power state after the hibernation image * has been saved to disk. * Called after the nonboot CPUs have been disabled and all of the low * level devices have been shut down (runs with IRQs off). * * @leave: Perform the first stage of the cleanup after the system sleep state * indicated by @set_target() has been left. * Called right after the control has been passed from the boot kernel to * the image kernel, before the nonboot CPUs are enabled and before devices * are resumed. Executed with interrupts disabled. * * @pre_restore: Prepare system for the restoration from a hibernation image. * Called right after devices have been frozen and before the nonboot * CPUs are disabled (runs with IRQs on). * * @restore_cleanup: Clean up after a failing image restoration. * Called right after the nonboot CPUs have been enabled and before * thawing devices (runs with IRQs on). * * @recover: Recover the platform from a failure to suspend devices. * Called by the PM core if the suspending of devices during hibernation * fails. This callback is optional and should only be implemented by * platforms which require special recovery actions in that situation. */ struct platform_hibernation_ops { int (*begin)(pm_message_t stage); void (*end)(void); int (*pre_snapshot)(void); void (*finish)(void); int (*prepare)(void); int (*enter)(void); void (*leave)(void); int (*pre_restore)(void); void (*restore_cleanup)(void); void (*recover)(void); }; #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ extern void register_nosave_region(unsigned long b, unsigned long e); extern int swsusp_page_is_forbidden(struct page *); extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); extern unsigned long get_safe_page(gfp_t gfp_mask); extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); extern u32 swsusp_hardware_signature; extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); extern bool hibernation_available(void); asmlinkage int swsusp_save(void); extern struct pbe *restore_pblist; int pfn_is_nosave(unsigned long pfn); int hibernate_quiet_exec(int (*func)(void *data), void *data); int hibernate_resume_nonboot_cpu_disable(void); int arch_hibernation_header_save(void *addr, unsigned int max_size); int arch_hibernation_header_restore(void *addr); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} static inline void hibernation_set_ops(const struct platform_hibernation_ops *ops) {} static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } static inline bool hibernation_available(void) { return false; } static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) { return -ENOTSUPP; } #endif /* CONFIG_HIBERNATION */ #if defined(CONFIG_HIBERNATION) && defined(CONFIG_SUSPEND) bool pm_hibernation_mode_is_suspend(void); #else static inline bool pm_hibernation_mode_is_suspend(void) { return false; } #endif int arch_resume_nosmt(void); #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV int is_hibernate_resume_dev(dev_t dev); #else static inline int is_hibernate_resume_dev(dev_t dev) { return 0; } #endif /* Hibernation and suspend events */ #define PM_HIBERNATION_PREPARE 0x0001 /* Going to hibernate */ #define PM_POST_HIBERNATION 0x0002 /* Hibernation finished */ #define PM_SUSPEND_PREPARE 0x0003 /* Going to suspend the system */ #define PM_POST_SUSPEND 0x0004 /* Suspend finished */ #define PM_RESTORE_PREPARE 0x0005 /* Going to restore a saved image */ #define PM_POST_RESTORE 0x0006 /* Restore failed */ extern struct mutex system_transition_mutex; #ifdef CONFIG_PM_SLEEP void save_processor_state(void); void restore_processor_state(void); /* kernel/power/main.c */ extern int register_pm_notifier(struct notifier_block *nb); extern int unregister_pm_notifier(struct notifier_block *nb); extern void ksys_sync_helper(void); extern void pm_report_hw_sleep_time(u64 t); extern void pm_report_max_hw_sleep(u64 t); void pm_restrict_gfp_mask(void); void pm_restore_gfp_mask(void); #define pm_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ { .notifier_call = fn, .priority = pri }; \ register_pm_notifier(&fn##_nb); \ } /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; static inline bool pm_suspended_storage(void) { return !gfp_has_io_fs(gfp_allowed_mask); } extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); extern void pm_system_cancel_wakeup(void); extern void pm_wakeup_clear(unsigned int irq_number); extern void pm_system_irq_wakeup(unsigned int irq_number); extern unsigned int pm_wakeup_irq(void); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); extern void pm_print_active_wakeup_sources(void); extern unsigned int lock_system_sleep(void); extern void unlock_system_sleep(unsigned int); extern bool pm_sleep_transition_in_progress(void); bool pm_hibernate_is_recovering(void); #else /* !CONFIG_PM_SLEEP */ static inline int register_pm_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_pm_notifier(struct notifier_block *nb) { return 0; } static inline void pm_report_hw_sleep_time(u64 t) {}; static inline void pm_report_max_hw_sleep(u64 t) {}; static inline void pm_restrict_gfp_mask(void) {} static inline void pm_restore_gfp_mask(void) {} static inline void ksys_sync_helper(void) {} #define pm_notifier(fn, pri) do { (void)(fn); } while (0) static inline bool pm_suspended_storage(void) { return false; } static inline bool pm_wakeup_pending(void) { return false; } static inline void pm_system_wakeup(void) {} static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} static inline unsigned int lock_system_sleep(void) { return 0; } static inline void unlock_system_sleep(unsigned int flags) {} static inline bool pm_sleep_transition_in_progress(void) { return false; } static inline bool pm_hibernate_is_recovering(void) { return false; } #endif /* !CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; extern bool pm_debug_messages_on; extern bool pm_debug_messages_should_print(void); static inline int pm_dyn_debug_messages_on(void) { #ifdef CONFIG_DYNAMIC_DEBUG return 1; #else return 0; #endif } #ifndef pr_fmt #define pr_fmt(fmt) "PM: " fmt #endif #define __pm_pr_dbg(fmt, ...) \ do { \ if (pm_debug_messages_should_print()) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ else if (pm_dyn_debug_messages_on()) \ pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #define __pm_deferred_pr_dbg(fmt, ...) \ do { \ if (pm_debug_messages_should_print()) \ printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #else #define pm_print_times_enabled (false) #define pm_debug_messages_on (false) #include <linux/printk.h> #define __pm_pr_dbg(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #define __pm_deferred_pr_dbg(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /** * pm_pr_dbg - print pm sleep debug messages * * If pm_debug_messages_on is enabled and the system is entering/leaving * suspend, print message. * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, * print message only from instances explicitly enabled on dynamic debug's * control. * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, * don't print message. */ #define pm_pr_dbg(fmt, ...) \ __pm_pr_dbg(fmt, ##__VA_ARGS__) #define pm_deferred_pr_dbg(fmt, ...) \ __pm_deferred_pr_dbg(fmt, ##__VA_ARGS__) #ifdef CONFIG_PM_AUTOSLEEP /* kernel/power/autosleep.c */ void queue_up_suspend_work(void); #else /* !CONFIG_PM_AUTOSLEEP */ static inline void queue_up_suspend_work(void) {} #endif /* !CONFIG_PM_AUTOSLEEP */ enum suspend_stat_step { SUSPEND_WORKING = 0, SUSPEND_FREEZE, SUSPEND_PREPARE, SUSPEND_SUSPEND, SUSPEND_SUSPEND_LATE, SUSPEND_SUSPEND_NOIRQ, SUSPEND_RESUME_NOIRQ, SUSPEND_RESUME_EARLY, SUSPEND_RESUME }; void dpm_save_failed_dev(const char *name); void dpm_save_failed_step(enum suspend_stat_step step); #endif /* _LINUX_SUSPEND_H */ |
| 3 1 1 1 1 3 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" struct wol_req_info { struct ethnl_req_info base; }; struct wol_reply_data { struct ethnl_reply_data base; struct ethtool_wolinfo wol; bool show_sopass; }; #define WOL_REPDATA(__reply_base) \ container_of(__reply_base, struct wol_reply_data, base) const struct nla_policy ethnl_wol_get_policy[] = { [ETHTOOL_A_WOL_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int wol_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct wol_reply_data *data = WOL_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; dev->ethtool_ops->get_wol(dev, &data->wol); ethnl_ops_complete(dev); /* do not include password in notifications */ data->show_sopass = !genl_info_is_ntf(info) && (data->wol.supported & WAKE_MAGICSECURE); return 0; } static int wol_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct wol_reply_data *data = WOL_REPDATA(reply_base); int len; len = ethnl_bitset32_size(&data->wol.wolopts, &data->wol.supported, WOL_MODE_COUNT, wol_mode_names, compact); if (len < 0) return len; if (data->show_sopass) len += nla_total_size(sizeof(data->wol.sopass)); return len; } static int wol_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct wol_reply_data *data = WOL_REPDATA(reply_base); int ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_WOL_MODES, &data->wol.wolopts, &data->wol.supported, WOL_MODE_COUNT, wol_mode_names, compact); if (ret < 0) return ret; if (data->show_sopass && nla_put(skb, ETHTOOL_A_WOL_SOPASS, sizeof(data->wol.sopass), data->wol.sopass)) return -EMSGSIZE; return 0; } /* WOL_SET */ const struct nla_policy ethnl_wol_set_policy[] = { [ETHTOOL_A_WOL_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_WOL_MODES] = { .type = NLA_NESTED }, [ETHTOOL_A_WOL_SOPASS] = { .type = NLA_BINARY, .len = SOPASS_MAX }, }; static int ethnl_set_wol_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_wol && ops->set_wol ? 1 : -EOPNOTSUPP; } static int ethnl_set_wol(struct ethnl_req_info *req_info, struct genl_info *info) { struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; bool mod = false; int ret; dev->ethtool_ops->get_wol(dev, &wol); ret = ethnl_update_bitset32(&wol.wolopts, WOL_MODE_COUNT, tb[ETHTOOL_A_WOL_MODES], wol_mode_names, info->extack, &mod); if (ret < 0) return ret; if (wol.wolopts & ~wol.supported) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_WOL_MODES], "cannot enable unsupported WoL mode"); return -EINVAL; } if (tb[ETHTOOL_A_WOL_SOPASS]) { if (!(wol.supported & WAKE_MAGICSECURE)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_WOL_SOPASS], "magicsecure not supported, cannot set password"); return -EINVAL; } ethnl_update_binary(wol.sopass, sizeof(wol.sopass), tb[ETHTOOL_A_WOL_SOPASS], &mod); } if (!mod) return 0; ret = dev->ethtool_ops->set_wol(dev, &wol); if (ret) return ret; dev->ethtool->wol_enabled = !!wol.wolopts; return 1; } const struct ethnl_request_ops ethnl_wol_request_ops = { .request_cmd = ETHTOOL_MSG_WOL_GET, .reply_cmd = ETHTOOL_MSG_WOL_GET_REPLY, .hdr_attr = ETHTOOL_A_WOL_HEADER, .req_info_size = sizeof(struct wol_req_info), .reply_data_size = sizeof(struct wol_reply_data), .prepare_data = wol_prepare_data, .reply_size = wol_reply_size, .fill_reply = wol_fill_reply, .set_validate = ethnl_set_wol_validate, .set = ethnl_set_wol, .set_ntf_cmd = ETHTOOL_MSG_WOL_NTF, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * AppArmor security module * * This file contains AppArmor auditing function definitions. * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #ifndef __AA_AUDIT_H #define __AA_AUDIT_H #include <linux/audit.h> #include <linux/fs.h> #include <linux/lsm_audit.h> #include <linux/sched.h> #include <linux/slab.h> #include "file.h" #include "label.h" extern const char *const audit_mode_names[]; #define AUDIT_MAX_INDEX 5 enum audit_mode { AUDIT_NORMAL, /* follow normal auditing of accesses */ AUDIT_QUIET_DENIED, /* quiet all denied access messages */ AUDIT_QUIET, /* quiet all messages */ AUDIT_NOQUIET, /* do not quiet audit messages */ AUDIT_ALL /* audit all accesses */ }; enum audit_type { AUDIT_APPARMOR_AUDIT, AUDIT_APPARMOR_ALLOWED, AUDIT_APPARMOR_DENIED, AUDIT_APPARMOR_HINT, AUDIT_APPARMOR_STATUS, AUDIT_APPARMOR_ERROR, AUDIT_APPARMOR_KILL, AUDIT_APPARMOR_AUTO }; #define OP_NULL NULL #define OP_SYSCTL "sysctl" #define OP_CAPABLE "capable" #define OP_UNLINK "unlink" #define OP_MKDIR "mkdir" #define OP_RMDIR "rmdir" #define OP_MKNOD "mknod" #define OP_TRUNC "truncate" #define OP_LINK "link" #define OP_SYMLINK "symlink" #define OP_RENAME_SRC "rename_src" #define OP_RENAME_DEST "rename_dest" #define OP_CHMOD "chmod" #define OP_CHOWN "chown" #define OP_GETATTR "getattr" #define OP_OPEN "open" #define OP_FRECEIVE "file_receive" #define OP_FPERM "file_perm" #define OP_FLOCK "file_lock" #define OP_FMMAP "file_mmap" #define OP_FMPROT "file_mprotect" #define OP_INHERIT "file_inherit" #define OP_PIVOTROOT "pivotroot" #define OP_MOUNT "mount" #define OP_UMOUNT "umount" #define OP_CREATE "create" #define OP_POST_CREATE "post_create" #define OP_BIND "bind" #define OP_CONNECT "connect" #define OP_LISTEN "listen" #define OP_ACCEPT "accept" #define OP_SENDMSG "sendmsg" #define OP_RECVMSG "recvmsg" #define OP_GETSOCKNAME "getsockname" #define OP_GETPEERNAME "getpeername" #define OP_GETSOCKOPT "getsockopt" #define OP_SETSOCKOPT "setsockopt" #define OP_SHUTDOWN "socket_shutdown" #define OP_PTRACE "ptrace" #define OP_SIGNAL "signal" #define OP_EXEC "exec" #define OP_CHANGE_HAT "change_hat" #define OP_CHANGE_PROFILE "change_profile" #define OP_CHANGE_ONEXEC "change_onexec" #define OP_STACK "stack" #define OP_STACK_ONEXEC "stack_onexec" #define OP_SETPROCATTR "setprocattr" #define OP_SETRLIMIT "setrlimit" #define OP_PROF_REPL "profile_replace" #define OP_PROF_LOAD "profile_load" #define OP_PROF_RM "profile_remove" #define OP_USERNS_CREATE "userns_create" #define OP_URING_OVERRIDE "uring_override" #define OP_URING_SQPOLL "uring_sqpoll" struct apparmor_audit_data { int error; int type; u16 class; const char *op; const struct cred *subj_cred; struct aa_label *subj_label; const char *name; const char *info; u32 request; u32 denied; union { /* these entries require a custom callback fn */ struct { struct aa_label *peer; union { struct { const char *target; kuid_t ouid; } fs; struct { int rlim; unsigned long max; } rlim; struct { int signal; int unmappedsig; }; struct { int type, protocol; void *addr; int addrlen; struct { void *addr; int addrlen; } peer; } net; }; }; struct { struct aa_profile *profile; const char *ns; long pos; } iface; struct { const char *src_name; const char *type; const char *trans; const char *data; unsigned long flags; } mnt; struct { struct aa_label *target; } uring; }; struct common_audit_data common; }; /* macros for dealing with apparmor_audit_data structure */ #define aad(SA) (container_of(SA, struct apparmor_audit_data, common)) #define aad_of_va(VA) aad((struct common_audit_data *)(VA)) #define DEFINE_AUDIT_DATA(NAME, T, C, X) \ /* TODO: cleanup audit init so we don't need _aad = {0,} */ \ struct apparmor_audit_data NAME = { \ .class = (C), \ .op = (X), \ .common.type = (T), \ .common.u.tsk = NULL, \ .common.apparmor_audit_data = &NAME, \ }; void aa_audit_msg(int type, struct apparmor_audit_data *ad, void (*cb) (struct audit_buffer *, void *)); int aa_audit(int type, struct aa_profile *profile, struct apparmor_audit_data *ad, void (*cb) (struct audit_buffer *, void *)); #define aa_audit_error(ERROR, AD, CB) \ ({ \ (AD)->error = (ERROR); \ aa_audit_msg(AUDIT_APPARMOR_ERROR, (AD), (CB)); \ (AD)->error; \ }) static inline int complain_error(int error) { if (error == -EPERM || error == -EACCES) return 0; return error; } void aa_audit_rule_free(void *vrule); int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp); int aa_audit_rule_known(struct audit_krule *rule); int aa_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *vrule); #endif /* __AA_AUDIT_H */ |
| 4 3 4 4 3 4 25 24 18 25 98 18 3 6 4 4 11 2 2 1 1 4 2 2 2 2 3 2 2 2 2 2 98 25 4 3 2 2 1 2 3 2 2 1 2 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * OSS compatible i/o control * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include "seq_oss_timer.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_event.h" static int snd_seq_oss_synth_info_user(struct seq_oss_devinfo *dp, void __user *arg) { struct synth_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; if (snd_seq_oss_synth_make_info(dp, info.device, &info) < 0) return -EINVAL; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_seq_oss_midi_info_user(struct seq_oss_devinfo *dp, void __user *arg) { struct midi_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; if (snd_seq_oss_midi_make_info(dp, info.device, &info) < 0) return -EINVAL; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_seq_oss_oob_user(struct seq_oss_devinfo *dp, void __user *arg) { unsigned char ev[8]; struct snd_seq_event tmpev; if (copy_from_user(ev, arg, 8)) return -EFAULT; memset(&tmpev, 0, sizeof(tmpev)); snd_seq_oss_fill_addr(dp, &tmpev, dp->addr.client, dp->addr.port); tmpev.time.tick = 0; if (! snd_seq_oss_process_event(dp, (union evrec *)ev, &tmpev)) { snd_seq_oss_dispatch(dp, &tmpev, 0, 0); } return 0; } int snd_seq_oss_ioctl(struct seq_oss_devinfo *dp, unsigned int cmd, unsigned long carg) { int dev, val; void __user *arg = (void __user *)carg; int __user *p = arg; switch (cmd) { case SNDCTL_TMR_TIMEBASE: case SNDCTL_TMR_TEMPO: case SNDCTL_TMR_START: case SNDCTL_TMR_STOP: case SNDCTL_TMR_CONTINUE: case SNDCTL_TMR_METRONOME: case SNDCTL_TMR_SOURCE: case SNDCTL_TMR_SELECT: case SNDCTL_SEQ_CTRLRATE: return snd_seq_oss_timer_ioctl(dp->timer, cmd, arg); case SNDCTL_SEQ_PANIC: snd_seq_oss_reset(dp); return -EINVAL; case SNDCTL_SEQ_SYNC: if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return 0; while (snd_seq_oss_writeq_sync(dp->writeq)) ; if (signal_pending(current)) return -ERESTARTSYS; return 0; case SNDCTL_SEQ_RESET: snd_seq_oss_reset(dp); return 0; case SNDCTL_SEQ_TESTMIDI: if (get_user(dev, p)) return -EFAULT; return snd_seq_oss_midi_open(dp, dev, dp->file_mode); case SNDCTL_SEQ_GETINCOUNT: if (dp->readq == NULL || ! is_read_mode(dp->file_mode)) return 0; return put_user(dp->readq->qlen, p) ? -EFAULT : 0; case SNDCTL_SEQ_GETOUTCOUNT: if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return 0; return put_user(snd_seq_oss_writeq_get_free_size(dp->writeq), p) ? -EFAULT : 0; case SNDCTL_SEQ_GETTIME: return put_user(snd_seq_oss_timer_cur_tick(dp->timer), p) ? -EFAULT : 0; case SNDCTL_SEQ_RESETSAMPLES: if (get_user(dev, p)) return -EFAULT; return snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); case SNDCTL_SEQ_NRSYNTHS: return put_user(dp->max_synthdev, p) ? -EFAULT : 0; case SNDCTL_SEQ_NRMIDIS: return put_user(dp->max_mididev, p) ? -EFAULT : 0; case SNDCTL_SYNTH_MEMAVL: if (get_user(dev, p)) return -EFAULT; val = snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); return put_user(val, p) ? -EFAULT : 0; case SNDCTL_FM_4OP_ENABLE: if (get_user(dev, p)) return -EFAULT; snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); return 0; case SNDCTL_SYNTH_INFO: case SNDCTL_SYNTH_ID: return snd_seq_oss_synth_info_user(dp, arg); case SNDCTL_SEQ_OUTOFBAND: return snd_seq_oss_oob_user(dp, arg); case SNDCTL_MIDI_INFO: return snd_seq_oss_midi_info_user(dp, arg); case SNDCTL_SEQ_THRESHOLD: if (! is_write_mode(dp->file_mode)) return 0; if (get_user(val, p)) return -EFAULT; if (val < 1) val = 1; if (val >= dp->writeq->maxlen) val = dp->writeq->maxlen - 1; snd_seq_oss_writeq_set_output(dp->writeq, val); return 0; case SNDCTL_MIDI_PRETIME: if (dp->readq == NULL || !is_read_mode(dp->file_mode)) return 0; if (get_user(val, p)) return -EFAULT; if (val <= 0) val = -1; else val = (HZ * val) / 10; dp->readq->pre_event_timeout = val; return put_user(val, p) ? -EFAULT : 0; default: if (! is_write_mode(dp->file_mode)) return -EIO; return snd_seq_oss_synth_ioctl(dp, 0, cmd, carg); } return 0; } |
| 20 20 20 20 4 4 20 4 4 4 4 20 3 20 20 4 4 20 4 1 1 20 4 20 20 20 20 20 20 20 13 13 13 13 13 13 13 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 | // SPDX-License-Identifier: GPL-2.0-only /* * Ram backed block device driver. * * Copyright (C) 2007 Nick Piggin * Copyright (C) 2007 Novell Inc. * * Parts derived from drivers/block/rd.c, and drivers/block/loop.c, copyright * of their respective owners. */ #include <linux/init.h> #include <linux/initrd.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/major.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/pagemap.h> #include <linux/xarray.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/debugfs.h> #include <linux/uaccess.h> /* * Each block ramdisk device has a xarray brd_pages of pages that stores * the pages containing the block device's contents. */ struct brd_device { int brd_number; struct gendisk *brd_disk; struct list_head brd_list; /* * Backing store of pages. This is the contents of the block device. */ struct xarray brd_pages; u64 brd_nr_pages; }; /* * Look up and return a brd's page with reference grabbed for a given sector. */ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) { struct page *page; XA_STATE(xas, &brd->brd_pages, sector >> PAGE_SECTORS_SHIFT); rcu_read_lock(); repeat: page = xas_load(&xas); if (xas_retry(&xas, page)) { xas_reset(&xas); goto repeat; } if (!page) goto out; if (!get_page_unless_zero(page)) { xas_reset(&xas); goto repeat; } if (unlikely(page != xas_reload(&xas))) { put_page(page); xas_reset(&xas); goto repeat; } out: rcu_read_unlock(); return page; } /* * Insert a new page for a given sector, if one does not already exist. * The returned page will grab reference. */ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector, blk_opf_t opf) { gfp_t gfp = (opf & REQ_NOWAIT) ? GFP_NOWAIT : GFP_NOIO; struct page *page, *ret; page = alloc_page(gfp | __GFP_ZERO | __GFP_HIGHMEM); if (!page) return ERR_PTR(-ENOMEM); xa_lock(&brd->brd_pages); ret = __xa_cmpxchg(&brd->brd_pages, sector >> PAGE_SECTORS_SHIFT, NULL, page, gfp); if (!ret) { brd->brd_nr_pages++; get_page(page); xa_unlock(&brd->brd_pages); return page; } if (!xa_is_err(ret)) { get_page(ret); xa_unlock(&brd->brd_pages); put_page(page); return ret; } xa_unlock(&brd->brd_pages); put_page(page); return ERR_PTR(xa_err(ret)); } /* * Free all backing store pages and xarray. This must only be called when * there are no other users of the device. */ static void brd_free_pages(struct brd_device *brd) { struct page *page; pgoff_t idx; xa_for_each(&brd->brd_pages, idx, page) { put_page(page); cond_resched(); } xa_destroy(&brd->brd_pages); } /* * Process a single segment. The segment is capped to not cross page boundaries * in both the bio and the brd backing memory. */ static bool brd_rw_bvec(struct brd_device *brd, struct bio *bio) { struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter); sector_t sector = bio->bi_iter.bi_sector; u32 offset = (sector & (PAGE_SECTORS - 1)) << SECTOR_SHIFT; blk_opf_t opf = bio->bi_opf; struct page *page; void *kaddr; bv.bv_len = min_t(u32, bv.bv_len, PAGE_SIZE - offset); page = brd_lookup_page(brd, sector); if (!page && op_is_write(opf)) { page = brd_insert_page(brd, sector, opf); if (IS_ERR(page)) goto out_error; } kaddr = bvec_kmap_local(&bv); if (op_is_write(opf)) { memcpy_to_page(page, offset, kaddr, bv.bv_len); } else { if (page) memcpy_from_page(kaddr, page, offset, bv.bv_len); else memset(kaddr, 0, bv.bv_len); } kunmap_local(kaddr); bio_advance_iter_single(bio, &bio->bi_iter, bv.bv_len); if (page) put_page(page); return true; out_error: if (PTR_ERR(page) == -ENOMEM && (opf & REQ_NOWAIT)) bio_wouldblock_error(bio); else bio_io_error(bio); return false; } static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size) { sector_t aligned_sector = round_up(sector, PAGE_SECTORS); sector_t aligned_end = round_down( sector + (size >> SECTOR_SHIFT), PAGE_SECTORS); struct page *page; if (aligned_end <= aligned_sector) return; xa_lock(&brd->brd_pages); while (aligned_sector < aligned_end && aligned_sector < rd_size * 2) { page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT); if (page) { put_page(page); brd->brd_nr_pages--; } aligned_sector += PAGE_SECTORS; } xa_unlock(&brd->brd_pages); } static void brd_submit_bio(struct bio *bio) { struct brd_device *brd = bio->bi_bdev->bd_disk->private_data; if (unlikely(op_is_discard(bio->bi_opf))) { brd_do_discard(brd, bio->bi_iter.bi_sector, bio->bi_iter.bi_size); bio_endio(bio); return; } do { if (!brd_rw_bvec(brd, bio)) return; } while (bio->bi_iter.bi_size); bio_endio(bio); } static const struct block_device_operations brd_fops = { .owner = THIS_MODULE, .submit_bio = brd_submit_bio, }; /* * And now the modules code and kernel interface. */ static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT; module_param(rd_nr, int, 0444); MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices"); unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE; module_param(rd_size, ulong, 0444); MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes."); static int max_part = 1; module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices"); MODULE_DESCRIPTION("Ram backed block device driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR); MODULE_ALIAS("rd"); #ifndef MODULE /* Legacy boot options - nonmodular */ static int __init ramdisk_size(char *str) { rd_size = simple_strtol(str, NULL, 0); return 1; } __setup("ramdisk_size=", ramdisk_size); #endif /* * The device scheme is derived from loop.c. Keep them in synch where possible * (should share code eventually). */ static LIST_HEAD(brd_devices); static DEFINE_MUTEX(brd_devices_mutex); static struct dentry *brd_debugfs_dir; static struct brd_device *brd_find_or_alloc_device(int i) { struct brd_device *brd; mutex_lock(&brd_devices_mutex); list_for_each_entry(brd, &brd_devices, brd_list) { if (brd->brd_number == i) { mutex_unlock(&brd_devices_mutex); return ERR_PTR(-EEXIST); } } brd = kzalloc(sizeof(*brd), GFP_KERNEL); if (!brd) { mutex_unlock(&brd_devices_mutex); return ERR_PTR(-ENOMEM); } brd->brd_number = i; list_add_tail(&brd->brd_list, &brd_devices); mutex_unlock(&brd_devices_mutex); return brd; } static void brd_free_device(struct brd_device *brd) { mutex_lock(&brd_devices_mutex); list_del(&brd->brd_list); mutex_unlock(&brd_devices_mutex); kfree(brd); } static int brd_alloc(int i) { struct brd_device *brd; struct gendisk *disk; char buf[DISK_NAME_LEN]; int err = -ENOMEM; struct queue_limits lim = { /* * This is so fdisk will align partitions on 4k, because of * direct_access API needing 4k alignment, returning a PFN * (This is only a problem on very small devices <= 4M, * otherwise fdisk will align on 1M. Regardless this call * is harmless) */ .physical_block_size = PAGE_SIZE, .max_hw_discard_sectors = UINT_MAX, .max_discard_segments = 1, .discard_granularity = PAGE_SIZE, .features = BLK_FEAT_SYNCHRONOUS | BLK_FEAT_NOWAIT, }; brd = brd_find_or_alloc_device(i); if (IS_ERR(brd)) return PTR_ERR(brd); xa_init(&brd->brd_pages); snprintf(buf, DISK_NAME_LEN, "ram%d", i); if (!IS_ERR_OR_NULL(brd_debugfs_dir)) debugfs_create_u64(buf, 0444, brd_debugfs_dir, &brd->brd_nr_pages); disk = brd->brd_disk = blk_alloc_disk(&lim, NUMA_NO_NODE); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_free_dev; } disk->major = RAMDISK_MAJOR; disk->first_minor = i * max_part; disk->minors = max_part; disk->fops = &brd_fops; disk->private_data = brd; strscpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); err = add_disk(disk); if (err) goto out_cleanup_disk; return 0; out_cleanup_disk: put_disk(disk); out_free_dev: brd_free_device(brd); return err; } static void brd_probe(dev_t dev) { brd_alloc(MINOR(dev) / max_part); } static void brd_cleanup(void) { struct brd_device *brd, *next; debugfs_remove_recursive(brd_debugfs_dir); list_for_each_entry_safe(brd, next, &brd_devices, brd_list) { del_gendisk(brd->brd_disk); put_disk(brd->brd_disk); brd_free_pages(brd); brd_free_device(brd); } } static inline void brd_check_and_reset_par(void) { if (unlikely(!max_part)) max_part = 1; /* * make sure 'max_part' can be divided exactly by (1U << MINORBITS), * otherwise, it is possiable to get same dev_t when adding partitions. */ if ((1U << MINORBITS) % max_part != 0) max_part = 1UL << fls(max_part); if (max_part > DISK_MAX_PARTS) { pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n", DISK_MAX_PARTS, DISK_MAX_PARTS); max_part = DISK_MAX_PARTS; } } static int __init brd_init(void) { int err, i; /* * brd module now has a feature to instantiate underlying device * structure on-demand, provided that there is an access dev node. * * (1) if rd_nr is specified, create that many upfront. else * it defaults to CONFIG_BLK_DEV_RAM_COUNT * (2) User can further extend brd devices by create dev node themselves * and have kernel automatically instantiate actual device * on-demand. Example: * mknod /path/devnod_name b 1 X # 1 is the rd major * fdisk -l /path/devnod_name * If (X / max_part) was not already created it will be created * dynamically. */ brd_check_and_reset_par(); brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL); if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) { err = -EIO; goto out_free; } for (i = 0; i < rd_nr; i++) brd_alloc(i); pr_info("brd: module loaded\n"); return 0; out_free: brd_cleanup(); pr_info("brd: module NOT loaded !!!\n"); return err; } static void __exit brd_exit(void) { unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); brd_cleanup(); pr_info("brd: module unloaded\n"); } module_init(brd_init); module_exit(brd_exit); |
| 39 30 15 16 40 32 40 1 5 5 6 5 5 5 5 2 5 5 13 13 13 13 13 2 32 28 28 27 6 28 32 13 32 2 2 2 2 1 1 2 1 3 3 1 1 3 14 14 14 13 14 4 3 3 4 26 14 20 4 26 49 20 49 49 35 35 34 35 35 35 35 23 35 27 3 35 35 46 3 45 32 32 32 32 32 32 32 32 32 7 7 5 6 5 5 32 32 5 5 5 3 5 5 3 32 43 3 2 41 42 42 42 42 42 41 29 29 29 29 27 8 28 27 23 23 29 42 23 23 1 23 22 42 47 49 21 19 11 11 10 9 2 8 1 8 1 20 21 5 10 7 3 3 2 3 3 9 11 7 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 | // SPDX-License-Identifier: GPL-2.0-or-later /* * tcp_diag.c Module for monitoring TCP transport protocols sockets. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/net.h> #include <linux/sock_diag.h> #include <linux/inet_diag.h> #include <linux/tcp.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/netlink.h> #include <net/tcp.h> static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *_info) { struct tcp_info *info = _info; if (inet_sk_state_load(sk) == TCP_LISTEN) { r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog); r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog); } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); } #ifdef CONFIG_TCP_MD5SIG static void tcp_diag_md5sig_fill(struct tcp_diag_md5sig *info, const struct tcp_md5sig_key *key) { info->tcpm_family = key->family; info->tcpm_prefixlen = key->prefixlen; info->tcpm_keylen = key->keylen; memcpy(info->tcpm_key, key->key, key->keylen); if (key->family == AF_INET) info->tcpm_addr[0] = key->addr.a4.s_addr; #if IS_ENABLED(CONFIG_IPV6) else if (key->family == AF_INET6) memcpy(&info->tcpm_addr, &key->addr.a6, sizeof(info->tcpm_addr)); #endif } static int tcp_diag_put_md5sig(struct sk_buff *skb, const struct tcp_md5sig_info *md5sig) { const struct tcp_md5sig_key *key; struct tcp_diag_md5sig *info; struct nlattr *attr; int md5sig_count = 0; hlist_for_each_entry_rcu(key, &md5sig->head, node) md5sig_count++; if (md5sig_count == 0) return 0; attr = nla_reserve(skb, INET_DIAG_MD5SIG, md5sig_count * sizeof(struct tcp_diag_md5sig)); if (!attr) return -EMSGSIZE; info = nla_data(attr); memset(info, 0, md5sig_count * sizeof(struct tcp_diag_md5sig)); hlist_for_each_entry_rcu(key, &md5sig->head, node) { tcp_diag_md5sig_fill(info++, key); if (--md5sig_count == 0) break; } return 0; } #endif static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk, const struct tcp_ulp_ops *ulp_ops, bool net_admin) { struct nlattr *nest; int err; nest = nla_nest_start_noflag(skb, INET_DIAG_ULP_INFO); if (!nest) return -EMSGSIZE; err = nla_put_string(skb, INET_ULP_INFO_NAME, ulp_ops->name); if (err) goto nla_failure; if (ulp_ops->get_info) err = ulp_ops->get_info(sk, skb, net_admin); if (err) goto nla_failure; nla_nest_end(skb, nest); return 0; nla_failure: nla_nest_cancel(skb, nest); return err; } static int tcp_diag_get_aux(struct sock *sk, bool net_admin, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_ulp_ops *ulp_ops; int err = 0; #ifdef CONFIG_TCP_MD5SIG if (net_admin) { struct tcp_md5sig_info *md5sig; rcu_read_lock(); md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); if (md5sig) err = tcp_diag_put_md5sig(skb, md5sig); rcu_read_unlock(); if (err < 0) return err; } #endif ulp_ops = icsk->icsk_ulp_ops; if (ulp_ops) { err = tcp_diag_put_ulp(skb, sk, ulp_ops, net_admin); if (err < 0) return err; } return 0; } static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); size_t size = 0; #ifdef CONFIG_TCP_MD5SIG if (net_admin && sk_fullsock(sk)) { const struct tcp_md5sig_info *md5sig; const struct tcp_md5sig_key *key; size_t md5sig_count = 0; rcu_read_lock(); md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); if (md5sig) { hlist_for_each_entry_rcu(key, &md5sig->head, node) md5sig_count++; } rcu_read_unlock(); size += nla_total_size(md5sig_count * sizeof(struct tcp_diag_md5sig)); } #endif if (sk_fullsock(sk)) { const struct tcp_ulp_ops *ulp_ops; ulp_ops = icsk->icsk_ulp_ops; if (ulp_ops) { size += nla_total_size(0) + nla_total_size(TCP_ULP_NAME_MAX); if (ulp_ops->get_info_size) size += ulp_ops->get_info_size(sk, net_admin); } } return size + nla_total_size(sizeof(struct tcp_info)) + nla_total_size(sizeof(struct inet_diag_msg)) + inet_diag_msg_attrs_size() + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) + 64; } static int tcp_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, u16 nlmsg_flags, bool net_admin) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); DEBUG_NET_WARN_ON_ONCE(tw->tw_state != TCP_TIME_WAIT); inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; r->idiag_state = READ_ONCE(tw->tw_substate); r->idiag_timer = 3; tmo = tw->tw_timer.expires - jiffies; r->idiag_expires = jiffies_delta_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, tw->tw_mark)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int tcp_req_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, u16 nlmsg_flags, bool net_admin) { struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; r->idiag_retrans = READ_ONCE(reqsk->num_retrans); BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); tmo = READ_ONCE(inet_reqsk(sk)->rsk_timer.expires) - jiffies; r->idiag_expires = jiffies_delta_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, inet_rsk(reqsk)->ir_mark)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, u16 nlmsg_flags, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return tcp_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); if (sk->sk_state == TCP_NEW_SYN_RECV) return tcp_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags, net_admin); } static void twsk_build_assert(void) { BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) != offsetof(struct sock, sk_family)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) != offsetof(struct inet_sock, inet_num)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) != offsetof(struct inet_sock, inet_dport)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) != offsetof(struct inet_sock, inet_rcv_saddr)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) != offsetof(struct inet_sock, inet_daddr)); #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) != offsetof(struct sock, sk_v6_rcv_saddr)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) != offsetof(struct sock, sk_v6_daddr)); #endif } static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct inet_diag_dump_data *cb_data = cb->data; struct net *net = sock_net(skb->sk); u32 idiag_states = r->idiag_states; struct inet_hashinfo *hashinfo; int i, num, s_i, s_num; struct sock *sk; hashinfo = net->ipv4.tcp_death_row.hashinfo; if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; s_i = cb->args[1]; s_num = num = cb->args[2]; if (cb->args[0] == 0) { if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport) goto skip_listen_ht; for (i = s_i; i <= hashinfo->lhash2_mask; i++) { struct inet_listen_hashbucket *ilb; struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->lhash2[i]; if (hlist_nulls_empty(&ilb->nulls_head)) { s_num = 0; continue; } spin_lock(&ilb->lock); sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) { num++; continue; } if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_listen; if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_listen; if (!inet_diag_bc_sk(cb_data, sk)) goto next_listen; if (inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, NLM_F_MULTI, net_admin) < 0) { spin_unlock(&ilb->lock); goto done; } next_listen: ++num; } spin_unlock(&ilb->lock); s_num = 0; } skip_listen_ht: cb->args[0] = 1; s_i = num = s_num = 0; } /* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets * with bh disabled. */ #define SKARR_SZ 16 /* Dump bound but inactive (not listening, connecting, etc.) sockets */ if (cb->args[0] == 1) { if (!(idiag_states & TCPF_BOUND_INACTIVE)) goto skip_bind_ht; for (i = s_i; i < hashinfo->bhash_size; i++) { struct inet_bind_hashbucket *ibb; struct inet_bind2_bucket *tb2; struct sock *sk_arr[SKARR_SZ]; int num_arr[SKARR_SZ]; int idx, accum, res; resume_bind_walk: num = 0; accum = 0; ibb = &hashinfo->bhash2[i]; if (hlist_empty(&ibb->chain)) { s_num = 0; continue; } spin_lock_bh(&ibb->lock); inet_bind_bucket_for_each(tb2, &ibb->chain) { if (!net_eq(ib2_net(tb2), net)) continue; sk_for_each_bound(sk, &tb2->owners) { struct inet_sock *inet = inet_sk(sk); if (num < s_num) goto next_bind; if (sk->sk_state != TCP_CLOSE || !inet->inet_num) goto next_bind; if (r->sdiag_family != AF_UNSPEC && r->sdiag_family != sk->sk_family) goto next_bind; if (!inet_diag_bc_sk(cb_data, sk)) goto next_bind; sock_hold(sk); num_arr[accum] = num; sk_arr[accum] = sk; if (++accum == SKARR_SZ) goto pause_bind_walk; next_bind: num++; } } pause_bind_walk: spin_unlock_bh(&ibb->lock); res = 0; for (idx = 0; idx < accum; idx++) { if (res >= 0) { res = inet_sk_diag_fill(sk_arr[idx], NULL, skb, cb, r, NLM_F_MULTI, net_admin); if (res < 0) num = num_arr[idx]; } sock_put(sk_arr[idx]); } if (res < 0) goto done; cond_resched(); if (accum == SKARR_SZ) { s_num = num + 1; goto resume_bind_walk; } s_num = 0; } skip_bind_ht: cb->args[0] = 2; s_i = num = s_num = 0; } if (!(idiag_states & ~TCPF_LISTEN)) goto out; for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); struct hlist_nulls_node *node; struct sock *sk_arr[SKARR_SZ]; int num_arr[SKARR_SZ]; int idx, accum, res; if (hlist_nulls_empty(&head->chain)) continue; if (i > s_i) s_num = 0; next_chunk: num = 0; accum = 0; spin_lock_bh(lock); sk_nulls_for_each(sk, node, &head->chain) { int state; if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next_normal; state = (sk->sk_state == TCP_TIME_WAIT) ? READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state; if (!(idiag_states & (1 << state))) goto next_normal; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_normal; if (r->id.idiag_sport != htons(sk->sk_num) && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != sk->sk_dport && r->id.idiag_dport) goto next_normal; twsk_build_assert(); if (!inet_diag_bc_sk(cb_data, sk)) goto next_normal; if (!refcount_inc_not_zero(&sk->sk_refcnt)) goto next_normal; num_arr[accum] = num; sk_arr[accum] = sk; if (++accum == SKARR_SZ) break; next_normal: ++num; } spin_unlock_bh(lock); res = 0; for (idx = 0; idx < accum; idx++) { if (res >= 0) { res = sk_diag_fill(sk_arr[idx], skb, cb, r, NLM_F_MULTI, net_admin); if (res < 0) num = num_arr[idx]; } sock_gen_put(sk_arr[idx]); } if (res < 0) break; cond_resched(); if (accum == SKARR_SZ) { s_num = num + 1; goto next_chunk; } } done: cb->args[1] = i; cb->args[2] = num; out: ; } static struct sock *tcp_diag_find_one_icsk(struct net *net, const struct inet_diag_req_v2 *req) { struct sock *sk; rcu_read_lock(); if (req->sdiag_family == AF_INET) { sk = inet_lookup(net, NULL, 0, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) } else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = inet_lookup(net, NULL, 0, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if); else sk = inet6_lookup(net, NULL, 0, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if); #endif } else { rcu_read_unlock(); return ERR_PTR(-EINVAL); } rcu_read_unlock(); if (!sk) return ERR_PTR(-ENOENT); if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_gen_put(sk); return ERR_PTR(-ENOENT); } return sk; } static int tcp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { struct sk_buff *in_skb = cb->skb; struct sk_buff *rep; struct sock *sk; struct net *net; bool net_admin; int err; net = sock_net(in_skb->sk); sk = tcp_diag_find_one_icsk(net, req); if (IS_ERR(sk)) return PTR_ERR(sk); net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN); rep = nlmsg_new(tcp_diag_get_aux_size(sk, net_admin), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; } err = sk_diag_fill(sk, rep, cb, req, 0, net_admin); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); goto out; } err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) sock_gen_put(sk); return err; } #ifdef CONFIG_INET_DIAG_DESTROY static int tcp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { struct net *net = sock_net(in_skb->sk); struct sock *sk; int err; sk = tcp_diag_find_one_icsk(net, req); if (IS_ERR(sk)) return PTR_ERR(sk); err = sock_diag_destroy(sk, ECONNABORTED); sock_gen_put(sk); return err; } #endif static const struct inet_diag_handler tcp_diag_handler = { .owner = THIS_MODULE, .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, .idiag_get_aux = tcp_diag_get_aux, .idiag_type = IPPROTO_TCP, .idiag_info_size = sizeof(struct tcp_info), #ifdef CONFIG_INET_DIAG_DESTROY .destroy = tcp_diag_destroy, #endif }; static int __init tcp_diag_init(void) { return inet_diag_register(&tcp_diag_handler); } static void __exit tcp_diag_exit(void) { inet_diag_unregister(&tcp_diag_handler); } module_init(tcp_diag_init); module_exit(tcp_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */); |
| 2683 874 196 192 465 1286 466 466 465 464 466 465 1286 1283 466 1286 466 466 466 465 466 1283 1286 1286 132 89 87 132 182 180 31 182 150 186 150 186 133 132 133 133 133 2 2 2 13 13 13 68 70 70 70 3010 3011 3013 3019 36 36 56 56 56 4644 4637 4637 166 167 167 1163 1163 41 41 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> #include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/fixmap.h> #include <asm/mtrr.h> #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); SYM_PIC_ALIAS(physical_mask); #endif pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); } void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { paravirt_release_pte(page_to_pfn(pte)); tlb_remove_ptdesc(tlb, page_ptdesc(pte)); } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table * entries need a full cr3 reload to flush. */ #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ static inline void pgd_list_add(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_add(&ptdesc->pt_list, &pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_del(&ptdesc->pt_list); } static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) { virt_to_ptdesc(pgd)->pt_mm = mm; } struct mm_struct *pgd_page_get_mm(struct page *page) { return page_ptdesc(page)->pt_mm; } static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) { /* PAE preallocates all its PMDs. No cloning needed. */ if (!IS_ENABLED(CONFIG_X86_PAE)) clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); /* List used to sync kernel mapping updates */ pgd_set_mm(pgd, mm); pgd_list_add(pgd); } static void pgd_dtor(pgd_t *pgd) { spin_lock(&pgd_lock); pgd_list_del(pgd); spin_unlock(&pgd_lock); } /* * List of all pgd's needed for non-PAE so it can invalidate entries * in both cached and uncached pgd's; not needed for PAE since the * kernel pmd is shared. If PAE were not to share the pmd a similar * tactic would be needed. This is essentially codepath-based locking * against pageattr.c; it is the unique case in which a valid change * of kernel pagetables can't be lazily synchronized by vmalloc faults. * vmalloc faults work because attached pagetables are never freed. * -- nyc */ #ifdef CONFIG_X86_PAE /* * In PAE mode, we need to do a cr3 reload (=tlb flush) when * updating the top-level pagetable entries to guarantee the * processor notices the update. Since this is expensive, and * all 4 top-level entries are used almost immediately in a * new process's life, we just pre-populate them here. */ #define PREALLOCATED_PMDS PTRS_PER_PGD /* * "USER_PMDS" are the PMDs for the user copy of the page tables when * PTI is enabled. They do not exist when PTI is disabled. Note that * this is distinct from the user _portion_ of the kernel page tables * which always exists. * * We allocate separate PMDs for the kernel part of the user page-table * when PTI is enabled. We need them to map the per-process LDT into the * user-space page-table. */ #define PREALLOCATED_USER_PMDS (boot_cpu_has(X86_FEATURE_PTI) ? \ KERNEL_PGD_PTRS : 0) #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); /* Note: almost everything apart from _PAGE_PRESENT is reserved at the pmd (PDPT) level. */ set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); /* * According to Intel App note "TLBs, Paging-Structure Caches, * and Their Invalidation", April 2007, document 317080-001, * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 #define PREALLOCATED_USER_PMDS 0 #define MAX_PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; struct ptdesc *ptdesc; for (i = 0; i < count; i++) if (pmds[i]) { ptdesc = virt_to_ptdesc(pmds[i]); pagetable_dtor(ptdesc); pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } } static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; gfp &= ~__GFP_HIGHMEM; for (i = 0; i < count; i++) { pmd_t *pmd = NULL; struct ptdesc *ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) failed = true; if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); ptdesc = NULL; failed = true; } if (ptdesc) { mm_inc_nr_pmds(mm); pmd = ptdesc_address(ptdesc); } pmds[i] = pmd; } if (failed) { free_pmds(mm, pmds, count); return -ENOMEM; } return 0; } /* * Mop up any pmd pages which may still be attached to the pgd. * Normally they will be freed by munmap/exit_mmap, but any pmd we * preallocate which never got a corresponding vma will need to be * freed manually. */ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) { pgd_t pgd = *pgdp; if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); mm_dec_nr_pmds(mm); } } static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { int i; for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; pgdp = kernel_to_user_pgdp(pgdp); for (i = 0; i < PREALLOCATED_USER_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]); #endif } static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { p4d_t *p4d; pud_t *pud; int i; p4d = p4d_offset(pgd, 0); pud = pud_offset(p4d, 0); for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { pmd_t *pmd = pmds[i]; if (i >= KERNEL_PGD_BOUNDARY) memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, pud, pmd); } } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); p4d_t *u_p4d; pud_t *u_pud; int i; u_p4d = p4d_offset(u_pgd, 0); u_pud = pud_offset(u_p4d, 0); s_pgd += KERNEL_PGD_BOUNDARY; u_pud += KERNEL_PGD_BOUNDARY; for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) { pmd_t *pmd = pmds[i]; memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, u_pud, pmd); } } #else static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { } #endif static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { /* * PTI and Xen need a whole page for the PAE PGD * even though the hardware only needs 32 bytes. * * For simplicity, allocate a page for all users. */ return __pgd_alloc(mm, pgd_allocation_order()); } static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) { __pgd_free(mm, pgd); } pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; pmd_t *pmds[PREALLOCATED_PMDS]; pgd = _pgd_alloc(mm); if (pgd == NULL) goto out; mm->pgd = pgd; if (sizeof(pmds) != 0 && preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) goto out_free_pgd; if (sizeof(u_pmds) != 0 && preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) goto out_free_pmds; if (paravirt_pgd_alloc(mm) != 0) goto out_free_user_pmds; /* * Make sure that pre-populating the pmds is atomic with * respect to anything walking the pgd_list, so that they * never see a partially populated pgd. */ spin_lock(&pgd_lock); pgd_ctor(mm, pgd); if (sizeof(pmds) != 0) pgd_prepopulate_pmd(mm, pgd, pmds); if (sizeof(u_pmds) != 0) pgd_prepopulate_user_pmd(mm, pgd, u_pmds); spin_unlock(&pgd_lock); return pgd; out_free_user_pmds: if (sizeof(u_pmds) != 0) free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); out_free_pmds: if (sizeof(pmds) != 0) free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: _pgd_free(mm, pgd); out: return NULL; } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); _pgd_free(mm, pgd); } /* * Used to set accessed or dirty bits in the page table entries * on other architectures. On x86, the accessed and dirty bits * are tracked by hardware. However, do_wp_page calls this function * to also make the pte writeable at the same time the dirty bit is * set. In that case we do actually need to write the PTE. */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(*ptep, entry); if (changed && dirty) set_pte(ptep, entry); return changed; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { int changed = !pud_same(*pudp, entry); VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } #endif int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { int ret = 0; if (pte_young(*ptep)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *) &ptep->pte); return ret; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { int ret = 0; if (pmd_young(*pmdp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); return ret; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp) { int ret = 0; if (pud_young(*pudp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pudp); return ret; } #endif int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { /* * On x86 CPUs, clearing the accessed bit without a TLB flush * doesn't cause data corruption. [ It could cause incorrect * page aging and the (mistaken) reclaim of hot pages, but the * chance of that should be relatively low. ] * * So as a performance optimization don't flush the TLB when * clearing the accessed bit, it will eventually be flushed by * a context switch or a VM operation anyway. [ In the rare * event of it not getting flushed for a long time the delay * shouldn't really matter because there's no real memory * pressure for swapout to react to. ] */ return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { int young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. */ return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); } #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { VM_WARN_ON_ONCE(!pud_present(*pudp)); pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return old; } #endif /** * reserve_top_address - Reserve a hole in the top of the kernel address space * @reserve: Size of hole to reserve * * Can be used to relocate the fixmap area and poke a hole in the top * of the kernel address space to make room for a hypervisor. */ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); #ifdef CONFIG_X86_64 /* * Ensure that the static initial page tables are covering the * fixmap completely. */ BUILD_BUG_ON(__end_of_permanent_fixed_addresses > (FIXMAP_PMD_NUM * PTRS_PER_PTE)); #endif if (idx >= __end_of_fixed_addresses) { BUG(); return; } set_pte_vaddr(address, pte); fixmaps_set++; } void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #if CONFIG_PGTABLE_LEVELS > 4 /** * p4d_set_huge - Set up kernel P4D mapping * @p4d: Pointer to the P4D entry * @addr: Virtual address associated with the P4D entry * @prot: Protection bits to use * * No 512GB pages yet -- always return 0 */ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } /** * p4d_clear_huge - Clear kernel P4D mapping when it is set * @p4d: Pointer to the P4D entry to clear * * No 512GB pages yet -- do nothing */ void p4d_clear_huge(p4d_t *p4d) { } #endif /** * pud_set_huge - Set up kernel PUD mapping * @pud: Pointer to the PUD entry * @addr: Virtual address associated with the PUD entry * @prot: Protection bits to use * * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this * function sets up a huge page only if the complete range has the same MTRR * caching mode. * * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger * page mapping attempt fails. * * Returns 1 on success and 0 on failure. */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); if (!uniform) return 0; /* Bail out if we are we on a populated non-leaf entry: */ if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pmd_set_huge - Set up kernel PMD mapping * @pmd: Pointer to the PMD entry * @addr: Virtual address associated with the PMD entry * @prot: Protection bits to use * * See text over pud_set_huge() above. * * Returns 1 on success and 0 on failure. */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); if (!uniform) { pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", __func__, addr, addr + PMD_SIZE); return 0; } /* Bail out if we are we on a populated non-leaf entry: */ if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pud_clear_huge - Clear kernel PUD mapping when it is set * @pud: Pointer to the PUD entry to clear. * * Returns 1 on success and 0 on failure (no PUD map is found). */ int pud_clear_huge(pud_t *pud) { if (pud_leaf(*pud)) { pud_clear(pud); return 1; } return 0; } /** * pmd_clear_huge - Clear kernel PMD mapping when it is set * @pmd: Pointer to the PMD entry to clear. * * Returns 1 on success and 0 on failure (no PMD map is found). */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_leaf(*pmd)) { pmd_clear(pmd); return 1; } return 0; } #ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear PUD entry and free PMD page * @pud: Pointer to a PUD * @addr: Virtual address associated with PUD * * Context: The PUD range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. * * NOTE: Callers must allow a single page allocation. */ int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd, *pmd_sv; pte_t *pte; int i; pmd = pud_pgtable(*pud); pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); if (!pmd_sv) return 0; for (i = 0; i < PTRS_PER_PMD; i++) { pmd_sv[i] = pmd[i]; if (!pmd_none(pmd[i])) pmd_clear(&pmd[i]); } pud_clear(pud); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(pmd_sv[i])) { pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); pte_free_kernel(&init_mm, pte); } } free_page((unsigned long)pmd_sv); pmd_free(&init_mm, pmd); return 1; } /** * pmd_free_pte_page - Clear PMD entry and free PTE page. * @pmd: Pointer to the PMD * @addr: Virtual address associated with PMD * * Context: The PMD range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; pte = (pte_t *)pmd_page_vaddr(*pmd); pmd_clear(pmd); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); pte_free_kernel(&init_mm, pte); return 1; } #else /* !CONFIG_X86_64 */ /* * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd PMD entries. See vmalloc_sync_one(). */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } #endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pte_mkwrite_shstk(pte); pte = pte_mkwrite_novma(pte); return pte_clear_saveddirty(pte); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pmd_mkwrite_shstk(pmd); pmd = pmd_mkwrite_novma(pmd); return pmd_clear_saveddirty(pmd); } void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { /* * Hardware before shadow stack can (rarely) set Dirty=1 * on a Write=0 PTE. So the below condition * only indicates a software bug when shadow stack is * supported by the HW. This checking is covered in * pte_shstk(). */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pte_shstk(pte)); } void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pmd_shstk(pmd)); } void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud)); } |
| 11 17 1 16 17 13 7 6 3 6 4 10 10 8 3 3 10 13 78 9 3 9 9 9 9 9 9 9 9 9 3 9 3 6 14 14 14 14 14 14 10 10 10 4 4 4 68 9 134 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fs.h> #include <linux/xattr.h> #include "overlayfs.h" static bool ovl_is_escaped_xattr(struct super_block *sb, const char *name) { struct ovl_fs *ofs = sb->s_fs_info; if (ofs->config.userxattr) return strncmp(name, OVL_XATTR_ESCAPE_USER_PREFIX, OVL_XATTR_ESCAPE_USER_PREFIX_LEN) == 0; else return strncmp(name, OVL_XATTR_ESCAPE_TRUSTED_PREFIX, OVL_XATTR_ESCAPE_TRUSTED_PREFIX_LEN - 1) == 0; } static bool ovl_is_own_xattr(struct super_block *sb, const char *name) { struct ovl_fs *ofs = OVL_FS(sb); if (ofs->config.userxattr) return strncmp(name, OVL_XATTR_USER_PREFIX, OVL_XATTR_USER_PREFIX_LEN) == 0; else return strncmp(name, OVL_XATTR_TRUSTED_PREFIX, OVL_XATTR_TRUSTED_PREFIX_LEN) == 0; } bool ovl_is_private_xattr(struct super_block *sb, const char *name) { return ovl_is_own_xattr(sb, name) && !ovl_is_escaped_xattr(sb, name); } static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { int err; struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct dentry *upperdentry = ovl_i_dentry_upper(inode); struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); struct path realpath; const struct cred *old_cred; if (!value && !upperdentry) { ovl_path_lower(dentry, &realpath); old_cred = ovl_override_creds(dentry->d_sb); err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0); ovl_revert_creds(old_cred); if (err < 0) goto out; } if (!upperdentry) { err = ovl_copy_up(dentry); if (err) goto out; realdentry = ovl_dentry_upper(dentry); } err = ovl_want_write(dentry); if (err) goto out; old_cred = ovl_override_creds(dentry->d_sb); if (value) { err = ovl_do_setxattr(ofs, realdentry, name, value, size, flags); } else { WARN_ON(flags != XATTR_REPLACE); err = ovl_do_removexattr(ofs, realdentry, name); } ovl_revert_creds(old_cred); ovl_drop_write(dentry); /* copy c/mtime */ ovl_copyattr(inode); out: return err; } static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { ssize_t res; const struct cred *old_cred; struct path realpath; ovl_i_path_real(inode, &realpath); old_cred = ovl_override_creds(dentry->d_sb); res = vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size); ovl_revert_creds(old_cred); return res; } static bool ovl_can_list(struct super_block *sb, const char *s) { /* Never list private (.overlay) */ if (ovl_is_private_xattr(sb, s)) return false; /* List all non-trusted xattrs */ if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0) return true; /* list other trusted for superuser only */ return ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); } ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) { struct dentry *realdentry = ovl_dentry_real(dentry); struct ovl_fs *ofs = OVL_FS(dentry->d_sb); ssize_t res; size_t len; char *s; const struct cred *old_cred; size_t prefix_len, name_len; old_cred = ovl_override_creds(dentry->d_sb); res = vfs_listxattr(realdentry, list, size); ovl_revert_creds(old_cred); if (res <= 0 || size == 0) return res; prefix_len = ofs->config.userxattr ? OVL_XATTR_USER_PREFIX_LEN : OVL_XATTR_TRUSTED_PREFIX_LEN; /* filter out private xattrs */ for (s = list, len = res; len;) { size_t slen = strnlen(s, len) + 1; /* underlying fs providing us with an broken xattr list? */ if (WARN_ON(slen > len)) return -EIO; len -= slen; if (!ovl_can_list(dentry->d_sb, s)) { res -= slen; memmove(s, s + slen, len); } else if (ovl_is_escaped_xattr(dentry->d_sb, s)) { res -= OVL_XATTR_ESCAPE_PREFIX_LEN; name_len = slen - prefix_len - OVL_XATTR_ESCAPE_PREFIX_LEN; s += prefix_len; memmove(s, s + OVL_XATTR_ESCAPE_PREFIX_LEN, name_len + len); s += name_len; } else { s += slen; } } return res; } static char *ovl_xattr_escape_name(const char *prefix, const char *name) { size_t prefix_len = strlen(prefix); size_t name_len = strlen(name); size_t escaped_len; char *escaped, *s; escaped_len = prefix_len + OVL_XATTR_ESCAPE_PREFIX_LEN + name_len; if (escaped_len > XATTR_NAME_MAX) return ERR_PTR(-EOPNOTSUPP); escaped = kmalloc(escaped_len + 1, GFP_KERNEL); if (escaped == NULL) return ERR_PTR(-ENOMEM); s = escaped; memcpy(s, prefix, prefix_len); s += prefix_len; memcpy(s, OVL_XATTR_ESCAPE_PREFIX, OVL_XATTR_ESCAPE_PREFIX_LEN); s += OVL_XATTR_ESCAPE_PREFIX_LEN; memcpy(s, name, name_len + 1); return escaped; } static int ovl_own_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size) { char *escaped; int r; escaped = ovl_xattr_escape_name(handler->prefix, name); if (IS_ERR(escaped)) return PTR_ERR(escaped); r = ovl_xattr_get(dentry, inode, escaped, buffer, size); kfree(escaped); return r; } static int ovl_own_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { char *escaped; int r; escaped = ovl_xattr_escape_name(handler->prefix, name); if (IS_ERR(escaped)) return PTR_ERR(escaped); r = ovl_xattr_set(dentry, inode, escaped, value, size, flags); kfree(escaped); return r; } static int ovl_other_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size) { return ovl_xattr_get(dentry, inode, name, buffer, size); } static int ovl_other_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { return ovl_xattr_set(dentry, inode, name, value, size, flags); } static const struct xattr_handler ovl_own_trusted_xattr_handler = { .prefix = OVL_XATTR_TRUSTED_PREFIX, .get = ovl_own_xattr_get, .set = ovl_own_xattr_set, }; static const struct xattr_handler ovl_own_user_xattr_handler = { .prefix = OVL_XATTR_USER_PREFIX, .get = ovl_own_xattr_get, .set = ovl_own_xattr_set, }; static const struct xattr_handler ovl_other_xattr_handler = { .prefix = "", /* catch all */ .get = ovl_other_xattr_get, .set = ovl_other_xattr_set, }; static const struct xattr_handler * const ovl_trusted_xattr_handlers[] = { &ovl_own_trusted_xattr_handler, &ovl_other_xattr_handler, NULL }; static const struct xattr_handler * const ovl_user_xattr_handlers[] = { &ovl_own_user_xattr_handler, &ovl_other_xattr_handler, NULL }; const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs) { return ofs->config.userxattr ? ovl_user_xattr_handlers : ovl_trusted_xattr_handlers; } |
| 10 10 10 4 1 10 6 2 1 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | // SPDX-License-Identifier: GPL-2.0-only /* iptables module for the packet checksum mangling * * (C) 2002 by Harald Welte <laforge@netfilter.org> * (C) 2010 Red Hat, Inc. * * Author: Michael S. Tsirkin <mst@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CHECKSUM.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michael S. Tsirkin <mst@redhat.com>"); MODULE_DESCRIPTION("Xtables: checksum modification"); MODULE_ALIAS("ipt_CHECKSUM"); MODULE_ALIAS("ip6t_CHECKSUM"); static unsigned int checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) { if (skb->ip_summed == CHECKSUM_PARTIAL && !skb_is_gso(skb)) skb_checksum_help(skb); return XT_CONTINUE; } static int checksum_tg_check(const struct xt_tgchk_param *par) { const struct xt_CHECKSUM_info *einfo = par->targinfo; const struct ip6t_ip6 *i6 = par->entryinfo; const struct ipt_ip *i4 = par->entryinfo; if (einfo->operation & ~XT_CHECKSUM_OP_FILL) { pr_info_ratelimited("unsupported CHECKSUM operation %x\n", einfo->operation); return -EINVAL; } if (!einfo->operation) return -EINVAL; switch (par->family) { case NFPROTO_IPV4: if (i4->proto == IPPROTO_UDP && (i4->invflags & XT_INV_PROTO) == 0) return 0; break; case NFPROTO_IPV6: if ((i6->flags & IP6T_F_PROTO) && i6->proto == IPPROTO_UDP && (i6->invflags & XT_INV_PROTO) == 0) return 0; break; } pr_warn_once("CHECKSUM should be avoided. If really needed, restrict with \"-p udp\" and only use in OUTPUT\n"); return 0; } static struct xt_target checksum_tg_reg[] __read_mostly = { { .name = "CHECKSUM", .family = NFPROTO_IPV4, .target = checksum_tg, .targetsize = sizeof(struct xt_CHECKSUM_info), .table = "mangle", .checkentry = checksum_tg_check, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "CHECKSUM", .family = NFPROTO_IPV6, .target = checksum_tg, .targetsize = sizeof(struct xt_CHECKSUM_info), .table = "mangle", .checkentry = checksum_tg_check, .me = THIS_MODULE, }, #endif }; static int __init checksum_tg_init(void) { return xt_register_targets(checksum_tg_reg, ARRAY_SIZE(checksum_tg_reg)); } static void __exit checksum_tg_exit(void) { xt_unregister_targets(checksum_tg_reg, ARRAY_SIZE(checksum_tg_reg)); } module_init(checksum_tg_init); module_exit(checksum_tg_exit); |
| 41 7 4 11 36 86 337 370 44 3 206 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Kernel-based Virtual Machine driver for Linux * * This header defines architecture specific interfaces, x86 version */ #ifndef _ASM_X86_KVM_HOST_H #define _ASM_X86_KVM_HOST_H #include <linux/types.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/tracepoint.h> #include <linux/cpumask.h> #include <linux/irq_work.h> #include <linux/irq.h> #include <linux/workqueue.h> #include <linux/kvm.h> #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <linux/perf_event.h> #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> #include <linux/irqbypass.h> #include <linux/kfifo.h> #include <linux/sched/vhost_task.h> #include <linux/call_once.h> #include <linux/atomic.h> #include <asm/apic.h> #include <asm/pvclock-abi.h> #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/msr-index.h> #include <asm/msr.h> #include <asm/asm.h> #include <asm/irq_remapping.h> #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> #include <asm/reboot.h> #include <hyperv/hvhdk.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS /* * CONFIG_KVM_MAX_NR_VCPUS is defined iff CONFIG_KVM!=n, provide a dummy max if * KVM is disabled (arbitrarily use the default from CONFIG_KVM_MAX_NR_VCPUS). */ #ifdef CONFIG_KVM_MAX_NR_VCPUS #define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS #else #define KVM_MAX_VCPUS 1024 #endif /* * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs * might be larger than the actual number of VCPUs because the * APIC ID encodes CPU topology information. * * In the worst case, we'll need less than one extra bit for the * Core ID, and less than one extra bit for the Package (Die) ID, * so ratio of 4 should be enough. */ #define KVM_VCPU_ID_RATIO 4 #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) /* memory slots that are not exposed to userspace */ #define KVM_INTERNAL_MEM_SLOTS 3 #define KVM_HALT_POLL_NS_DEFAULT 200000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) #define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \ KVM_BUS_LOCK_DETECTION_EXIT) #define KVM_X86_NOTIFY_VMEXIT_VALID_BITS (KVM_X86_NOTIFY_VMEXIT_ENABLED | \ KVM_X86_NOTIFY_VMEXIT_USER) /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) #define KVM_REQ_LOAD_MMU_PGD KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) #define KVM_REQ_NMI KVM_ARCH_REQ(9) #define KVM_REQ_PMU KVM_ARCH_REQ(10) #define KVM_REQ_PMI KVM_ARCH_REQ(11) #ifdef CONFIG_KVM_SMM #define KVM_REQ_SMI KVM_ARCH_REQ(12) #endif #define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) #define KVM_REQ_MCLOCK_INPROGRESS \ KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_SCAN_IOAPIC \ KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_GLOBAL_CLOCK_UPDATE KVM_ARCH_REQ(16) #define KVM_REQ_APIC_PAGE_RELOAD \ KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HV_CRASH KVM_ARCH_REQ(18) #define KVM_REQ_IOAPIC_EOI_EXIT KVM_ARCH_REQ(19) #define KVM_REQ_HV_RESET KVM_ARCH_REQ(20) #define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) #define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) #define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23) #define KVM_REQ_GET_NESTED_STATE_PAGES KVM_ARCH_REQ(24) #define KVM_REQ_APICV_UPDATE \ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) #define KVM_REQ_TLB_FLUSH_GUEST \ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_RECALC_INTERCEPTS KVM_ARCH_REQ(29) #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HV_TLB_FLUSH \ KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \ KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \ | X86_CR4_LAM_SUP | X86_CR4_CET)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G #define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) #define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) #define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) #define KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO 50 #define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 256 #define KVM_NR_VAR_MTRR 8 #define ASYNC_PF_PER_VCPU 64 enum kvm_reg { VCPU_REGS_RAX = __VCPU_REGS_RAX, VCPU_REGS_RCX = __VCPU_REGS_RCX, VCPU_REGS_RDX = __VCPU_REGS_RDX, VCPU_REGS_RBX = __VCPU_REGS_RBX, VCPU_REGS_RSP = __VCPU_REGS_RSP, VCPU_REGS_RBP = __VCPU_REGS_RBP, VCPU_REGS_RSI = __VCPU_REGS_RSI, VCPU_REGS_RDI = __VCPU_REGS_RDI, #ifdef CONFIG_X86_64 VCPU_REGS_R8 = __VCPU_REGS_R8, VCPU_REGS_R9 = __VCPU_REGS_R9, VCPU_REGS_R10 = __VCPU_REGS_R10, VCPU_REGS_R11 = __VCPU_REGS_R11, VCPU_REGS_R12 = __VCPU_REGS_R12, VCPU_REGS_R13 = __VCPU_REGS_R13, VCPU_REGS_R14 = __VCPU_REGS_R14, VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, NR_VCPU_REGS, VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR0, VCPU_EXREG_CR3, VCPU_EXREG_CR4, VCPU_EXREG_RFLAGS, VCPU_EXREG_SEGMENTS, VCPU_EXREG_EXIT_INFO_1, VCPU_EXREG_EXIT_INFO_2, }; enum { VCPU_SREG_ES, VCPU_SREG_CS, VCPU_SREG_SS, VCPU_SREG_DS, VCPU_SREG_FS, VCPU_SREG_GS, VCPU_SREG_TR, VCPU_SREG_LDTR, }; enum exit_fastpath_completion { EXIT_FASTPATH_NONE, EXIT_FASTPATH_REENTER_GUEST, EXIT_FASTPATH_EXIT_HANDLED, EXIT_FASTPATH_EXIT_USERSPACE, }; typedef enum exit_fastpath_completion fastpath_t; struct x86_emulate_ctxt; struct x86_exception; union kvm_smram; enum x86_intercept; enum x86_intercept_stage; #define KVM_NR_DB_REGS 4 #define DR6_BUS_LOCK (1 << 11) #define DR6_BD (1 << 13) #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) #define DR6_RTM (1 << 16) /* * DR6_ACTIVE_LOW combines fixed-1 and active-low bits. * We can regard all the bits in DR6_FIXED_1 as active_low bits; * they will never be 0 for now, but when they are defined * in the future it will require no code change. * * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. */ #define DR6_ACTIVE_LOW 0xffff0ff0 #define DR6_VOLATILE 0x0001e80f #define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) #define DR7_GD (1 << 13) #define DR7_VOLATILE 0xffff2bff #define KVM_GUESTDBG_VALID_MASK \ (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_SINGLESTEP | \ KVM_GUESTDBG_USE_HW_BP | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_INJECT_BP | \ KVM_GUESTDBG_INJECT_DB | \ KVM_GUESTDBG_BLOCKIRQ) #define PFERR_PRESENT_MASK BIT(0) #define PFERR_WRITE_MASK BIT(1) #define PFERR_USER_MASK BIT(2) #define PFERR_RSVD_MASK BIT(3) #define PFERR_FETCH_MASK BIT(4) #define PFERR_PK_MASK BIT(5) #define PFERR_SS_MASK BIT(6) #define PFERR_SGX_MASK BIT(15) #define PFERR_GUEST_RMP_MASK BIT_ULL(31) #define PFERR_GUEST_FINAL_MASK BIT_ULL(32) #define PFERR_GUEST_PAGE_MASK BIT_ULL(33) #define PFERR_GUEST_ENC_MASK BIT_ULL(34) #define PFERR_GUEST_SIZEM_MASK BIT_ULL(35) #define PFERR_GUEST_VMPL_MASK BIT_ULL(36) /* * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks * when emulating instructions that triggers implicit access. */ #define PFERR_IMPLICIT_ACCESS BIT_ULL(48) /* * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred * when the guest was accessing private memory. */ #define PFERR_PRIVATE_ACCESS BIT_ULL(49) #define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* * The following bit is set with PV-EOI, unset on EOI. * We detect PV-EOI changes by guest by comparing * this bit with PV-EOI in guest memory. * See the implementation in apic_update_pv_eoi. */ #define KVM_APIC_PV_EOI_PENDING 1 struct kvm_kernel_irqfd; struct kvm_kernel_irq_routing_entry; /* * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page * also includes TDP pages) to determine whether or not a page can be used in * the given MMU context. This is a subset of the overall kvm_cpu_role to * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows * allocating 2 bytes per gfn instead of 4 bytes per gfn. * * Upper-level shadow pages having gptes are tracked for write-protection via * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must * not create more than 2^16-1 upper-level shadow pages at a single gfn, * otherwise gfn_write_track will overflow and explosions will ensue. * * A unique shadow page (SP) for a gfn is created if and only if an existing SP * cannot be reused. The ability to reuse a SP is tracked by its role, which * incorporates various mode bits and properties of the SP. Roughly speaking, * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * * But, even though there are 20 bits in the mask below, not all combinations * of modes and flags are possible: * * - invalid shadow pages are not accounted, mirror pages are not shadowed, * so the bits are effectively 18. * * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); * execonly and ad_disabled are only used for nested EPT which has * has_4_byte_gpte=0. Therefore, 2 bits are always unused. * * - the 4 bits of level are effectively limited to the values 2/3/4/5, * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE * paging has exactly one upper level, making level completely redundant * when has_4_byte_gpte=1. * * - on top of this, smep_andnot_wp and smap_andnot_wp are only set if * cr0_wp=0, therefore these three bits only give rise to 5 possibilities. * * Therefore, the maximum number of possible upper-level shadow pages for a * single gfn is a bit less than 2^13. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; unsigned has_4_byte_gpte:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; unsigned invalid:1; unsigned efer_nx:1; unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; unsigned ad_disabled:1; unsigned guest_mode:1; unsigned passthrough:1; unsigned is_mirror:1; unsigned :4; /* * This is left at the top of the word so that * kvm_memslots_for_spte_role can extract it with a * simple shift. While there is room, give it a whole * byte so it is also faster to load it from memory. */ unsigned smm:8; }; }; /* * kvm_mmu_extended_role complements kvm_mmu_page_role, tracking properties * relevant to the current MMU configuration. When loading CR0, CR4, or EFER, * including on nested transitions, if nothing in the full role changes then * MMU re-configuration can be skipped. @valid bit is set on first usage so we * don't treat all-zero structure as valid data. * * The properties that are tracked in the extended role but not the page role * are for things that either (a) do not affect the validity of the shadow page * or (b) are indirectly reflected in the shadow page's role. For example, * CR4.PKE only affects permission checks for software walks of the guest page * tables (because KVM doesn't support Protection Keys with shadow paging), and * CR0.PG, CR4.PAE, and CR4.PSE are indirectly reflected in role.level. * * Note, SMEP and SMAP are not redundant with sm*p_andnot_wp in the page role. * If CR0.WP=1, KVM can reuse shadow pages for the guest regardless of SMEP and * SMAP, but the MMU's permission checks for software walks need to be SMEP and * SMAP aware regardless of CR0.WP. */ union kvm_mmu_extended_role { u32 word; struct { unsigned int valid:1; unsigned int execonly:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; unsigned int efer_lma:1; }; }; union kvm_cpu_role { u64 as_u64; struct { union kvm_mmu_page_role base; union kvm_mmu_extended_role ext; }; }; struct kvm_rmap_head { atomic_long_t val; }; struct kvm_pio_request { unsigned long count; int in; int port; int size; }; #define PT64_ROOT_MAX_LEVEL 5 struct rsvd_bits_validate { u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL]; u64 bad_mt_xwr; }; struct kvm_mmu_root_info { gpa_t pgd; hpa_t hpa; }; #define KVM_MMU_ROOT_INFO_INVALID \ ((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE }) #define KVM_MMU_NUM_PREV_ROOTS 3 #define KVM_MMU_ROOT_CURRENT BIT(0) #define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) #define KVM_MMU_ROOTS_ALL (BIT(1 + KVM_MMU_NUM_PREV_ROOTS) - 1) #define KVM_HAVE_MMU_RWLOCK struct kvm_mmu_page; struct kvm_page_fault; /* * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, * and 2-level 32-bit). The kvm_mmu structure abstracts the details of the * current mmu mode. */ struct kvm_mmu { unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t gva_or_gpa, u64 access, struct x86_exception *exception); int (*sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i); struct kvm_mmu_root_info root; hpa_t mirror_root_hpa; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; /* * The pkru_mask indicates if protection key checks are needed. It * consists of 16 domains indexed by page fault error code bits [4:1], * with PFEC.RSVD replaced by ACC_USER_MASK from the page tables. * Each domain has 2 bits which are ANDed with AD and WD from PKRU. */ u32 pkru_mask; struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; /* * Bitmap; bit set = permission fault * Byte index: page fault error code [4:1] * Bit index: pte permissions in ACC_* format */ u8 permissions[16]; u64 *pae_root; u64 *pml4_root; u64 *pml5_root; /* * check zero bits on shadow page table entries, these * bits include not only hardware reserved bits but also * the bits spte never used. */ struct rsvd_bits_validate shadow_zero_check; struct rsvd_bits_validate guest_rsvd_check; u64 pdptrs[4]; /* pae */ }; enum pmc_type { KVM_PMC_GP = 0, KVM_PMC_FIXED, }; struct kvm_pmc { enum pmc_type type; u8 idx; bool is_paused; bool intr; /* * Base value of the PMC counter, relative to the *consumed* count in * the associated perf_event. This value includes counter updates from * the perf_event and emulated_count since the last time the counter * was reprogrammed, but it is *not* the current value as seen by the * guest or userspace. * * The count is relative to the associated perf_event so that KVM * doesn't need to reprogram the perf_event every time the guest writes * to the counter. */ u64 counter; /* * PMC events triggered by KVM emulation that haven't been fully * processed, i.e. haven't undergone overflow detection. */ u64 emulated_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; /* * only for creating or reusing perf_event, * eventsel value for general purpose counters, * ctrl value for fixed counters. */ u64 current_config; }; /* More counters may conflict with other existing Architectural MSRs */ #define KVM_MAX(a, b) ((a) >= (b) ? (a) : (b)) #define KVM_MAX_NR_INTEL_GP_COUNTERS 8 #define KVM_MAX_NR_AMD_GP_COUNTERS 6 #define KVM_MAX_NR_GP_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_GP_COUNTERS, \ KVM_MAX_NR_AMD_GP_COUNTERS) #define KVM_MAX_NR_INTEL_FIXED_COUNTERS 3 #define KVM_MAX_NR_AMD_FIXED_COUNTERS 0 #define KVM_MAX_NR_FIXED_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_FIXED_COUNTERS, \ KVM_MAX_NR_AMD_FIXED_COUNTERS) struct kvm_pmu { u8 version; unsigned nr_arch_gp_counters; unsigned nr_arch_fixed_counters; unsigned available_event_types; u64 fixed_ctr_ctrl; u64 fixed_ctr_ctrl_rsvd; u64 global_ctrl; u64 global_status; u64 counter_bitmask[2]; u64 global_ctrl_rsvd; u64 global_status_rsvd; u64 reserved_bits; u64 raw_event_mask; struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS]; struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS]; /* * Overlay the bitmap with a 64-bit atomic so that all bits can be * set in a single access, e.g. to reprogram all counters when the PMU * filter changes. */ union { DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); atomic64_t __reprogram_pmi; }; DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); DECLARE_BITMAP(pmc_counting_instructions, X86_PMC_IDX_MAX); DECLARE_BITMAP(pmc_counting_branches, X86_PMC_IDX_MAX); u64 ds_area; u64 pebs_enable; u64 pebs_enable_rsvd; u64 pebs_data_cfg; u64 pebs_data_cfg_rsvd; /* * If a guest counter is cross-mapped to host counter with different * index, its PEBS capability will be temporarily disabled. * * The user should make sure that this mask is updated * after disabling interrupts and before perf_guest_get_msrs(); */ u64 host_cross_mapped_mask; /* * The gate to release perf_events not marked in * pmc_in_use only once in a vcpu time slice. */ bool need_cleanup; /* * The total number of programmed perf_events and it helps to avoid * redundant check before cleanup if guest don't use vPMU at all. */ u8 event_count; }; struct kvm_pmu_ops; enum { KVM_DEBUGREG_BP_ENABLED = BIT(0), KVM_DEBUGREG_WONT_EXIT = BIT(1), /* * Guest debug registers (DR0-3, DR6 and DR7) are saved/restored by * hardware on exit from or enter to guest. KVM needn't switch them. * DR0-3, DR6 and DR7 are set to their architectural INIT value on VM * exit, host values need to be restored. */ KVM_DEBUGREG_AUTO_SWITCH = BIT(2), }; struct kvm_mtrr { u64 var[KVM_NR_VAR_MTRR * 2]; u64 fixed_64k; u64 fixed_16k[2]; u64 fixed_4k[8]; u64 deftype; }; /* Hyper-V SynIC timer */ struct kvm_vcpu_hv_stimer { struct hrtimer timer; int index; union hv_stimer_config config; u64 count; u64 exp_time; struct hv_message msg; bool msg_pending; }; /* Hyper-V synthetic interrupt controller (SynIC)*/ struct kvm_vcpu_hv_synic { u64 version; u64 control; u64 msg_page; u64 evt_page; atomic64_t sint[HV_SYNIC_SINT_COUNT]; atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT]; DECLARE_BITMAP(auto_eoi_bitmap, 256); DECLARE_BITMAP(vec_bitmap, 256); bool active; bool dont_zero_synic_pages; }; /* The maximum number of entries on the TLB flush fifo. */ #define KVM_HV_TLB_FLUSH_FIFO_SIZE (16) /* * Note: the following 'magic' entry is made up by KVM to avoid putting * anything besides GVA on the TLB flush fifo. It is theoretically possible * to observe a request to flush 4095 PFNs starting from 0xfffffffffffff000 * which will look identical. KVM's action to 'flush everything' instead of * flushing these particular addresses is, however, fully legitimate as * flushing more than requested is always OK. */ #define KVM_HV_TLB_FLUSHALL_ENTRY ((u64)-1) enum hv_tlb_flush_fifos { HV_L1_TLB_FLUSH_FIFO, HV_L2_TLB_FLUSH_FIFO, HV_NR_TLB_FLUSH_FIFOS, }; struct kvm_vcpu_hv_tlb_flush_fifo { spinlock_t write_lock; DECLARE_KFIFO(entries, u64, KVM_HV_TLB_FLUSH_FIFO_SIZE); }; /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { struct kvm_vcpu *vcpu; u32 vp_index; u64 hv_vapic; s64 runtime_offset; struct kvm_vcpu_hv_synic synic; struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); bool enforce_cpuid; struct { u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ u32 features_ebx; /* HYPERV_CPUID_FEATURES.EBX */ u32 features_edx; /* HYPERV_CPUID_FEATURES.EDX */ u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ } cpuid_cache; struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS]; /* * Preallocated buffers for handling hypercalls that pass sparse vCPU * sets (for high vCPU counts, they're too large to comfortably fit on * the stack). */ u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS]; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); struct hv_vp_assist_page vp_assist_page; struct { u64 pa_page_gpa; u64 vm_id; u32 vp_id; } nested; }; struct kvm_hypervisor_cpuid { u32 base; u32 limit; }; #ifdef CONFIG_KVM_XEN /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; u32 current_runstate; u8 upcall_vector; struct gfn_to_pfn_cache vcpu_info_cache; struct gfn_to_pfn_cache vcpu_time_info_cache; struct gfn_to_pfn_cache runstate_cache; struct gfn_to_pfn_cache runstate2_cache; u64 last_steal; u64 runstate_entry_time; u64 runstate_times[4]; unsigned long evtchn_pending_sel; u32 vcpu_id; /* The Xen / ACPI vCPU ID */ u32 timer_virq; u64 timer_expires; /* In guest epoch */ atomic_t timer_pending; struct hrtimer timer; int poll_evtchn; struct timer_list poll_timer; struct kvm_hypervisor_cpuid cpuid; }; #endif struct kvm_queued_exception { bool pending; bool injected; bool has_error_code; u8 vector; u32 error_code; unsigned long payload; bool has_payload; }; /* * Hardware-defined CPUID leafs that are either scattered by the kernel or are * unknown to the kernel, but need to be directly used by KVM. Note, these * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. */ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, CPUID_7_1_EDX, CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, CPUID_7_2_EDX, CPUID_24_0_EBX, CPUID_8000_0021_ECX, CPUID_7_1_ECX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; struct kvm_vcpu_arch { /* * rip and regs accesses must go through * kvm_{register,rip}_{read,write} functions. */ unsigned long regs[NR_VCPU_REGS]; u32 regs_avail; u32 regs_dirty; unsigned long cr0; unsigned long cr0_guest_owned_bits; unsigned long cr2; unsigned long cr3; unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr4_guest_rsvd_bits; unsigned long cr8; u32 host_pkru; u32 pkru; u32 hflags; u64 efer; u64 host_debugctl; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ bool load_eoi_exitmap_pending; DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; int32_t apic_arb_prio; int mp_state; u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; bool at_instruction_boundary; bool tpr_access_reporting; bool xfd_no_write_intercept; u64 microcode_version; u64 arch_capabilities; u64 perf_capabilities; /* * Paging state of the vcpu * * If the vcpu runs in guest mode with two level paging this still saves * the paging mode of the l1 guest. This context is always used to * handle faults. */ struct kvm_mmu *mmu; /* Non-nested MMU for L1 */ struct kvm_mmu root_mmu; /* L1 MMU when running nested */ struct kvm_mmu guest_mmu; /* * Paging state of an L2 guest (used for nested npt) * * This context will save all necessary information to walk page tables * of an L2 guest. This context is only initialized for page table * walking and not for faulting since we never handle l2 page faults on * the host. */ struct kvm_mmu nested_mmu; /* * Pointer to the mmu context currently used for * gva_to_gpa translations. */ struct kvm_mmu *walk_mmu; struct kvm_mmu_memory_cache mmu_pte_list_desc_cache; struct kvm_mmu_memory_cache mmu_shadow_page_cache; struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; /* * This cache is to allocate external page table. E.g. private EPT used * by the TDX module. */ struct kvm_mmu_memory_cache mmu_external_spt_cache; /* * QEMU userspace and the guest each have their own FPU state. * In vcpu_run, we switch between the user and guest FPU contexts. * While running a VCPU, the VCPU thread will have the guest FPU * context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpstate" state here contains the guest FPU context, with the * host PRKU bits. */ struct fpu_guest guest_fpu; u64 xcr0; u64 guest_supported_xcr0; u64 ia32_xss; u64 guest_supported_xss; struct kvm_pio_request pio; void *pio_data; void *sev_pio_data; unsigned sev_pio_count; u8 event_exit_inst_len; bool exception_from_userspace; /* Exceptions to be injected to the guest. */ struct kvm_queued_exception exception; /* Exception VM-Exits to be synthesized to L1. */ struct kvm_queued_exception exception_vmexit; struct kvm_queued_interrupt { bool injected; bool soft; u8 nr; } interrupt; int halt_request; /* real mode on Intel only */ int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; bool cpuid_dynamic_bits_dirty; bool is_amd_compatible; /* * cpu_caps holds the effective guest capabilities, i.e. the features * the vCPU is allowed to use. Typically, but not always, features can * be used by the guest if and only if both KVM and userspace want to * expose the feature to the guest. * * A common exception is for virtualization holes, i.e. when KVM can't * prevent the guest from using a feature, in which case the vCPU "has" * the feature regardless of what KVM or userspace desires. * * Note, features that don't require KVM involvement in any way are * NOT enforced/sanitized by KVM, i.e. are taken verbatim from the * guest CPUID provided by userspace. */ u32 cpu_caps[NR_KVM_CPU_CAPS]; u64 reserved_gpa_bits; int maxphyaddr; /* emulate context */ struct x86_emulate_ctxt *emulate_ctxt; bool emulate_regs_need_sync_to_vcpu; bool emulate_regs_need_sync_from_vcpu; int (*complete_userspace_io)(struct kvm_vcpu *vcpu); unsigned long cui_linear_rip; int cui_rdmsr_imm_reg; gpa_t time; s8 pvclock_tsc_shift; u32 pvclock_tsc_mul; unsigned int hw_tsc_khz; struct gfn_to_pfn_cache pv_time; /* set guest stopped flag in pvclock flags field */ bool pvclock_set_guest_stopped_request; struct { u8 preempted; u64 msr_val; u64 last_steal; struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; u64 tsc_offset; /* current tsc offset */ u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; u64 this_tsc_nsec; u64 this_tsc_write; u64 this_tsc_generation; bool tsc_catchup; bool tsc_always_catchup; s8 virtual_tsc_shift; u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; u64 msr_ia32_power_ctl; u64 l1_tsc_scaling_ratio; u64 tsc_scaling_ratio; /* current scaling ratio */ atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ /* Number of NMIs pending injection, not including hardware vNMIs. */ unsigned int nmi_pending; bool nmi_injected; /* Trying to inject an NMI this entry */ bool smi_pending; /* SMI queued after currently running handler */ u8 handling_intr_from_guest; struct kvm_mtrr mtrr_state; u64 pat; unsigned switch_db_regs; unsigned long db[KVM_NR_DB_REGS]; unsigned long dr6; unsigned long dr7; unsigned long eff_db[KVM_NR_DB_REGS]; unsigned long guest_debug_dr7; u64 msr_platform_info; u64 msr_misc_features_enables; u64 mcg_cap; u64 mcg_status; u64 mcg_ctl; u64 mcg_ext_ctl; u64 *mce_banks; u64 *mci_ctl2_banks; /* Cache MMIO info */ u64 mmio_gva; unsigned mmio_access; gfn_t mmio_gfn; u64 mmio_gen; struct kvm_pmu pmu; /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; #ifdef CONFIG_KVM_HYPERV bool hyperv_enabled; struct kvm_vcpu_hv *hyperv; #endif #ifdef CONFIG_KVM_XEN struct kvm_vcpu_xen xen; #endif cpumask_var_t wbinvd_dirty_mask; unsigned long last_retry_eip; unsigned long last_retry_addr; struct { bool halted; gfn_t gfns[ASYNC_PF_PER_VCPU]; struct gfn_to_hva_cache data; u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */ u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */ u16 vec; u32 id; u32 host_apf_flags; bool send_always; bool delivery_as_pf_vmexit; bool pageready_pending; } apf; /* OSVW MSRs (AMD only) */ struct { u64 length; u64 status; } osvw; struct { u64 msr_val; struct gfn_to_hva_cache data; } pv_eoi; u64 msr_kvm_poll_control; /* pv related host specific info */ struct { bool pv_unhalted; } pv; int pending_ioapic_eoi; int pending_external_vector; int highest_stale_pending_ioapic_eoi; /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; /* Flush the L1 Data cache for L1TF mitigation on VMENTER */ bool l1tf_flush_l1d; /* Host CPU on which VM-entry was most recently attempted */ int last_vmentry_cpu; /* AMD MSRC001_0015 Hardware Configuration */ u64 msr_hwcr; /* pv related cpuid info */ struct { /* * value of the eax register in the KVM_CPUID_FEATURES CPUID * leaf. */ u32 features; /* * indicates whether pv emulation should be disabled if features * are not present in the guest's cpuid */ bool enforce; } pv_cpuid; /* Protected Guests */ bool guest_state_protected; bool guest_tsc_protected; /* * Set when PDPTS were loaded directly by the userspace without * reading the guest memory */ bool pdptrs_from_userspace; #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; #endif }; struct kvm_lpage_info { int disallow_lpage; }; struct kvm_arch_memory_slot { struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned short *gfn_write_track; }; /* * Track the mode of the optimized logical map, as the rules for decoding the * destination vary per mode. Enabling the optimized logical map requires all * software-enabled local APIs to be in the same mode, each addressable APIC to * be mapped to only one MDA, and each MDA to map to at most one APIC. */ enum kvm_apic_logical_mode { /* All local APICs are software disabled. */ KVM_APIC_MODE_SW_DISABLED, /* All software enabled local APICs in xAPIC cluster addressing mode. */ KVM_APIC_MODE_XAPIC_CLUSTER, /* All software enabled local APICs in xAPIC flat addressing mode. */ KVM_APIC_MODE_XAPIC_FLAT, /* All software enabled local APICs in x2APIC mode. */ KVM_APIC_MODE_X2APIC, /* * Optimized map disabled, e.g. not all local APICs in the same logical * mode, same logical ID assigned to multiple APICs, etc. */ KVM_APIC_MODE_MAP_DISABLED, }; struct kvm_apic_map { struct rcu_head rcu; enum kvm_apic_logical_mode logical_mode; u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; struct kvm_lapic *xapic_cluster_map[16][4]; }; struct kvm_lapic *phys_map[]; }; /* Hyper-V synthetic debugger (SynDbg)*/ struct kvm_hv_syndbg { struct { u64 control; u64 status; u64 send_page; u64 recv_page; u64 pending_page; } control; u64 options; }; /* Current state of Hyper-V TSC page clocksource */ enum hv_tsc_page_status { /* TSC page was not set up or disabled */ HV_TSC_PAGE_UNSET = 0, /* TSC page MSR was written by the guest, update pending */ HV_TSC_PAGE_GUEST_CHANGED, /* TSC page update was triggered from the host side */ HV_TSC_PAGE_HOST_CHANGED, /* TSC page was properly set up and is currently active */ HV_TSC_PAGE_SET, /* TSC page was set up with an inaccessible GPA */ HV_TSC_PAGE_BROKEN, }; #ifdef CONFIG_KVM_HYPERV /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; u64 hv_guest_os_id; u64 hv_hypercall; u64 hv_tsc_page; enum hv_tsc_page_status hv_tsc_page_status; /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; u64 hv_crash_ctl; struct ms_hyperv_tsc_page tsc_ref; struct idr conn_to_evt; u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; u64 hv_invtsc_control; /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; /* * How many SynICs use 'AutoEOI' feature * (protected by arch.apicv_update_lock) */ unsigned int synic_auto_eoi_used; struct kvm_hv_syndbg hv_syndbg; bool xsaves_xsavec_checked; }; #endif struct msr_bitmap_range { u32 flags; u32 nmsrs; u32 base; unsigned long *bitmap; }; #ifdef CONFIG_KVM_XEN /* Xen emulation context */ struct kvm_xen { struct mutex xen_lock; u32 xen_version; bool long_mode; bool runstate_update_flag; u8 upcall_vector; struct gfn_to_pfn_cache shinfo_cache; struct idr evtchn_ports; unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; struct kvm_xen_hvm_config hvm_config; }; #endif enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; struct kvm_x86_msr_filter { u8 count; bool default_allow:1; struct msr_bitmap_range ranges[16]; }; struct kvm_x86_pmu_event_filter { __u32 action; __u32 nevents; __u32 fixed_counter_bitmap; __u32 flags; __u32 nr_includes; __u32 nr_excludes; __u64 *includes; __u64 *excludes; __u64 events[]; }; enum kvm_apicv_inhibit { /********************************************************************/ /* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */ /********************************************************************/ /* * APIC acceleration is disabled by a module parameter * and/or not supported in hardware. */ APICV_INHIBIT_REASON_DISABLED, /* * APIC acceleration is inhibited because AutoEOI feature is * being used by a HyperV guest. */ APICV_INHIBIT_REASON_HYPERV, /* * APIC acceleration is inhibited because the userspace didn't yet * enable the kernel/split irqchip. */ APICV_INHIBIT_REASON_ABSENT, /* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ * (out of band, debug measure of blocking all interrupts on this vCPU) * was enabled, to avoid AVIC/APICv bypassing it. */ APICV_INHIBIT_REASON_BLOCKIRQ, /* * APICv is disabled because not all vCPUs have a 1:1 mapping between * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack. */ APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED, /* * For simplicity, the APIC acceleration is inhibited * first time either APIC ID or APIC base are changed by the guest * from their reset values. */ APICV_INHIBIT_REASON_APIC_ID_MODIFIED, APICV_INHIBIT_REASON_APIC_BASE_MODIFIED, /******************************************************/ /* INHIBITs that are relevant only to the AMD's AVIC. */ /******************************************************/ /* * AVIC is inhibited on a vCPU because it runs a nested guest. * * This is needed because unlike APICv, the peers of this vCPU * cannot use the doorbell mechanism to signal interrupts via AVIC when * a vCPU runs nested. */ APICV_INHIBIT_REASON_NESTED, /* * On SVM, the wait for the IRQ window is implemented with pending vIRQ, * which cannot be injected when the AVIC is enabled, thus AVIC * is inhibited while KVM waits for IRQ window. */ APICV_INHIBIT_REASON_IRQWIN, /* * PIT (i8254) 're-inject' mode, relies on EOI intercept, * which AVIC doesn't support for edge triggered interrupts. */ APICV_INHIBIT_REASON_PIT_REINJ, /* * AVIC is disabled because SEV doesn't support it. */ APICV_INHIBIT_REASON_SEV, /* * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1 * mapping between logical ID and vCPU. */ APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, /* * AVIC is disabled because the vCPU's APIC ID is beyond the max * supported by AVIC/x2AVIC, i.e. the vCPU is unaddressable. */ APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG, NR_APICV_INHIBIT_REASONS, }; #define __APICV_INHIBIT_REASON(reason) \ { BIT(APICV_INHIBIT_REASON_##reason), #reason } #define APICV_INHIBIT_REASONS \ __APICV_INHIBIT_REASON(DISABLED), \ __APICV_INHIBIT_REASON(HYPERV), \ __APICV_INHIBIT_REASON(ABSENT), \ __APICV_INHIBIT_REASON(BLOCKIRQ), \ __APICV_INHIBIT_REASON(PHYSICAL_ID_ALIASED), \ __APICV_INHIBIT_REASON(APIC_ID_MODIFIED), \ __APICV_INHIBIT_REASON(APIC_BASE_MODIFIED), \ __APICV_INHIBIT_REASON(NESTED), \ __APICV_INHIBIT_REASON(IRQWIN), \ __APICV_INHIBIT_REASON(PIT_REINJ), \ __APICV_INHIBIT_REASON(SEV), \ __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED), \ __APICV_INHIBIT_REASON(PHYSICAL_ID_TOO_BIG) struct kvm_possible_nx_huge_pages { /* * A list of kvm_mmu_page structs that, if zapped, could possibly be * replaced by an NX huge page. A shadow page is on this list if its * existence disallows an NX huge page (nx_huge_page_disallowed is set) * and there are no other conditions that prevent a huge page, e.g. * the backing host page is huge, dirtly logging is not enabled for its * memslot, etc... Note, zapping shadow pages on this list doesn't * guarantee an NX huge page will be created in its stead, e.g. if the * guest attempts to execute from the region then KVM obviously can't * create an NX huge page (without hanging the guest). */ struct list_head pages; u64 nr_pages; }; enum kvm_mmu_type { KVM_SHADOW_MMU, #ifdef CONFIG_X86_64 KVM_TDP_MMU, #endif KVM_NR_MMU_TYPES, }; struct kvm_arch { unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; u8 mmu_valid_gen; u8 vm_type; bool has_private_mem; bool has_protected_state; bool has_protected_eoi; bool pre_fault_allowed; struct hlist_head *mmu_page_hash; struct list_head active_mmu_pages; struct kvm_possible_nx_huge_pages possible_nx_huge_pages[KVM_NR_MMU_TYPES]; #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING struct kvm_page_track_notifier_head track_notifier_head; #endif /* * Protects marking pages unsync during page faults, as TDP MMU page * faults only take mmu_lock for read. For simplicity, the unsync * pages lock is always taken when marking pages unsync regardless of * whether mmu_lock is held for read or write. */ spinlock_t mmu_unsync_pages_lock; u64 shadow_mmio_value; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; unsigned long nr_possible_bypass_irqs; #ifdef CONFIG_KVM_IOAPIC struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; #endif atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; bool apic_access_memslot_enabled; bool apic_access_memslot_inhibited; /* Protects apicv_inhibit_reasons */ struct rw_semaphore apicv_update_lock; unsigned long apicv_inhibit_reasons; gpa_t wall_clock; u64 disabled_exits; s64 kvmclock_offset; /* * This also protects nr_vcpus_matched_tsc which is read from a * preemption-disabled region, so it must be a raw spinlock. */ raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; u64 last_tsc_write; u32 last_tsc_khz; u64 last_tsc_offset; u64 cur_tsc_nsec; u64 cur_tsc_write; u64 cur_tsc_offset; u64 cur_tsc_generation; int nr_vcpus_matched_tsc; u32 default_tsc_khz; bool user_set_tsc; u64 apic_bus_cycle_ns; seqcount_raw_spinlock_t pvclock_sc; bool use_master_clock; u64 master_kernel_ns; u64 master_cycle_now; struct delayed_work kvmclock_update_work; struct delayed_work kvmclock_sync_work; #ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; #endif #ifdef CONFIG_KVM_XEN struct kvm_xen xen; #endif bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; u32 bsp_vcpu_id; u64 disabled_quirks; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; bool disabled_lapic_found; bool x2apic_format; bool x2apic_broadcast_quirk_disabled; bool has_mapped_host_mmio; bool guest_can_read_msr_platform_info; bool exception_payload_enabled; bool triple_fault_event; bool bus_lock_detection_enabled; bool enable_pmu; u32 notify_window; u32 notify_vmexit_flags; /* * If exit_on_emulation_error is set, and the in-kernel instruction * emulator fails to emulate an instruction, allow userspace * the opportunity to look at it. */ bool exit_on_emulation_error; /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; struct kvm_x86_msr_filter __rcu *msr_filter; u32 hypercall_exit_enabled; /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct vhost_task *nx_huge_page_recovery_thread; u64 nx_huge_page_last; struct once nx_once; #ifdef CONFIG_X86_64 #ifdef CONFIG_KVM_PROVE_MMU /* * The number of TDP MMU pages across all roots. Used only to sanity * check that KVM isn't leaking TDP MMU pages. */ atomic64_t tdp_mmu_pages; #endif /* * List of struct kvm_mmu_pages being used as roots. * All struct kvm_mmu_pages in the list should have * tdp_mmu_page set. * * For reads, this list is protected by: * RCU alone or * the MMU lock in read mode + RCU or * the MMU lock in write mode * * For writes, this list is protected by tdp_mmu_pages_lock; see * below for the details. * * Roots will remain in the list until their tdp_mmu_root_count * drops to zero, at which point the thread that decremented the * count to zero should removed the root from the list and clean * it up, freeing the root after an RCU grace period. */ struct list_head tdp_mmu_roots; /* * Protects accesses to the following fields when the MMU lock * is held in read mode: * - tdp_mmu_roots (above) * - the link field of kvm_mmu_page structs used by the TDP MMU * - possible_nx_huge_pages[KVM_TDP_MMU]; * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU * Because the lock is only taken within the MMU lock, strictly * speaking it is redundant to acquire this lock when the thread * holds the MMU lock in write mode. However it often simplifies * the code to do so. */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ /* * If set, at least one shadow root has been allocated. This flag * is used as one input when determining whether certain memslot * related allocations are necessary. */ bool shadow_root_allocated; #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING /* * If set, the VM has (or had) an external write tracking user, and * thus all write tracking metadata has been allocated, even if KVM * itself isn't using write tracking. */ bool external_write_tracking_enabled; #endif #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; spinlock_t hv_root_tdp_lock; struct hv_partition_assist_pg *hv_pa_pg; #endif /* * VM-scope maximum vCPU ID. Used to determine the size of structures * that increase along with the maximum vCPU ID, in which case, using * the global KVM_MAX_VCPU_IDS may lead to significant memory waste. */ u32 max_vcpu_ids; bool disable_nx_huge_pages; /* * Memory caches used to allocate shadow pages when performing eager * page splitting. No need for a shadowed_info_cache since eager page * splitting only allocates direct shadow pages. * * Protected by kvm->slots_lock. */ struct kvm_mmu_memory_cache split_shadow_page_cache; struct kvm_mmu_memory_cache split_page_header_cache; /* * Memory cache used to allocate pte_list_desc structs while splitting * huge pages. In the worst case, to split one huge page, 512 * pte_list_desc structs are needed to add each lower level leaf sptep * to the rmap plus 1 to extend the parent_ptes rmap of the lower level * page table. * * Protected by kvm->slots_lock. */ #define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) struct kvm_mmu_memory_cache split_desc_cache; gfn_t gfn_direct_bits; /* * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A Zero * value indicates CPU dirty logging is unsupported or disabled in * current VM. */ int cpu_dirty_log_size; }; struct kvm_vm_stat { struct kvm_vm_stat_generic generic; u64 mmu_shadow_zapped; u64 mmu_pte_write; u64 mmu_pde_zapped; u64 mmu_flooded; u64 mmu_recycled; u64 mmu_cache_miss; u64 mmu_unsync; union { struct { atomic64_t pages_4k; atomic64_t pages_2m; atomic64_t pages_1g; }; atomic64_t pages[KVM_NR_PAGE_SIZES]; }; u64 nx_lpage_splits; u64 max_mmu_page_hash_collisions; u64 max_mmu_rmap_size; }; struct kvm_vcpu_stat { struct kvm_vcpu_stat_generic generic; u64 pf_taken; u64 pf_fixed; u64 pf_emulate; u64 pf_spurious; u64 pf_fast; u64 pf_mmio_spte_created; u64 pf_guest; u64 tlb_flush; u64 invlpg; u64 exits; u64 io_exits; u64 mmio_exits; u64 signal_exits; u64 irq_window_exits; u64 nmi_window_exits; u64 l1d_flush; u64 halt_exits; u64 request_irq_exits; u64 irq_exits; u64 host_state_reload; u64 fpu_reload; u64 insn_emulation; u64 insn_emulation_fail; u64 hypercalls; u64 irq_injections; u64 nmi_injections; u64 req_event; u64 nested_run; u64 directed_yield_attempted; u64 directed_yield_successful; u64 preemption_reported; u64 preemption_other; u64 guest_mode; u64 notify_window_exits; }; struct x86_instruction_info; struct msr_data { bool host_initiated; u32 index; u64 data; }; struct kvm_lapic_irq { u32 vector; u16 delivery_mode; u16 dest_mode; bool level; u16 trig_mode; u32 shorthand; u32 dest_id; bool msi_redir_hint; }; static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) { return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; } enum kvm_x86_run_flags { KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0), KVM_RUN_LOAD_GUEST_DR6 = BIT(1), KVM_RUN_LOAD_DEBUGCTL = BIT(2), }; struct kvm_x86_ops { const char *name; int (*check_processor_compatibility)(void); int (*enable_virtualization_cpu)(void); void (*disable_virtualization_cpu)(void); cpu_emergency_virt_cb *emergency_disable_virtualization_cpu; void (*hardware_unsetup)(void); bool (*has_emulated_msr)(struct kvm *kvm, u32 index); void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); unsigned int vm_size; int (*vm_init)(struct kvm *kvm); void (*vm_destroy)(struct kvm *kvm); void (*vm_pre_destroy)(struct kvm *kvm); /* Create, but do not attach this VCPU */ int (*vcpu_precreate)(struct kvm *kvm); int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); void (*prepare_switch_to_guest)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); /* * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to * match the host's value even while the guest is active. */ const u64 HOST_OWNED_DEBUGCTL; void (*update_exception_bitmap)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int (*get_cpl)(struct kvm_vcpu *vcpu); int (*get_cpl_no_cache)(struct kvm_vcpu *vcpu); void (*set_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); bool (*is_valid_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*post_set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); bool (*get_if_flag)(struct kvm_vcpu *vcpu); void (*flush_tlb_all)(struct kvm_vcpu *vcpu); void (*flush_tlb_current)(struct kvm_vcpu *vcpu); #if IS_ENABLED(CONFIG_HYPERV) int (*flush_remote_tlbs)(struct kvm *kvm); int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); #endif /* * Flush any TLB entries associated with the given GVA. * Does not need to flush GPA->HPA mappings. * Can potentially get non-canonical addresses through INVLPGs, which * the implementation may choose to ignore if appropriate. */ void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr); /* * Flush any TLB entries created by the guest. Like tlb_flush_gva(), * does not need to flush GPA->HPA mappings. */ void (*flush_tlb_guest)(struct kvm_vcpu *vcpu); int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, u64 run_flags); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, unsigned char *hypercall_addr); void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); void (*inject_nmi)(struct kvm_vcpu *vcpu); void (*inject_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); /* Whether or not a virtual NMI is pending in hardware. */ bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu); /* * Attempt to pend a virtual NMI in hardware. Returns %true on success * to allow using static_call_ret0 as the fallback. */ bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); const bool x2apic_icr_is_split; const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); u8 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); /* Update external mapping with page table link. */ int (*link_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, void *external_spt); /* Update the external page table from spte getting set. */ int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, kvm_pfn_t pfn_for_gfn); /* Update external page tables for page table about to be freed. */ int (*free_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, void *external_spt); /* Update external page table from spte getting removed, and flush TLB. */ int (*remove_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, kvm_pfn_t pfn_for_gfn); bool (*has_wbinvd_exit)(void); u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu); /* * Retrieve somewhat arbitrary exit/entry information. Intended to * be used only from within tracepoints or error paths. */ void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); void (*get_entry_info)(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage, struct x86_exception *exception); void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu); const struct kvm_x86_nested_ops *nested_ops; void (*vcpu_blocking)(struct kvm_vcpu *vcpu); void (*vcpu_unblocking)(struct kvm_vcpu *vcpu); int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct kvm_vcpu *vcpu, u32 vector); void (*pi_start_bypass)(struct kvm *kvm); void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); bool (*protected_apic_has_interrupt)(struct kvm_vcpu *vcpu); int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired); void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); void (*setup_mce)(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_SMM int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram); int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram); void (*enable_smi_window)(struct kvm_vcpu *vcpu); #endif int (*dev_get_attr)(u32 group, u64 attr, u64 *val); int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); int (*vcpu_mem_enc_ioctl)(struct kvm_vcpu *vcpu, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); void (*guest_memory_reclaimed)(struct kvm *kvm); int (*get_feature_msr)(u32 msr, u64 *data); int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*recalc_intercepts)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); /* * Returns vCPU specific APICv inhibit reasons */ unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); int (*gmem_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn, bool is_private); }; struct kvm_x86_nested_ops { void (*leave_nested)(struct kvm_vcpu *vcpu); bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, unsigned user_data_size); int (*set_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state); bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu); int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int (*enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu); }; struct kvm_x86_init_ops { int (*hardware_setup)(void); unsigned int (*handle_intel_pt_intr)(void); struct kvm_x86_ops *runtime_ops; struct kvm_pmu_ops *pmu_ops; }; struct kvm_arch_async_pf { u32 token; gfn_t gfn; unsigned long cr3; bool direct_map; u64 error_code; }; extern u32 __read_mostly kvm_nr_uret_msrs; extern bool __read_mostly allow_smaller_maxphyaddr; extern bool __read_mostly enable_apicv; extern bool __read_mostly enable_ipiv; extern bool __read_mostly enable_device_posted_irqs; extern struct kvm_x86_ops kvm_x86_ops; #define kvm_x86_call(func) static_call(kvm_x86_##func) #define kvm_pmu_call(func) static_call(kvm_x86_pmu_##func) #define KVM_X86_OP(func) \ DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func)); #define KVM_X86_OP_OPTIONAL KVM_X86_OP #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops); void kvm_x86_vendor_exit(void); #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { return kvzalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT); } #define __KVM_HAVE_ARCH_VM_FREE void kvm_arch_free_vm(struct kvm *kvm); #if IS_ENABLED(CONFIG_HYPERV) #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { if (kvm_x86_ops.flush_remote_tlbs && !kvm_x86_call(flush_remote_tlbs)(kvm)) return 0; else return -ENOTSUPP; } #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { if (!kvm_x86_ops.flush_remote_tlbs_range) return -EOPNOTSUPP; return kvm_x86_call(flush_remote_tlbs_range)(kvm, gfn, nr_pages); } #endif /* CONFIG_HYPERV */ enum kvm_intr_type { /* Values are arbitrary, but must be non-zero. */ KVM_HANDLING_IRQ = 1, KVM_HANDLING_NMI, }; /* Enable perf NMI and timer modes to work, and minimise false positives. */ #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest && \ (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI))) void __init kvm_mmu_x86_module_init(void); int kvm_mmu_vendor_module_init(void); void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); int kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, const struct kvm_memory_slot *memslot, int start_level); void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot, int target_level); void kvm_mmu_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot, u64 start, u64 end, int target_level); void kvm_mmu_recover_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); extern bool tdp_enabled; u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); /* * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing * userspace I/O) to indicate that the emulation context * should be reused as is, i.e. skip initialization of * emulation context, instruction fetch and decode. * * EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware. * Indicates that only select instructions (tagged with * EmulateOnUD) should be emulated (to minimize the emulator * attack surface). See also EMULTYPE_TRAP_UD_FORCED. * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by * kvm_x86_ops.skip_emulated_instruction() implementations if * EMULTYPE_COMPLETE_USER_EXIT is not set. * * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to * retry native execution under certain conditions, * Can only be set in conjunction with EMULTYPE_PF. * * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was * triggered by KVM's magic "force emulation" prefix, * which is opt in via module param (off by default). * Bypasses EmulateOnUD restriction despite emulating * due to an intercepted #UD (see EMULTYPE_TRAP_UD). * Used to test the full emulator from userspace. * * EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware * backdoor emulation, which is opt in via module param. * VMware backdoor emulation handles select instructions * and reinjects the #GP for all other cases. * * EMULTYPE_PF - Set when an intercepted #PF triggers the emulation, in which case * the CR2/GPA value pass on the stack is valid. * * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility * state and inject single-step #DBs after skipping * an instruction (after completing userspace I/O). * * EMULTYPE_WRITE_PF_TO_SP - Set when emulating an intercepted page fault that * is attempting to write a gfn that contains one or * more of the PTEs used to translate the write itself, * and the owning page table is being shadowed by KVM. * If emulation of the faulting instruction fails and * this flag is set, KVM will exit to userspace instead * of retrying emulation as KVM cannot make forward * progress. * * If emulation fails for a write to guest page tables, * KVM unprotects (zaps) the shadow page for the target * gfn and resumes the guest to retry the non-emulatable * instruction (on hardware). Unprotecting the gfn * doesn't allow forward progress for a self-changing * access because doing so also zaps the translation for * the gfn, i.e. retrying the instruction will hit a * !PRESENT fault, which results in a new shadow page * and sends KVM back to square one. */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) #define EMULTYPE_ALLOW_RETRY_PF (1 << 3) #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) #define EMULTYPE_PF (1 << 6) #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) static inline bool kvm_can_emulate_event_vectoring(int emul_type) { return !(emul_type & EMULTYPE_PF); } int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); int kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data); int kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data); int __kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data); int __kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data); int kvm_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data); int kvm_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data); int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu); int kvm_emulate_rdmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg); int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu); int kvm_emulate_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg); int kvm_emulate_as_nop(struct kvm_vcpu *vcpu); int kvm_emulate_invd(struct kvm_vcpu *vcpu); int kvm_emulate_mwait(struct kvm_vcpu *vcpu); int kvm_handle_invalid_op(struct kvm_vcpu *vcpu); int kvm_emulate_monitor(struct kvm_vcpu *vcpu); int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0); void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu); int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload); void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr, bool has_error_code, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr); static inline int __kvm_irq_line_state(unsigned long *irq_state, int irq_source_id, int level) { /* Logical OR for level trig interrupt */ if (level) __set_bit(irq_source_id, irq_state); else __clear_bit(irq_source_id, irq_state); return !!(*irq_state); } void kvm_inject_nmi(struct kvm_vcpu *vcpu); int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool always_retry); static inline bool kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa) { return __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, false); } void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); bool kvm_apicv_activated(struct kvm *kvm); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu); void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); static inline void kvm_set_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason) { kvm_set_or_clear_apicv_inhibit(kvm, reason, true); } static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason) { kvm_set_or_clear_apicv_inhibit(kvm, reason, false); } int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, unsigned long roots); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES #define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) #endif #define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) static inline u16 kvm_read_ldt(void) { u16 ldt; asm("sldt %0" : "=g"(ldt)); return ldt; } static inline void kvm_load_ldt(u16 sel) { asm("lldt %0" : : "rm"(sel)); } #ifdef CONFIG_X86_64 static inline unsigned long read_msr(unsigned long msr) { u64 value; rdmsrq(msr, value); return value; } #endif static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); } #define TSS_IOPB_BASE_OFFSET 0x66 #define TSS_BASE_SIZE 0x68 #define TSS_IOPB_SIZE (65536 / 8) #define TSS_REDIRECTION_SIZE (256 / 8) #define RMODE_TSS_SIZE \ (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1) enum { TASK_SWITCH_CALL = 0, TASK_SWITCH_IRET = 1, TASK_SWITCH_JMP = 2, TASK_SWITCH_GATE = 3, }; #define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ #ifdef CONFIG_KVM_SMM #define HF_SMM_MASK (1 << 1) #define HF_SMM_INSIDE_NMI_MASK (1 << 2) # define KVM_MAX_NR_ADDRESS_SPACES 2 /* SMM is currently unsupported for guests with private memory. */ # define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) #else # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) #endif int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_extint(struct kvm_vcpu *v); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); int kvm_add_user_return_msr(u32 msr); int kvm_find_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); void kvm_user_return_msr_update_cache(unsigned int index, u64 val); u64 kvm_get_user_return_msr(unsigned int slot); static inline bool kvm_is_supported_user_return_msr(u32 msr) { return kvm_find_user_return_msr(msr) >= 0; } u64 kvm_scale_tsc(u64 tsc, u64 ratio); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); void kvm_make_scan_ioapic_request(struct kvm *kvm); void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap); bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu); bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu); extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ return (irq->delivery_mode == APIC_DM_FIXED || irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { kvm_x86_call(vcpu_blocking)(vcpu); } static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { kvm_x86_call(vcpu_unblocking)(vcpu); } static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC return default_cpu_present_to_apicid(mps_cpu); #else WARN_ON_ONCE(1); return BAD_APICID; #endif } int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); #define KVM_CLOCK_VALID_FLAGS \ (KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC) #define KVM_X86_VALID_QUIRKS \ (KVM_X86_QUIRK_LINT0_REENABLED | \ KVM_X86_QUIRK_CD_NW_CLEARED | \ KVM_X86_QUIRK_LAPIC_MMIO_HOLE | \ KVM_X86_QUIRK_OUT_7E_INC_RIP | \ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \ KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ KVM_X86_QUIRK_SLOT_ZAP_ALL | \ KVM_X86_QUIRK_STUFF_FEATURE_MSRS | \ KVM_X86_QUIRK_IGNORE_GUEST_PAT) #define KVM_X86_CONDITIONAL_QUIRKS \ (KVM_X86_QUIRK_CD_NW_CLEARED | \ KVM_X86_QUIRK_IGNORE_GUEST_PAT) /* * KVM previously used a u32 field in kvm_run to indicate the hypercall was * initiated from long mode. KVM now sets bit 0 to indicate long mode, but the * remaining 31 lower bits must be 0 to preserve ABI. */ #define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1) static inline bool kvm_arch_has_irq_bypass(void) { return enable_device_posted_irqs; } #endif /* _ASM_X86_KVM_HOST_H */ |
| 422 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2018 HUAWEI, Inc. * https://www.huawei.com/ * Copyright (C) 2024 Alibaba Cloud */ #include "internal.h" struct z_erofs_gbuf { spinlock_t lock; void *ptr; struct page **pages; unsigned int nrpages; }; static struct z_erofs_gbuf *z_erofs_gbufpool, *z_erofs_rsvbuf; static unsigned int z_erofs_gbuf_count, z_erofs_gbuf_nrpages, z_erofs_rsv_nrpages; module_param_named(global_buffers, z_erofs_gbuf_count, uint, 0444); module_param_named(reserved_pages, z_erofs_rsv_nrpages, uint, 0444); atomic_long_t erofs_global_shrink_cnt; /* for all mounted instances */ /* protects `erofs_sb_list_lock` and the mounted `erofs_sb_list` */ static DEFINE_SPINLOCK(erofs_sb_list_lock); static LIST_HEAD(erofs_sb_list); static unsigned int shrinker_run_no; static struct shrinker *erofs_shrinker_info; static unsigned int z_erofs_gbuf_id(void) { return raw_smp_processor_id() % z_erofs_gbuf_count; } void *z_erofs_get_gbuf(unsigned int requiredpages) __acquires(gbuf->lock) { struct z_erofs_gbuf *gbuf; migrate_disable(); gbuf = &z_erofs_gbufpool[z_erofs_gbuf_id()]; spin_lock(&gbuf->lock); /* check if the buffer is too small */ if (requiredpages > gbuf->nrpages) { spin_unlock(&gbuf->lock); migrate_enable(); /* (for sparse checker) pretend gbuf->lock is still taken */ __acquire(gbuf->lock); return NULL; } return gbuf->ptr; } void z_erofs_put_gbuf(void *ptr) __releases(gbuf->lock) { struct z_erofs_gbuf *gbuf; gbuf = &z_erofs_gbufpool[z_erofs_gbuf_id()]; DBG_BUGON(gbuf->ptr != ptr); spin_unlock(&gbuf->lock); migrate_enable(); } int z_erofs_gbuf_growsize(unsigned int nrpages) { static DEFINE_MUTEX(gbuf_resize_mutex); struct page **tmp_pages = NULL; struct z_erofs_gbuf *gbuf; void *ptr, *old_ptr; int last, i, j; mutex_lock(&gbuf_resize_mutex); /* avoid shrinking gbufs, since no idea how many fses rely on */ if (nrpages <= z_erofs_gbuf_nrpages) { mutex_unlock(&gbuf_resize_mutex); return 0; } for (i = 0; i < z_erofs_gbuf_count; ++i) { gbuf = &z_erofs_gbufpool[i]; tmp_pages = kcalloc(nrpages, sizeof(*tmp_pages), GFP_KERNEL); if (!tmp_pages) goto out; for (j = 0; j < gbuf->nrpages; ++j) tmp_pages[j] = gbuf->pages[j]; do { last = j; j = alloc_pages_bulk(GFP_KERNEL, nrpages, tmp_pages); if (last == j) goto out; } while (j != nrpages); ptr = vmap(tmp_pages, nrpages, VM_MAP, PAGE_KERNEL); if (!ptr) goto out; spin_lock(&gbuf->lock); kfree(gbuf->pages); gbuf->pages = tmp_pages; old_ptr = gbuf->ptr; gbuf->ptr = ptr; gbuf->nrpages = nrpages; spin_unlock(&gbuf->lock); if (old_ptr) vunmap(old_ptr); } z_erofs_gbuf_nrpages = nrpages; out: if (i < z_erofs_gbuf_count && tmp_pages) { for (j = 0; j < nrpages; ++j) if (tmp_pages[j] && (j >= gbuf->nrpages || tmp_pages[j] != gbuf->pages[j])) __free_page(tmp_pages[j]); kfree(tmp_pages); } mutex_unlock(&gbuf_resize_mutex); return i < z_erofs_gbuf_count ? -ENOMEM : 0; } int __init z_erofs_gbuf_init(void) { unsigned int i, total = num_possible_cpus(); if (z_erofs_gbuf_count) total = min(z_erofs_gbuf_count, total); z_erofs_gbuf_count = total; /* The last (special) global buffer is the reserved buffer */ total += !!z_erofs_rsv_nrpages; z_erofs_gbufpool = kcalloc(total, sizeof(*z_erofs_gbufpool), GFP_KERNEL); if (!z_erofs_gbufpool) return -ENOMEM; if (z_erofs_rsv_nrpages) { z_erofs_rsvbuf = &z_erofs_gbufpool[total - 1]; z_erofs_rsvbuf->pages = kcalloc(z_erofs_rsv_nrpages, sizeof(*z_erofs_rsvbuf->pages), GFP_KERNEL); if (!z_erofs_rsvbuf->pages) { z_erofs_rsvbuf = NULL; z_erofs_rsv_nrpages = 0; } } for (i = 0; i < total; ++i) spin_lock_init(&z_erofs_gbufpool[i].lock); return 0; } void z_erofs_gbuf_exit(void) { int i, j; for (i = 0; i < z_erofs_gbuf_count + (!!z_erofs_rsvbuf); ++i) { struct z_erofs_gbuf *gbuf = &z_erofs_gbufpool[i]; if (gbuf->ptr) { vunmap(gbuf->ptr); gbuf->ptr = NULL; } if (!gbuf->pages) continue; for (j = 0; j < gbuf->nrpages; ++j) if (gbuf->pages[j]) put_page(gbuf->pages[j]); kfree(gbuf->pages); gbuf->pages = NULL; } kfree(z_erofs_gbufpool); } struct page *__erofs_allocpage(struct page **pagepool, gfp_t gfp, bool tryrsv) { struct page *page = *pagepool; if (page) { *pagepool = (struct page *)page_private(page); } else if (tryrsv && z_erofs_rsvbuf && z_erofs_rsvbuf->nrpages) { spin_lock(&z_erofs_rsvbuf->lock); if (z_erofs_rsvbuf->nrpages) page = z_erofs_rsvbuf->pages[--z_erofs_rsvbuf->nrpages]; spin_unlock(&z_erofs_rsvbuf->lock); } if (!page) page = alloc_page(gfp); DBG_BUGON(page && page_ref_count(page) != 1); return page; } void erofs_release_pages(struct page **pagepool) { while (*pagepool) { struct page *page = *pagepool; *pagepool = (struct page *)page_private(page); /* try to fill reserved global pool first */ if (z_erofs_rsvbuf && z_erofs_rsvbuf->nrpages < z_erofs_rsv_nrpages) { spin_lock(&z_erofs_rsvbuf->lock); if (z_erofs_rsvbuf->nrpages < z_erofs_rsv_nrpages) { z_erofs_rsvbuf->pages[z_erofs_rsvbuf->nrpages++] = page; spin_unlock(&z_erofs_rsvbuf->lock); continue; } spin_unlock(&z_erofs_rsvbuf->lock); } put_page(page); } } void erofs_shrinker_register(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); mutex_init(&sbi->umount_mutex); spin_lock(&erofs_sb_list_lock); list_add(&sbi->list, &erofs_sb_list); spin_unlock(&erofs_sb_list_lock); } void erofs_shrinker_unregister(struct super_block *sb) { struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); while (!xa_empty(&sbi->managed_pslots)) { z_erofs_shrink_scan(sbi, ~0UL); cond_resched(); } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); mutex_unlock(&sbi->umount_mutex); } static unsigned long erofs_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return atomic_long_read(&erofs_global_shrink_cnt) ?: SHRINK_EMPTY; } static unsigned long erofs_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct erofs_sb_info *sbi; struct list_head *p; unsigned long nr = sc->nr_to_scan; unsigned int run_no; unsigned long freed = 0; spin_lock(&erofs_sb_list_lock); do { run_no = ++shrinker_run_no; } while (run_no == 0); /* Iterate over all mounted superblocks and try to shrink them */ p = erofs_sb_list.next; while (p != &erofs_sb_list) { sbi = list_entry(p, struct erofs_sb_info, list); /* * We move the ones we do to the end of the list, so we stop * when we see one we have already done. */ if (sbi->shrinker_run_no == run_no) break; if (!mutex_trylock(&sbi->umount_mutex)) { p = p->next; continue; } spin_unlock(&erofs_sb_list_lock); sbi->shrinker_run_no = run_no; freed += z_erofs_shrink_scan(sbi, nr - freed); spin_lock(&erofs_sb_list_lock); /* Get the next list element before we move this one */ p = p->next; /* * Move this one to the end of the list to provide some * fairness. */ list_move_tail(&sbi->list, &erofs_sb_list); mutex_unlock(&sbi->umount_mutex); if (freed >= nr) break; } spin_unlock(&erofs_sb_list_lock); return freed; } int __init erofs_init_shrinker(void) { erofs_shrinker_info = shrinker_alloc(0, "erofs-shrinker"); if (!erofs_shrinker_info) return -ENOMEM; erofs_shrinker_info->count_objects = erofs_shrink_count; erofs_shrinker_info->scan_objects = erofs_shrink_scan; shrinker_register(erofs_shrinker_info); return 0; } void erofs_exit_shrinker(void) { shrinker_free(erofs_shrinker_info); } |
| 3666 2459 2459 2458 1597 97 97 1606 1608 30 1602 435 1602 1611 97 3600 282 3600 3610 3600 30 241 114 3610 3609 3609 3606 3610 134 3621 3614 3608 3614 3609 6099 6112 6111 6095 6102 2341 6100 6112 18 18 18 18 18 18 1 73 73 73 73 73 73 73 73 2192 63 74 74 74 2606 2608 2602 1972 1795 890 694 1677 48 20 20 48 2611 2605 2611 6062 6064 6076 6045 5062 6062 4284 4285 152 4183 3 3 3 3 1 1 1 1 1 1 1 1 1 1 11 11 11 11 11 11 11 30 30 30 30 30 30 30 30 30 30 2198 2110 2193 18 18 3 2193 9 2194 21 2195 2192 13 9 3 15 11 10 28 28 27 26 2201 2201 2196 108 108 108 401 402 401 402 401 403 402 401 401 402 403 402 403 399 403 398 402 226 189 4085 4086 4091 1315 4102 4095 4091 2554 26 25 2540 2545 2537 1101 2536 4089 2428 4093 3654 4092 2535 2532 2539 157 154 154 154 154 152 157 542 539 541 255 255 233 255 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; static const int page_cluster_max = 31; struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; /* block memcg migration while the folio moves between lru */ if (move_fn != lru_add && !folio_test_clear_lru(folio)) continue; folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ offsetof(struct cpu_fbatches, op) >= \ offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_move_tail); } void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) __releases(lruvec->lru_lock) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; if (!cost) { spin_unlock_irq(&lruvec->lru_lock); return; } for (;;) { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += cost; else lruvec->anon_cost += cost; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); lruvec = parent_lruvec(lruvec); if (!lruvec) break; spin_lock_irq(&lruvec->lru_lock); } } void lru_note_cost_refault(struct folio *folio) { struct lruvec *lruvec; lruvec = folio_lruvec_lock_irq(folio); lru_note_cost_unlock_irq(lruvec, folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_activate); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); if (folio_test_unevictable(folio)) return; /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); return; } do { if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio); return; } new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); } static bool lru_gen_clear_refs(struct folio *folio) { struct lru_gen_folio *lrugen; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); if (gen < 0) return true; set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS | BIT(PG_workingset), 0); lrugen = &folio_lruvec(folio)->lrugen; /* whether can do without shuffling under the LRU lock */ return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type])); } #else /* !CONFIG_LRU_GEN */ static void lru_gen_inc_refs(struct folio *folio) { } static bool lru_gen_clear_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (folio_test_dropbehind(folio)) return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_folio_seq() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); if (lru_gen_enabled()) lru_gen_clear_refs(folio); else folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add); fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); /* It helps everyone if we do our own local drain immediately. */ lru_add_drain(); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[PAGEVEC_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } static const struct ctl_table swap_sysctl_table[] = { { .procname = "page-cluster", .data = &page_cluster, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = (void *)&page_cluster_max, } }; /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = PAGES_TO_MB(totalram_pages()); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ register_sysctl_init("vm", swap_sysctl_table); } |
| 118 118 118 46 46 5 5 40 41 98 99 94 98 5 94 98 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * registration of device and proc * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/compat.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/initval.h> #include "seq_oss_device.h" #include "seq_oss_synth.h" /* * module option */ MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("OSS-compatible sequencer module"); MODULE_LICENSE("GPL"); /* Takashi says this is really only for sound-service-0-, but this is OK. */ MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_SEQUENCER); MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_MUSIC); /* * prototypes */ static int register_device(void); static void unregister_device(void); #ifdef CONFIG_SND_PROC_FS static int register_proc(void); static void unregister_proc(void); #else static inline int register_proc(void) { return 0; } static inline void unregister_proc(void) {} #endif static int odev_open(struct inode *inode, struct file *file); static int odev_release(struct inode *inode, struct file *file); static ssize_t odev_read(struct file *file, char __user *buf, size_t count, loff_t *offset); static ssize_t odev_write(struct file *file, const char __user *buf, size_t count, loff_t *offset); static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg); static __poll_t odev_poll(struct file *file, poll_table * wait); /* * module interface */ static struct snd_seq_driver seq_oss_synth_driver = { .driver = { .name = KBUILD_MODNAME, .probe = snd_seq_oss_synth_probe, .remove = snd_seq_oss_synth_remove, }, .id = SNDRV_SEQ_DEV_ID_OSS, .argsize = sizeof(struct snd_seq_oss_reg), }; static int __init alsa_seq_oss_init(void) { int rc; rc = register_device(); if (rc < 0) goto error; rc = register_proc(); if (rc < 0) { unregister_device(); goto error; } rc = snd_seq_oss_create_client(); if (rc < 0) { unregister_proc(); unregister_device(); goto error; } rc = snd_seq_driver_register(&seq_oss_synth_driver); if (rc < 0) { snd_seq_oss_delete_client(); unregister_proc(); unregister_device(); goto error; } /* success */ snd_seq_oss_synth_init(); error: return rc; } static void __exit alsa_seq_oss_exit(void) { snd_seq_driver_unregister(&seq_oss_synth_driver); snd_seq_oss_delete_client(); unregister_proc(); unregister_device(); } module_init(alsa_seq_oss_init) module_exit(alsa_seq_oss_exit) /* * ALSA minor device interface */ static DEFINE_MUTEX(register_mutex); static int odev_open(struct inode *inode, struct file *file) { int level; if (iminor(inode) == SNDRV_MINOR_OSS_MUSIC) level = SNDRV_SEQ_OSS_MODE_MUSIC; else level = SNDRV_SEQ_OSS_MODE_SYNTH; guard(mutex)(®ister_mutex); return snd_seq_oss_open(file, level); } static int odev_release(struct inode *inode, struct file *file) { struct seq_oss_devinfo *dp; dp = file->private_data; if (!dp) return 0; guard(mutex)(®ister_mutex); snd_seq_oss_release(dp); return 0; } static ssize_t odev_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; return snd_seq_oss_read(dp, buf, count); } static ssize_t odev_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; return snd_seq_oss_write(dp, buf, count, file); } static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct seq_oss_devinfo *dp; long rc; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; if (cmd != SNDCTL_SEQ_SYNC && mutex_lock_interruptible(®ister_mutex)) return -ERESTARTSYS; rc = snd_seq_oss_ioctl(dp, cmd, arg); if (cmd != SNDCTL_SEQ_SYNC) mutex_unlock(®ister_mutex); return rc; } #ifdef CONFIG_COMPAT static long odev_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return odev_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } #else #define odev_ioctl_compat NULL #endif static __poll_t odev_poll(struct file *file, poll_table * wait) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return EPOLLERR; return snd_seq_oss_poll(dp, file, wait); } /* * registration of sequencer minor device */ static const struct file_operations seq_oss_f_ops = { .owner = THIS_MODULE, .read = odev_read, .write = odev_write, .open = odev_open, .release = odev_release, .poll = odev_poll, .unlocked_ioctl = odev_ioctl, .compat_ioctl = odev_ioctl_compat, .llseek = noop_llseek, }; static int __init register_device(void) { int rc; guard(mutex)(®ister_mutex); rc = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0, &seq_oss_f_ops, NULL); if (rc < 0) { pr_err("ALSA: seq_oss: can't register device seq\n"); return rc; } rc = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_MUSIC, NULL, 0, &seq_oss_f_ops, NULL); if (rc < 0) { pr_err("ALSA: seq_oss: can't register device music\n"); snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0); return rc; } return 0; } static void unregister_device(void) { guard(mutex)(®ister_mutex); if (snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_MUSIC, NULL, 0) < 0) pr_err("ALSA: seq_oss: error unregister device music\n"); if (snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0) < 0) pr_err("ALSA: seq_oss: error unregister device seq\n"); } /* * /proc interface */ #ifdef CONFIG_SND_PROC_FS static struct snd_info_entry *info_entry; static void info_read(struct snd_info_entry *entry, struct snd_info_buffer *buf) { guard(mutex)(®ister_mutex); snd_iprintf(buf, "OSS sequencer emulation version %s\n", SNDRV_SEQ_OSS_VERSION_STR); snd_seq_oss_system_info_read(buf); snd_seq_oss_synth_info_read(buf); snd_seq_oss_midi_info_read(buf); } static int __init register_proc(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, SNDRV_SEQ_OSS_PROCNAME, snd_seq_root); if (entry == NULL) return -ENOMEM; entry->content = SNDRV_INFO_CONTENT_TEXT; entry->private_data = NULL; entry->c.text.read = info_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); return -ENOMEM; } info_entry = entry; return 0; } static void unregister_proc(void) { snd_info_free_entry(info_entry); info_entry = NULL; } #endif /* CONFIG_SND_PROC_FS */ |
| 201 5 116 128 204 2 48 3 119 189 62 1 4 119 113 141 12 141 3 130 130 35 118 44 118 72 110 6 121 47 137 139 48 2 19 145 137 10 23 19 2 13 71 2 29 29 7 6 112 2 6 117 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * * Copyright (C) 2011 Novell Inc. */ #include <linux/kernel.h> #include <linux/uuid.h> #include <linux/fs.h> #include <linux/fsverity.h> #include <linux/namei.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include "ovl_entry.h" #undef pr_fmt #define pr_fmt(fmt) "overlayfs: " fmt enum ovl_path_type { __OVL_PATH_UPPER = (1 << 0), __OVL_PATH_MERGE = (1 << 1), __OVL_PATH_ORIGIN = (1 << 2), }; #define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER) #define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE) #define OVL_TYPE_ORIGIN(type) ((type) & __OVL_PATH_ORIGIN) #define OVL_XATTR_NAMESPACE "overlay." #define OVL_XATTR_TRUSTED_PREFIX XATTR_TRUSTED_PREFIX OVL_XATTR_NAMESPACE #define OVL_XATTR_TRUSTED_PREFIX_LEN (sizeof(OVL_XATTR_TRUSTED_PREFIX) - 1) #define OVL_XATTR_USER_PREFIX XATTR_USER_PREFIX OVL_XATTR_NAMESPACE #define OVL_XATTR_USER_PREFIX_LEN (sizeof(OVL_XATTR_USER_PREFIX) - 1) #define OVL_XATTR_ESCAPE_PREFIX OVL_XATTR_NAMESPACE #define OVL_XATTR_ESCAPE_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_PREFIX) - 1) #define OVL_XATTR_ESCAPE_TRUSTED_PREFIX OVL_XATTR_TRUSTED_PREFIX OVL_XATTR_ESCAPE_PREFIX #define OVL_XATTR_ESCAPE_TRUSTED_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_TRUSTED_PREFIX) - 1) #define OVL_XATTR_ESCAPE_USER_PREFIX OVL_XATTR_USER_PREFIX OVL_XATTR_ESCAPE_PREFIX #define OVL_XATTR_ESCAPE_USER_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_USER_PREFIX) - 1) enum ovl_xattr { OVL_XATTR_OPAQUE, OVL_XATTR_REDIRECT, OVL_XATTR_ORIGIN, OVL_XATTR_IMPURE, OVL_XATTR_NLINK, OVL_XATTR_UPPER, OVL_XATTR_UUID, OVL_XATTR_METACOPY, OVL_XATTR_PROTATTR, OVL_XATTR_XWHITEOUT, }; enum ovl_inode_flag { /* Pure upper dir that may contain non pure upper entries */ OVL_IMPURE, /* Non-merge dir that may contain whiteout entries */ OVL_WHITEOUTS, OVL_INDEX, OVL_UPPERDATA, /* Inode number will remain constant over copy up. */ OVL_CONST_INO, OVL_HAS_DIGEST, OVL_VERIFIED_DIGEST, }; enum ovl_entry_flag { OVL_E_UPPER_ALIAS, OVL_E_OPAQUE, OVL_E_CONNECTED, /* Lower stack may contain xwhiteout entries */ OVL_E_XWHITEOUTS, }; enum { OVL_REDIRECT_OFF, /* "off" mode is never used. In effect */ OVL_REDIRECT_FOLLOW, /* ...it translates to either "follow" */ OVL_REDIRECT_NOFOLLOW, /* ...or "nofollow". */ OVL_REDIRECT_ON, }; enum { OVL_UUID_OFF, OVL_UUID_NULL, OVL_UUID_AUTO, OVL_UUID_ON, }; enum { OVL_XINO_OFF, OVL_XINO_AUTO, OVL_XINO_ON, }; enum { OVL_VERITY_OFF, OVL_VERITY_ON, OVL_VERITY_REQUIRE, }; /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, * where: * origin.fh - exported file handle of the lower file * origin.uuid - uuid of the lower filesystem */ #define OVL_FH_VERSION 0 #define OVL_FH_MAGIC 0xfb /* CPU byte order required for fid decoding: */ #define OVL_FH_FLAG_BIG_ENDIAN (1 << 0) #define OVL_FH_FLAG_ANY_ENDIAN (1 << 1) /* Is the real inode encoded in fid an upper inode? */ #define OVL_FH_FLAG_PATH_UPPER (1 << 2) #define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN | \ OVL_FH_FLAG_PATH_UPPER) #if defined(__LITTLE_ENDIAN) #define OVL_FH_FLAG_CPU_ENDIAN 0 #elif defined(__BIG_ENDIAN) #define OVL_FH_FLAG_CPU_ENDIAN OVL_FH_FLAG_BIG_ENDIAN #else #error Endianness not defined #endif /* The type used to be returned by overlay exportfs for misaligned fid */ #define OVL_FILEID_V0 0xfb /* The type returned by overlay exportfs for 32bit aligned fid */ #define OVL_FILEID_V1 0xf8 /* On-disk format for "origin" file handle */ struct ovl_fb { u8 version; /* 0 */ u8 magic; /* 0xfb */ u8 len; /* size of this header + size of fid */ u8 flags; /* OVL_FH_FLAG_* */ u8 type; /* fid_type of fid */ uuid_t uuid; /* uuid of filesystem */ u32 fid[]; /* file identifier should be 32bit aligned in-memory */ } __packed; /* In-memory and on-wire format for overlay file handle */ struct ovl_fh { u8 padding[3]; /* make sure fb.fid is 32bit aligned */ union { struct ovl_fb fb; DECLARE_FLEX_ARRAY(u8, buf); }; } __packed; #define OVL_FH_WIRE_OFFSET offsetof(struct ovl_fh, fb) #define OVL_FH_LEN(fh) (OVL_FH_WIRE_OFFSET + (fh)->fb.len) #define OVL_FH_FID_OFFSET (OVL_FH_WIRE_OFFSET + \ offsetof(struct ovl_fb, fid)) /* On-disk format for "metacopy" xattr (if non-zero size) */ struct ovl_metacopy { u8 version; /* 0 */ u8 len; /* size of this header + used digest bytes */ u8 flags; u8 digest_algo; /* FS_VERITY_HASH_ALG_* constant, 0 for no digest */ u8 digest[FS_VERITY_MAX_DIGEST_SIZE]; /* Only the used part on disk */ } __packed; #define OVL_METACOPY_MAX_SIZE (sizeof(struct ovl_metacopy)) #define OVL_METACOPY_MIN_SIZE (OVL_METACOPY_MAX_SIZE - FS_VERITY_MAX_DIGEST_SIZE) #define OVL_METACOPY_INIT { 0, OVL_METACOPY_MIN_SIZE } static inline int ovl_metadata_digest_size(const struct ovl_metacopy *metacopy) { if (metacopy->len < OVL_METACOPY_MIN_SIZE) return 0; return (int)metacopy->len - OVL_METACOPY_MIN_SIZE; } /* No atime modification on underlying */ #define OVL_OPEN_FLAGS (O_NOATIME) extern const char *const ovl_xattr_table[][2]; static inline const char *ovl_xattr(struct ovl_fs *ofs, enum ovl_xattr ox) { return ovl_xattr_table[ox][ofs->config.userxattr]; } /* * When changing ownership of an upper object map the intended ownership * according to the upper layer's idmapping. When an upper mount idmaps files * that are stored on-disk as owned by id 1001 to id 1000 this means stat on * this object will report it as being owned by id 1000 when calling stat via * the upper mount. * In order to change ownership of an object so stat reports id 1000 when * called on an idmapped upper mount the value written to disk - i.e., the * value stored in ia_*id - must 1001. The mount mapping helper will thus take * care to map 1000 to 1001. * The mnt idmapping helpers are nops if the upper layer isn't idmapped. */ static inline int ovl_do_notify_change(struct ovl_fs *ofs, struct dentry *upperdentry, struct iattr *attr) { return notify_change(ovl_upper_mnt_idmap(ofs), upperdentry, attr, NULL); } static inline int ovl_do_rmdir(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { int err = vfs_rmdir(ovl_upper_mnt_idmap(ofs), dir, dentry); pr_debug("rmdir(%pd2) = %i\n", dentry, err); return err; } static inline int ovl_do_unlink(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { int err = vfs_unlink(ovl_upper_mnt_idmap(ofs), dir, dentry, NULL); pr_debug("unlink(%pd2) = %i\n", dentry, err); return err; } static inline int ovl_do_link(struct ovl_fs *ofs, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { int err = vfs_link(old_dentry, ovl_upper_mnt_idmap(ofs), dir, new_dentry, NULL); pr_debug("link(%pd2, %pd2) = %i\n", old_dentry, new_dentry, err); return err; } static inline int ovl_do_create(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode) { int err = vfs_create(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, true); pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err); return err; } static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode) { struct dentry *ret; ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode); pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret)); return ret; } static inline int ovl_do_mknod(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev); pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err); return err; } static inline int ovl_do_symlink(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry, const char *oldname) { int err = vfs_symlink(ovl_upper_mnt_idmap(ofs), dir, dentry, oldname); pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err); return err; } static inline ssize_t ovl_do_getxattr(const struct path *path, const char *name, void *value, size_t size) { int err, len; WARN_ON(path->dentry->d_sb != path->mnt->mnt_sb); err = vfs_getxattr(mnt_idmap(path->mnt), path->dentry, name, value, size); len = (value && err > 0) ? err : 0; pr_debug("getxattr(%pd2, \"%s\", \"%*pE\", %zu, 0) = %i\n", path->dentry, name, min(len, 48), value, size, err); return err; } static inline ssize_t ovl_getxattr_upper(struct ovl_fs *ofs, struct dentry *upperdentry, enum ovl_xattr ox, void *value, size_t size) { struct path upperpath = { .dentry = upperdentry, .mnt = ovl_upper_mnt(ofs), }; return ovl_do_getxattr(&upperpath, ovl_xattr(ofs, ox), value, size); } static inline ssize_t ovl_path_getxattr(struct ovl_fs *ofs, const struct path *path, enum ovl_xattr ox, void *value, size_t size) { return ovl_do_getxattr(path, ovl_xattr(ofs, ox), value, size); } static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int err = vfs_setxattr(ovl_upper_mnt_idmap(ofs), dentry, name, value, size, flags); pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, %d) = %i\n", dentry, name, min((int)size, 48), value, size, flags, err); return err; } static inline int ovl_setxattr(struct ovl_fs *ofs, struct dentry *dentry, enum ovl_xattr ox, const void *value, size_t size) { return ovl_do_setxattr(ofs, dentry, ovl_xattr(ofs, ox), value, size, 0); } static inline int ovl_do_removexattr(struct ovl_fs *ofs, struct dentry *dentry, const char *name) { int err = vfs_removexattr(ovl_upper_mnt_idmap(ofs), dentry, name); pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err); return err; } static inline int ovl_removexattr(struct ovl_fs *ofs, struct dentry *dentry, enum ovl_xattr ox) { return ovl_do_removexattr(ofs, dentry, ovl_xattr(ofs, ox)); } static inline int ovl_do_set_acl(struct ovl_fs *ofs, struct dentry *dentry, const char *acl_name, struct posix_acl *acl) { return vfs_set_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name, acl); } static inline int ovl_do_remove_acl(struct ovl_fs *ofs, struct dentry *dentry, const char *acl_name) { return vfs_remove_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name); } static inline int ovl_do_rename(struct ovl_fs *ofs, struct dentry *olddir, struct dentry *olddentry, struct dentry *newdir, struct dentry *newdentry, unsigned int flags) { int err; struct renamedata rd = { .mnt_idmap = ovl_upper_mnt_idmap(ofs), .old_parent = olddir, .old_dentry = olddentry, .new_parent = newdir, .new_dentry = newdentry, .flags = flags, }; pr_debug("rename(%pd2, %pd2, 0x%x)\n", olddentry, newdentry, flags); err = vfs_rename(&rd); if (err) { pr_debug("...rename(%pd2, %pd2, ...) = %i\n", olddentry, newdentry, err); } return err; } static inline int ovl_do_whiteout(struct ovl_fs *ofs, struct inode *dir, struct dentry *dentry) { int err = vfs_whiteout(ovl_upper_mnt_idmap(ofs), dir, dentry); pr_debug("whiteout(%pd2) = %i\n", dentry, err); return err; } static inline struct file *ovl_do_tmpfile(struct ovl_fs *ofs, struct dentry *dentry, umode_t mode) { struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = dentry }; struct file *file = kernel_tmpfile_open(ovl_upper_mnt_idmap(ofs), &path, mode, O_LARGEFILE | O_WRONLY, current_cred()); int err = PTR_ERR_OR_ZERO(file); pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err); return file; } static inline struct dentry *ovl_lookup_upper(struct ovl_fs *ofs, const char *name, struct dentry *base, int len) { return lookup_one(ovl_upper_mnt_idmap(ofs), &QSTR_LEN(name, len), base); } static inline struct dentry *ovl_lookup_upper_unlocked(struct ovl_fs *ofs, const char *name, struct dentry *base, int len) { return lookup_one_unlocked(ovl_upper_mnt_idmap(ofs), &QSTR_LEN(name, len), base); } static inline bool ovl_open_flags_need_copy_up(int flags) { if (!flags) return false; return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)); } /* util.c */ int ovl_parent_lock(struct dentry *parent, struct dentry *child); static inline void ovl_parent_unlock(struct dentry *parent) { inode_unlock(parent->d_inode); } int ovl_get_write_access(struct dentry *dentry); void ovl_put_write_access(struct dentry *dentry); void ovl_start_write(struct dentry *dentry); void ovl_end_write(struct dentry *dentry); int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); void ovl_revert_creds(const struct cred *old_cred); static inline const struct cred *ovl_creds(struct super_block *sb) { return OVL_FS(sb)->creator_cred; } int ovl_can_decode_fh(struct super_block *sb); struct dentry *ovl_indexdir(struct super_block *sb); bool ovl_index_all(struct super_block *sb); bool ovl_verify_lower(struct super_block *sb); struct ovl_path *ovl_stack_alloc(unsigned int n); void ovl_stack_cpy(struct ovl_path *dst, struct ovl_path *src, unsigned int n); void ovl_stack_put(struct ovl_path *stack, unsigned int n); void ovl_stack_free(struct ovl_path *stack, unsigned int n); struct ovl_entry *ovl_alloc_entry(unsigned int numlower); void ovl_free_entry(struct ovl_entry *oe); bool ovl_dentry_remote(struct dentry *dentry); void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *realdentry); void ovl_dentry_init_reval(struct dentry *dentry, struct dentry *upperdentry, struct ovl_entry *oe); void ovl_dentry_init_flags(struct dentry *dentry, struct dentry *upperdentry, struct ovl_entry *oe, unsigned int mask); bool ovl_dentry_weird(struct dentry *dentry); static inline bool ovl_dentry_casefolded(struct dentry *dentry) { return sb_has_encoding(dentry->d_sb) && IS_CASEFOLDED(d_inode(dentry)); } enum ovl_path_type ovl_path_type(struct dentry *dentry); void ovl_path_upper(struct dentry *dentry, struct path *path); void ovl_path_lower(struct dentry *dentry, struct path *path); void ovl_path_lowerdata(struct dentry *dentry, struct path *path); struct inode *ovl_i_path_real(struct inode *inode, struct path *path); enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); enum ovl_path_type ovl_path_realdata(struct dentry *dentry, struct path *path); struct dentry *ovl_dentry_upper(struct dentry *dentry); struct dentry *ovl_dentry_lower(struct dentry *dentry); struct dentry *ovl_dentry_lowerdata(struct dentry *dentry); int ovl_dentry_set_lowerdata(struct dentry *dentry, struct ovl_path *datapath); const struct ovl_layer *ovl_i_layer_lower(struct inode *inode); const struct ovl_layer *ovl_layer_lower(struct dentry *dentry); struct dentry *ovl_dentry_real(struct dentry *dentry); struct dentry *ovl_i_dentry_upper(struct inode *inode); struct inode *ovl_inode_upper(struct inode *inode); struct inode *ovl_inode_lower(struct inode *inode); struct inode *ovl_inode_lowerdata(struct inode *inode); struct inode *ovl_inode_real(struct inode *inode); struct inode *ovl_inode_realdata(struct inode *inode); const char *ovl_lowerdata_redirect(struct inode *inode); struct ovl_dir_cache *ovl_dir_cache(struct inode *inode); void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache); void ovl_dentry_set_flag(unsigned long flag, struct dentry *dentry); void ovl_dentry_clear_flag(unsigned long flag, struct dentry *dentry); bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry); bool ovl_dentry_is_opaque(struct dentry *dentry); bool ovl_dentry_is_whiteout(struct dentry *dentry); void ovl_dentry_set_opaque(struct dentry *dentry); bool ovl_dentry_has_xwhiteouts(struct dentry *dentry); void ovl_dentry_set_xwhiteouts(struct dentry *dentry); void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs, const struct ovl_layer *layer); bool ovl_dentry_has_upper_alias(struct dentry *dentry); void ovl_dentry_set_upper_alias(struct dentry *dentry); bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags); bool ovl_dentry_needs_data_copy_up_locked(struct dentry *dentry, int flags); bool ovl_has_upperdata(struct inode *inode); void ovl_set_upperdata(struct inode *inode); const char *ovl_dentry_get_redirect(struct dentry *dentry); void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect); void ovl_inode_update(struct inode *inode, struct dentry *upperdentry); void ovl_dir_modified(struct dentry *dentry, bool impurity); u64 ovl_inode_version_get(struct inode *inode); bool ovl_is_whiteout(struct dentry *dentry); bool ovl_path_is_whiteout(struct ovl_fs *ofs, const struct path *path); struct file *ovl_path_open(const struct path *path, int flags); int ovl_copy_up_start(struct dentry *dentry, int flags); void ovl_copy_up_end(struct dentry *dentry); bool ovl_already_copied_up(struct dentry *dentry, int flags); char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path, enum ovl_xattr ox); bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path); bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path); bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs, const struct path *upperpath); static inline bool ovl_upper_is_whiteout(struct ovl_fs *ofs, struct dentry *upperdentry) { struct path upperpath = { .dentry = upperdentry, .mnt = ovl_upper_mnt(ofs), }; return ovl_path_is_whiteout(ofs, &upperpath); } static inline bool ovl_check_origin_xattr(struct ovl_fs *ofs, struct dentry *upperdentry) { struct path upperpath = { .dentry = upperdentry, .mnt = ovl_upper_mnt(ofs), }; return ovl_path_check_origin_xattr(ofs, &upperpath); } int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry, enum ovl_xattr ox, const void *value, size_t size, int xerr); int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry); bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); bool ovl_is_inuse(struct dentry *dentry); bool ovl_need_index(struct dentry *dentry); int ovl_nlink_start(struct dentry *dentry); void ovl_nlink_end(struct dentry *dentry); int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *work, struct dentry *upperdir, struct dentry *upper); int ovl_check_metacopy_xattr(struct ovl_fs *ofs, const struct path *path, struct ovl_metacopy *data); int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d, struct ovl_metacopy *metacopy); bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding); int ovl_ensure_verity_loaded(const struct path *path); int ovl_validate_verity(struct ovl_fs *ofs, const struct path *metapath, const struct path *datapath); int ovl_get_verity_digest(struct ovl_fs *ofs, const struct path *src, struct ovl_metacopy *metacopy); int ovl_sync_status(struct ovl_fs *ofs); static inline void ovl_set_flag(unsigned long flag, struct inode *inode) { set_bit(flag, &OVL_I(inode)->flags); } static inline void ovl_clear_flag(unsigned long flag, struct inode *inode) { clear_bit(flag, &OVL_I(inode)->flags); } static inline bool ovl_test_flag(unsigned long flag, struct inode *inode) { return test_bit(flag, &OVL_I(inode)->flags); } static inline bool ovl_is_impuredir(struct super_block *sb, struct dentry *upperdentry) { struct ovl_fs *ofs = OVL_FS(sb); struct path upperpath = { .dentry = upperdentry, .mnt = ovl_upper_mnt(ofs), }; return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y'; } static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs, const struct path *path) { return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE); } static inline bool ovl_redirect_follow(struct ovl_fs *ofs) { return ofs->config.redirect_mode != OVL_REDIRECT_NOFOLLOW; } static inline bool ovl_redirect_dir(struct ovl_fs *ofs) { return ofs->config.redirect_mode == OVL_REDIRECT_ON; } static inline bool ovl_origin_uuid(struct ovl_fs *ofs) { return ofs->config.uuid != OVL_UUID_OFF; } static inline bool ovl_has_fsid(struct ovl_fs *ofs) { return ofs->config.uuid == OVL_UUID_ON || ofs->config.uuid == OVL_UUID_AUTO; } /* * With xino=auto, we do best effort to keep all inodes on same st_dev and * d_ino consistent with st_ino. * With xino=on, we do the same effort but we warn if we failed. */ static inline bool ovl_xino_warn(struct ovl_fs *ofs) { return ofs->config.xino == OVL_XINO_ON; } /* * To avoid regressions in existing setups with overlay lower offline changes, * we allow lower changes only if none of the new features are used. */ static inline bool ovl_allow_offline_changes(struct ovl_fs *ofs) { return (!ofs->config.index && !ofs->config.metacopy && !ovl_redirect_dir(ofs) && !ovl_xino_warn(ofs)); } /* All layers on same fs? */ static inline bool ovl_same_fs(struct ovl_fs *ofs) { return ofs->xino_mode == 0; } /* All overlay inodes have same st_dev? */ static inline bool ovl_same_dev(struct ovl_fs *ofs) { return ofs->xino_mode >= 0; } static inline unsigned int ovl_xino_bits(struct ovl_fs *ofs) { return ovl_same_dev(ofs) ? ofs->xino_mode : 0; } static inline void ovl_inode_lock(struct inode *inode) { mutex_lock(&OVL_I(inode)->lock); } static inline int ovl_inode_lock_interruptible(struct inode *inode) { return mutex_lock_interruptible(&OVL_I(inode)->lock); } static inline void ovl_inode_unlock(struct inode *inode) { mutex_unlock(&OVL_I(inode)->lock); } /* namei.c */ int ovl_check_fb_len(struct ovl_fb *fb, int fb_len); static inline int ovl_check_fh_len(struct ovl_fh *fh, int fh_len) { if (fh_len < sizeof(struct ovl_fh)) return -EINVAL; return ovl_check_fb_len(&fh->fb, fh_len - OVL_FH_WIRE_OFFSET); } struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh, struct vfsmount *mnt, bool connected); int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, struct dentry *upperdentry, struct ovl_path **stackp); int ovl_verify_set_fh(struct ovl_fs *ofs, struct dentry *dentry, enum ovl_xattr ox, const struct ovl_fh *fh, bool is_upper, bool set); int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, enum ovl_xattr ox, struct dentry *real, bool is_upper, bool set); struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index, bool connected); int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index); int ovl_get_index_name_fh(const struct ovl_fh *fh, struct qstr *name); int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct qstr *name); struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh); struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, struct dentry *origin, bool verify); int ovl_path_next(int idx, struct dentry *dentry, struct path *path, const struct ovl_layer **layer); int ovl_verify_lowerdata(struct dentry *dentry); struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); bool ovl_lower_positive(struct dentry *dentry); static inline int ovl_verify_origin_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh, bool set) { return ovl_verify_set_fh(ofs, upper, OVL_XATTR_ORIGIN, fh, false, set); } static inline int ovl_verify_origin(struct ovl_fs *ofs, struct dentry *upper, struct dentry *origin, bool set) { return ovl_verify_origin_xattr(ofs, upper, OVL_XATTR_ORIGIN, origin, false, set); } static inline int ovl_verify_upper(struct ovl_fs *ofs, struct dentry *index, struct dentry *upper, bool set) { return ovl_verify_origin_xattr(ofs, index, OVL_XATTR_UPPER, upper, true, set); } /* readdir.c */ extern const struct file_operations ovl_dir_operations; struct file *ovl_dir_real_file(const struct file *file, bool want_upper); int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list); void ovl_cleanup_whiteouts(struct ovl_fs *ofs, struct dentry *upper, struct list_head *list); void ovl_cache_free(struct list_head *list); void ovl_dir_cache_free(struct inode *inode); int ovl_check_d_type_supported(const struct path *realpath); int ovl_workdir_cleanup(struct ovl_fs *ofs, struct dentry *parent, struct vfsmount *mnt, struct dentry *dentry, int level); int ovl_indexdir_cleanup(struct ovl_fs *ofs); /* * Can we iterate real dir directly? * * Non-merge dir may contain whiteouts from a time it was a merge upper, before * lower dir was removed under it and possibly before it was rotated from upper * to lower layer. */ static inline bool ovl_dir_is_real(struct inode *dir) { return !ovl_test_flag(OVL_WHITEOUTS, dir); } /* inode.c */ int ovl_set_nlink_upper(struct dentry *dentry); int ovl_set_nlink_lower(struct dentry *dentry); unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry, struct dentry *upperdentry, unsigned int fallback); int ovl_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap, struct inode *inode, int type, bool rcu, bool noperm); static inline struct posix_acl *ovl_get_inode_acl(struct inode *inode, int type, bool rcu) { return do_ovl_get_acl(&nop_mnt_idmap, inode, type, rcu, true); } static inline struct posix_acl *ovl_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type) { return do_ovl_get_acl(idmap, d_inode(dentry), type, false, false); } int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); struct posix_acl *ovl_get_acl_path(const struct path *path, const char *acl_name, bool noperm); #else #define ovl_get_inode_acl NULL #define ovl_get_acl NULL #define ovl_set_acl NULL static inline struct posix_acl *ovl_get_acl_path(const struct path *path, const char *acl_name, bool noperm) { return NULL; } #endif int ovl_update_time(struct inode *inode, int flags); bool ovl_is_private_xattr(struct super_block *sb, const char *name); struct ovl_inode_params { struct inode *newinode; struct dentry *upperdentry; struct ovl_entry *oe; bool index; char *redirect; char *lowerdata_redirect; }; void ovl_inode_init(struct inode *inode, struct ovl_inode_params *oip, unsigned long ino, int fsid); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, bool is_upper); bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir); struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir); struct inode *ovl_get_inode(struct super_block *sb, struct ovl_inode_params *oip); void ovl_copyattr(struct inode *to); /* vfs fileattr flags read from overlay.protattr xattr to ovl inode */ #define OVL_PROT_I_FLAGS_MASK (S_APPEND | S_IMMUTABLE) /* vfs fileattr flags copied from real to ovl inode */ #define OVL_FATTR_I_FLAGS_MASK (OVL_PROT_I_FLAGS_MASK | S_SYNC | S_NOATIME) /* vfs inode flags copied from real to ovl inode */ #define OVL_COPY_I_FLAGS_MASK (OVL_FATTR_I_FLAGS_MASK | S_CASEFOLD) /* * fileattr flags copied from lower to upper inode on copy up. * We cannot copy up immutable/append-only flags, because that would prevent * linking temp inode to upper dir, so we store them in xattr instead. */ #define OVL_COPY_FS_FLAGS_MASK (FS_SYNC_FL | FS_NOATIME_FL) #define OVL_COPY_FSX_FLAGS_MASK (FS_XFLAG_SYNC | FS_XFLAG_NOATIME) #define OVL_PROT_FS_FLAGS_MASK (FS_APPEND_FL | FS_IMMUTABLE_FL) #define OVL_PROT_FSX_FLAGS_MASK (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE) void ovl_check_protattr(struct inode *inode, struct dentry *upper); int ovl_set_protattr(struct inode *inode, struct dentry *upper, struct file_kattr *fa); static inline void ovl_copyflags(struct inode *from, struct inode *to) { unsigned int mask = OVL_COPY_I_FLAGS_MASK; inode_set_flags(to, from->i_flags & mask, mask); } /* dir.c */ extern const struct inode_operations ovl_dir_inode_operations; int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir, struct dentry *dentry); struct ovl_cattr { dev_t rdev; umode_t mode; const char *link; struct dentry *hardlink; }; #define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) }) struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent, struct dentry *newdentry, struct ovl_cattr *attr); int ovl_cleanup(struct ovl_fs *ofs, struct dentry *workdir, struct dentry *dentry); struct dentry *ovl_lookup_temp(struct ovl_fs *ofs, struct dentry *workdir); struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, struct ovl_cattr *attr); /* file.c */ extern const struct file_operations ovl_file_operations; int ovl_real_fileattr_get(const struct path *realpath, struct file_kattr *fa); int ovl_real_fileattr_set(const struct path *realpath, struct file_kattr *fa); int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa); int ovl_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa); struct ovl_file; struct ovl_file *ovl_file_alloc(struct file *realfile); void ovl_file_free(struct ovl_file *of); /* copy_up.c */ int ovl_copy_up(struct dentry *dentry); int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, struct dentry *upper); /* export.c */ extern const struct export_operations ovl_export_operations; extern const struct export_operations ovl_export_fid_operations; /* super.c */ int ovl_fill_super(struct super_block *sb, struct fs_context *fc); /* Will this overlay be forced to mount/remount ro? */ static inline bool ovl_force_readonly(struct ovl_fs *ofs) { return (!ovl_upper_mnt(ofs) || !ofs->workdir); } /* xattr.c */ const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs); int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); |
| 6 6 6 6 17 12 11 9 12 11 6 6 11 12 8 12 19 13 19 9 8 6 6 4 8 8 8 8 8 1 1 1 12 4 7 6 4 3 6 6 2 1 2 7 7 7 7 7 6 5 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/user.h> #include <linux/regset.h> #include <linux/syscalls.h> #include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/desc.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/proto.h> #include <asm/gsseg.h> #include "tls.h" /* * sys_alloc_thread_area: get a yet unused TLS descriptor index. */ static int get_free_idx(void) { struct thread_struct *t = ¤t->thread; int idx; for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++) if (desc_empty(&t->tls_array[idx])) return idx + GDT_ENTRY_TLS_MIN; return -ESRCH; } static bool tls_desc_okay(const struct user_desc *info) { /* * For historical reasons (i.e. no one ever documented how any * of the segmentation APIs work), user programs can and do * assume that a struct user_desc that's all zeros except for * entry_number means "no segment at all". This never actually * worked. In fact, up to Linux 3.19, a struct user_desc like * this would create a 16-bit read-write segment with base and * limit both equal to zero. * * That was close enough to "no segment at all" until we * hardened this function to disallow 16-bit TLS segments. Fix * it up by interpreting these zeroed segments the way that they * were almost certainly intended to be interpreted. * * The correct way to ask for "no segment at all" is to specify * a user_desc that satisfies LDT_empty. To keep everything * working, we accept both. * * Note that there's a similar kludge in modify_ldt -- look at * the distinction between modes 1 and 0x11. */ if (LDT_empty(info) || LDT_zero(info)) return true; /* * espfix is required for 16-bit data segments, but espfix * only works for LDT segments. */ if (!info->seg_32bit) return false; /* Only allow data segments in the TLS array. */ if (info->contents > 1) return false; /* * Non-present segments with DPL 3 present an interesting attack * surface. The kernel should handle such segments correctly, * but TLS is very difficult to protect in a sandbox, so prevent * such segments from being created. * * If userspace needs to remove a TLS entry, it can still delete * it outright. */ if (info->seg_not_present) return false; return true; } static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { struct thread_struct *t = &p->thread; struct desc_struct *desc = &t->tls_array[idx - GDT_ENTRY_TLS_MIN]; int cpu; /* * We must not get preempted while modifying the TLS. */ cpu = get_cpu(); while (n-- > 0) { if (LDT_empty(info) || LDT_zero(info)) memset(desc, 0, sizeof(*desc)); else fill_ldt(desc, info); ++info; ++desc; } if (t == ¤t->thread) load_TLS(t, cpu); put_cpu(); } /* * Set a given TLS descriptor: */ int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *u_info, int can_allocate) { struct user_desc info; unsigned short __maybe_unused sel, modified_sel; if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; if (!tls_desc_okay(&info)) return -EINVAL; if (idx == -1) idx = info.entry_number; /* * index -1 means the kernel should try to find and * allocate an empty descriptor: */ if (idx == -1 && can_allocate) { idx = get_free_idx(); if (idx < 0) return idx; if (put_user(idx, &u_info->entry_number)) return -EFAULT; } if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; set_tls_desc(p, idx, &info, 1); /* * If DS, ES, FS, or GS points to the modified segment, forcibly * refresh it. Only needed on x86_64 because x86_32 reloads them * on return to user mode. */ modified_sel = (idx << 3) | 3; if (p == current) { #ifdef CONFIG_X86_64 savesegment(ds, sel); if (sel == modified_sel) loadsegment(ds, sel); savesegment(es, sel); if (sel == modified_sel) loadsegment(es, sel); savesegment(fs, sel); if (sel == modified_sel) loadsegment(fs, sel); #endif savesegment(gs, sel); if (sel == modified_sel) load_gs_index(sel); } else { #ifdef CONFIG_X86_64 if (p->thread.fsindex == modified_sel) p->thread.fsbase = info.base_addr; if (p->thread.gsindex == modified_sel) p->thread.gsbase = info.base_addr; #endif } return 0; } SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, u_info) { return do_set_thread_area(current, -1, u_info, 1); } /* * Get the current Thread-Local Storage area: */ static void fill_user_desc(struct user_desc *info, int idx, const struct desc_struct *desc) { memset(info, 0, sizeof(*info)); info->entry_number = idx; info->base_addr = get_desc_base(desc); info->limit = get_desc_limit(desc); info->seg_32bit = desc->d; info->contents = desc->type >> 2; info->read_exec_only = !(desc->type & 2); info->limit_in_pages = desc->g; info->seg_not_present = !desc->p; info->useable = desc->avl; #ifdef CONFIG_X86_64 info->lm = desc->l; #endif } int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *u_info) { struct user_desc info; int index; if (idx == -1 && get_user(idx, &u_info->entry_number)) return -EFAULT; if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; index = idx - GDT_ENTRY_TLS_MIN; index = array_index_nospec(index, GDT_ENTRY_TLS_MAX - GDT_ENTRY_TLS_MIN + 1); fill_user_desc(&info, idx, &p->thread.tls_array[index]); if (copy_to_user(u_info, &info, sizeof(info))) return -EFAULT; return 0; } SYSCALL_DEFINE1(get_thread_area, struct user_desc __user *, u_info) { return do_get_thread_area(current, -1, u_info); } int regset_tls_active(struct task_struct *target, const struct user_regset *regset) { struct thread_struct *t = &target->thread; int n = GDT_ENTRY_TLS_ENTRIES; while (n > 0 && desc_empty(&t->tls_array[n - 1])) --n; return n; } int regset_tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { const struct desc_struct *tls; struct user_desc v; int pos; for (pos = 0, tls = target->thread.tls_array; to.left; pos++, tls++) { fill_user_desc(&v, GDT_ENTRY_TLS_MIN + pos, tls); membuf_write(&to, &v, sizeof(v)); } return 0; } int regset_tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || (count % sizeof(struct user_desc)) != 0) return -EINVAL; if (kbuf) info = kbuf; else if (__copy_from_user(infobuf, ubuf, count)) return -EFAULT; else info = infobuf; for (i = 0; i < count / sizeof(struct user_desc); i++) if (!tls_desc_okay(info + i)) return -EINVAL; set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); return 0; } |
| 202 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 | /* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* Copyright (c) 2002-2007 Volkswagen Group Electronic Research * Copyright (c) 2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> * * 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 name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * 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. * */ #ifndef CAN_ML_H #define CAN_ML_H #include <linux/can.h> #include <linux/list.h> #include <linux/netdevice.h> #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; struct can_dev_rcv_lists { struct hlist_head rx[RX_MAX]; struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; int entries; }; struct can_ml_priv { struct can_dev_rcv_lists dev_rcv_lists; #ifdef CAN_J1939 struct j1939_priv *j1939_priv; #endif }; static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) { return netdev_get_ml_priv(dev, ML_PRIV_CAN); } static inline void can_set_ml_priv(struct net_device *dev, struct can_ml_priv *ml_priv) { netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); } #endif /* CAN_ML_H */ |
| 24 16 16 24 24 24 24 24 15 15 15 15 15 1 1 1 1 5 4 3 2 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge per vlan tunnel port dst_metadata netlink control interface * * Authors: * Roopa Prabhu <roopa@cumulusnetworks.com> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include <net/dst_metadata.h> #include "br_private.h" #include "br_private_tunnel.h" static size_t __get_vlan_tinfo_size(void) { return nla_total_size(0) + /* nest IFLA_BRIDGE_VLAN_TUNNEL_INFO */ nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_VLAN_TUNNEL_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BRIDGE_VLAN_TUNNEL_VID */ nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_VLAN_TUNNEL_FLAGS */ } bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *v_last) { __be32 tunid_curr = tunnel_id_to_key32(v_curr->tinfo.tunnel_id); __be32 tunid_last = tunnel_id_to_key32(v_last->tinfo.tunnel_id); return (be32_to_cpu(tunid_curr) - be32_to_cpu(tunid_last)) == 1; } static int __get_num_vlan_tunnel_infos(struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v, *vtbegin = NULL, *vtend = NULL; int num_tinfos = 0; /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v) || !v->tinfo.tunnel_id) continue; if (!vtbegin) { goto initvars; } else if ((v->vid - vtend->vid) == 1 && vlan_tunid_inrange(v, vtend)) { vtend = v; continue; } else { if ((vtend->vid - vtbegin->vid) > 0) num_tinfos += 2; else num_tinfos += 1; } initvars: vtbegin = v; vtend = v; } if (vtbegin && vtend) { if ((vtend->vid - vtbegin->vid) > 0) num_tinfos += 2; else num_tinfos += 1; } return num_tinfos; } int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg) { int num_tinfos; if (!vg) return 0; rcu_read_lock(); num_tinfos = __get_num_vlan_tunnel_infos(vg); rcu_read_unlock(); return num_tinfos * __get_vlan_tinfo_size(); } static int br_fill_vlan_tinfo(struct sk_buff *skb, u16 vid, __be64 tunnel_id, u16 flags) { __be32 tid = tunnel_id_to_key32(tunnel_id); struct nlattr *tmap; tmap = nla_nest_start_noflag(skb, IFLA_BRIDGE_VLAN_TUNNEL_INFO); if (!tmap) return -EMSGSIZE; if (nla_put_u32(skb, IFLA_BRIDGE_VLAN_TUNNEL_ID, be32_to_cpu(tid))) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BRIDGE_VLAN_TUNNEL_VID, vid)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BRIDGE_VLAN_TUNNEL_FLAGS, flags)) goto nla_put_failure; nla_nest_end(skb, tmap); return 0; nla_put_failure: nla_nest_cancel(skb, tmap); return -EMSGSIZE; } static int br_fill_vlan_tinfo_range(struct sk_buff *skb, struct net_bridge_vlan *vtbegin, struct net_bridge_vlan *vtend) { int err; if (vtend && (vtend->vid - vtbegin->vid) > 0) { /* add range to skb */ err = br_fill_vlan_tinfo(skb, vtbegin->vid, vtbegin->tinfo.tunnel_id, BRIDGE_VLAN_INFO_RANGE_BEGIN); if (err) return err; err = br_fill_vlan_tinfo(skb, vtend->vid, vtend->tinfo.tunnel_id, BRIDGE_VLAN_INFO_RANGE_END); if (err) return err; } else { err = br_fill_vlan_tinfo(skb, vtbegin->vid, vtbegin->tinfo.tunnel_id, 0); if (err) return err; } return 0; } int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vtbegin = NULL; struct net_bridge_vlan *vtend = NULL; struct net_bridge_vlan *v; int err; /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (!v->tinfo.tunnel_dst) continue; if (!vtbegin) { goto initvars; } else if ((v->vid - vtend->vid) == 1 && vlan_tunid_inrange(v, vtend)) { vtend = v; continue; } else { err = br_fill_vlan_tinfo_range(skb, vtbegin, vtend); if (err) return err; } initvars: vtbegin = v; vtend = v; } if (vtbegin) { err = br_fill_vlan_tinfo_range(skb, vtbegin, vtend); if (err) return err; } return 0; } static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1] = { [IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC] = { .strict_start_type = IFLA_BRIDGE_VLAN_TUNNEL_FLAGS + 1 }, [IFLA_BRIDGE_VLAN_TUNNEL_ID] = { .type = NLA_U32 }, [IFLA_BRIDGE_VLAN_TUNNEL_VID] = { .type = NLA_U16 }, [IFLA_BRIDGE_VLAN_TUNNEL_FLAGS] = { .type = NLA_U16 }, }; int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, u16 vid, u32 tun_id, bool *changed) { int err = 0; if (!p) return -EINVAL; switch (cmd) { case RTM_SETLINK: err = nbp_vlan_tunnel_info_add(p, vid, tun_id); if (!err) *changed = true; break; case RTM_DELLINK: if (!nbp_vlan_tunnel_info_delete(p, vid)) *changed = true; break; } return err; } int br_parse_vlan_tunnel_info(struct nlattr *attr, struct vtunnel_info *tinfo) { struct nlattr *tb[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1]; u32 tun_id; u16 vid, flags = 0; int err; memset(tinfo, 0, sizeof(*tinfo)); err = nla_parse_nested_deprecated(tb, IFLA_BRIDGE_VLAN_TUNNEL_MAX, attr, vlan_tunnel_policy, NULL); if (err < 0) return err; if (!tb[IFLA_BRIDGE_VLAN_TUNNEL_ID] || !tb[IFLA_BRIDGE_VLAN_TUNNEL_VID]) return -EINVAL; tun_id = nla_get_u32(tb[IFLA_BRIDGE_VLAN_TUNNEL_ID]); vid = nla_get_u16(tb[IFLA_BRIDGE_VLAN_TUNNEL_VID]); if (vid >= VLAN_VID_MASK) return -ERANGE; if (tb[IFLA_BRIDGE_VLAN_TUNNEL_FLAGS]) flags = nla_get_u16(tb[IFLA_BRIDGE_VLAN_TUNNEL_FLAGS]); tinfo->tunid = tun_id; tinfo->vid = vid; tinfo->flags = flags; return 0; } /* send a notification if v_curr can't enter the range and start a new one */ static void __vlan_tunnel_handle_range(const struct net_bridge_port *p, struct net_bridge_vlan **v_start, struct net_bridge_vlan **v_end, int v_curr, bool curr_change) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; vg = nbp_vlan_group(p); if (!vg) return; v = br_vlan_find(vg, v_curr); if (!*v_start) goto out_init; if (v && curr_change && br_vlan_can_enter_range(v, *v_end)) { *v_end = v; return; } br_vlan_notify(p->br, p, (*v_start)->vid, (*v_end)->vid, RTM_NEWVLAN); out_init: /* we start a range only if there are any changes to notify about */ *v_start = curr_change ? v : NULL; *v_end = *v_start; } int br_process_vlan_tunnel_info(const struct net_bridge *br, const struct net_bridge_port *p, int cmd, struct vtunnel_info *tinfo_curr, struct vtunnel_info *tinfo_last, bool *changed) { int err; if (tinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (tinfo_last->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) return -EINVAL; memcpy(tinfo_last, tinfo_curr, sizeof(struct vtunnel_info)); } else if (tinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END) { struct net_bridge_vlan *v_start = NULL, *v_end = NULL; int t, v; if (!(tinfo_last->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN)) return -EINVAL; if ((tinfo_curr->vid - tinfo_last->vid) != (tinfo_curr->tunid - tinfo_last->tunid)) return -EINVAL; t = tinfo_last->tunid; for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) { bool curr_change = false; err = br_vlan_tunnel_info(p, cmd, v, t, &curr_change); if (err) break; t++; if (curr_change) *changed = curr_change; __vlan_tunnel_handle_range(p, &v_start, &v_end, v, curr_change); } if (v_start && v_end) br_vlan_notify(br, p, v_start->vid, v_end->vid, RTM_NEWVLAN); if (err) return err; memset(tinfo_last, 0, sizeof(struct vtunnel_info)); memset(tinfo_curr, 0, sizeof(struct vtunnel_info)); } else { if (tinfo_last->flags) return -EINVAL; err = br_vlan_tunnel_info(p, cmd, tinfo_curr->vid, tinfo_curr->tunid, changed); if (err) return err; br_vlan_notify(br, p, tinfo_curr->vid, 0, RTM_NEWVLAN); memset(tinfo_last, 0, sizeof(struct vtunnel_info)); memset(tinfo_curr, 0, sizeof(struct vtunnel_info)); } return 0; } |
| 4 2 2 2 2 2 2 2 2 2 2 2 2 5 5 5 3 3 3 3 3 3 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 | /* gf128mul.c - GF(2^128) multiplication functions * * Copyright (c) 2003, Dr Brian Gladman, Worcester, UK. * Copyright (c) 2006, Rik Snel <rsnel@cube.dyndns.org> * * Based on Dr Brian Gladman's (GPL'd) work published at * http://gladman.plushost.co.uk/oldsite/cryptography_technology/index.php * See the original copyright notice below. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. */ /* --------------------------------------------------------------------------- Copyright (c) 2003, Dr Brian Gladman, Worcester, UK. All rights reserved. LICENSE TERMS The free distribution and use of this software in both source and binary form is allowed (with or without changes) provided that: 1. distributions of this source code include the above copyright notice, this list of conditions and the following disclaimer; 2. distributions in binary form include the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other associated materials; 3. the copyright holder's name is not used to endorse products built using this software without specific written permission. ALTERNATIVELY, provided that this notice is retained in full, this product may be distributed under the terms of the GNU General Public License (GPL), in which case the provisions of the GPL apply INSTEAD OF those given above. DISCLAIMER This software is provided 'as is' with no explicit or implied warranties in respect of its properties, including, but not limited to, correctness and/or fitness for purpose. --------------------------------------------------------------------------- Issue 31/01/2006 This file provides fast multiplication in GF(2^128) as required by several cryptographic authentication modes */ #include <crypto/gf128mul.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> #define gf128mul_dat(q) { \ q(0x00), q(0x01), q(0x02), q(0x03), q(0x04), q(0x05), q(0x06), q(0x07),\ q(0x08), q(0x09), q(0x0a), q(0x0b), q(0x0c), q(0x0d), q(0x0e), q(0x0f),\ q(0x10), q(0x11), q(0x12), q(0x13), q(0x14), q(0x15), q(0x16), q(0x17),\ q(0x18), q(0x19), q(0x1a), q(0x1b), q(0x1c), q(0x1d), q(0x1e), q(0x1f),\ q(0x20), q(0x21), q(0x22), q(0x23), q(0x24), q(0x25), q(0x26), q(0x27),\ q(0x28), q(0x29), q(0x2a), q(0x2b), q(0x2c), q(0x2d), q(0x2e), q(0x2f),\ q(0x30), q(0x31), q(0x32), q(0x33), q(0x34), q(0x35), q(0x36), q(0x37),\ q(0x38), q(0x39), q(0x3a), q(0x3b), q(0x3c), q(0x3d), q(0x3e), q(0x3f),\ q(0x40), q(0x41), q(0x42), q(0x43), q(0x44), q(0x45), q(0x46), q(0x47),\ q(0x48), q(0x49), q(0x4a), q(0x4b), q(0x4c), q(0x4d), q(0x4e), q(0x4f),\ q(0x50), q(0x51), q(0x52), q(0x53), q(0x54), q(0x55), q(0x56), q(0x57),\ q(0x58), q(0x59), q(0x5a), q(0x5b), q(0x5c), q(0x5d), q(0x5e), q(0x5f),\ q(0x60), q(0x61), q(0x62), q(0x63), q(0x64), q(0x65), q(0x66), q(0x67),\ q(0x68), q(0x69), q(0x6a), q(0x6b), q(0x6c), q(0x6d), q(0x6e), q(0x6f),\ q(0x70), q(0x71), q(0x72), q(0x73), q(0x74), q(0x75), q(0x76), q(0x77),\ q(0x78), q(0x79), q(0x7a), q(0x7b), q(0x7c), q(0x7d), q(0x7e), q(0x7f),\ q(0x80), q(0x81), q(0x82), q(0x83), q(0x84), q(0x85), q(0x86), q(0x87),\ q(0x88), q(0x89), q(0x8a), q(0x8b), q(0x8c), q(0x8d), q(0x8e), q(0x8f),\ q(0x90), q(0x91), q(0x92), q(0x93), q(0x94), q(0x95), q(0x96), q(0x97),\ q(0x98), q(0x99), q(0x9a), q(0x9b), q(0x9c), q(0x9d), q(0x9e), q(0x9f),\ q(0xa0), q(0xa1), q(0xa2), q(0xa3), q(0xa4), q(0xa5), q(0xa6), q(0xa7),\ q(0xa8), q(0xa9), q(0xaa), q(0xab), q(0xac), q(0xad), q(0xae), q(0xaf),\ q(0xb0), q(0xb1), q(0xb2), q(0xb3), q(0xb4), q(0xb5), q(0xb6), q(0xb7),\ q(0xb8), q(0xb9), q(0xba), q(0xbb), q(0xbc), q(0xbd), q(0xbe), q(0xbf),\ q(0xc0), q(0xc1), q(0xc2), q(0xc3), q(0xc4), q(0xc5), q(0xc6), q(0xc7),\ q(0xc8), q(0xc9), q(0xca), q(0xcb), q(0xcc), q(0xcd), q(0xce), q(0xcf),\ q(0xd0), q(0xd1), q(0xd2), q(0xd3), q(0xd4), q(0xd5), q(0xd6), q(0xd7),\ q(0xd8), q(0xd9), q(0xda), q(0xdb), q(0xdc), q(0xdd), q(0xde), q(0xdf),\ q(0xe0), q(0xe1), q(0xe2), q(0xe3), q(0xe4), q(0xe5), q(0xe6), q(0xe7),\ q(0xe8), q(0xe9), q(0xea), q(0xeb), q(0xec), q(0xed), q(0xee), q(0xef),\ q(0xf0), q(0xf1), q(0xf2), q(0xf3), q(0xf4), q(0xf5), q(0xf6), q(0xf7),\ q(0xf8), q(0xf9), q(0xfa), q(0xfb), q(0xfc), q(0xfd), q(0xfe), q(0xff) \ } /* * Given a value i in 0..255 as the byte overflow when a field element * in GF(2^128) is multiplied by x^8, the following macro returns the * 16-bit value that must be XOR-ed into the low-degree end of the * product to reduce it modulo the polynomial x^128 + x^7 + x^2 + x + 1. * * There are two versions of the macro, and hence two tables: one for * the "be" convention where the highest-order bit is the coefficient of * the highest-degree polynomial term, and one for the "le" convention * where the highest-order bit is the coefficient of the lowest-degree * polynomial term. In both cases the values are stored in CPU byte * endianness such that the coefficients are ordered consistently across * bytes, i.e. in the "be" table bits 15..0 of the stored value * correspond to the coefficients of x^15..x^0, and in the "le" table * bits 15..0 correspond to the coefficients of x^0..x^15. * * Therefore, provided that the appropriate byte endianness conversions * are done by the multiplication functions (and these must be in place * anyway to support both little endian and big endian CPUs), the "be" * table can be used for multiplications of both "bbe" and "ble" * elements, and the "le" table can be used for multiplications of both * "lle" and "lbe" elements. */ #define xda_be(i) ( \ (i & 0x80 ? 0x4380 : 0) ^ (i & 0x40 ? 0x21c0 : 0) ^ \ (i & 0x20 ? 0x10e0 : 0) ^ (i & 0x10 ? 0x0870 : 0) ^ \ (i & 0x08 ? 0x0438 : 0) ^ (i & 0x04 ? 0x021c : 0) ^ \ (i & 0x02 ? 0x010e : 0) ^ (i & 0x01 ? 0x0087 : 0) \ ) #define xda_le(i) ( \ (i & 0x80 ? 0xe100 : 0) ^ (i & 0x40 ? 0x7080 : 0) ^ \ (i & 0x20 ? 0x3840 : 0) ^ (i & 0x10 ? 0x1c20 : 0) ^ \ (i & 0x08 ? 0x0e10 : 0) ^ (i & 0x04 ? 0x0708 : 0) ^ \ (i & 0x02 ? 0x0384 : 0) ^ (i & 0x01 ? 0x01c2 : 0) \ ) static const u16 gf128mul_table_le[256] = gf128mul_dat(xda_le); static const u16 gf128mul_table_be[256] = gf128mul_dat(xda_be); /* * The following functions multiply a field element by x^8 in * the polynomial field representation. They use 64-bit word operations * to gain speed but compensate for machine endianness and hence work * correctly on both styles of machine. */ static void gf128mul_x8_lle(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); u64 _tt = gf128mul_table_le[b & 0xff]; x->b = cpu_to_be64((b >> 8) | (a << 56)); x->a = cpu_to_be64((a >> 8) ^ (_tt << 48)); } /* time invariant version of gf128mul_x8_lle */ static void gf128mul_x8_lle_ti(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); u64 _tt = xda_le(b & 0xff); /* avoid table lookup */ x->b = cpu_to_be64((b >> 8) | (a << 56)); x->a = cpu_to_be64((a >> 8) ^ (_tt << 48)); } static void gf128mul_x8_bbe(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); u64 _tt = gf128mul_table_be[a >> 56]; x->a = cpu_to_be64((a << 8) | (b >> 56)); x->b = cpu_to_be64((b << 8) ^ _tt); } void gf128mul_x8_ble(le128 *r, const le128 *x) { u64 a = le64_to_cpu(x->a); u64 b = le64_to_cpu(x->b); u64 _tt = gf128mul_table_be[a >> 56]; r->a = cpu_to_le64((a << 8) | (b >> 56)); r->b = cpu_to_le64((b << 8) ^ _tt); } EXPORT_SYMBOL(gf128mul_x8_ble); void gf128mul_lle(be128 *r, const be128 *b) { /* * The p array should be aligned to twice the size of its element type, * so that every even/odd pair is guaranteed to share a cacheline * (assuming a cacheline size of 32 bytes or more, which is by far the * most common). This ensures that each be128_xor() call in the loop * takes the same amount of time regardless of the value of 'ch', which * is derived from function parameter 'b', which is commonly used as a * key, e.g., for GHASH. The odd array elements are all set to zero, * making each be128_xor() a NOP if its associated bit in 'ch' is not * set, and this is equivalent to calling be128_xor() conditionally. * This approach aims to avoid leaking information about such keys * through execution time variances. * * Unfortunately, __aligned(16) or higher does not work on x86 for * variables on the stack so we need to perform the alignment by hand. */ be128 array[16 + 3] = {}; be128 *p = PTR_ALIGN(&array[0], 2 * sizeof(be128)); int i; p[0] = *r; for (i = 0; i < 7; ++i) gf128mul_x_lle(&p[2 * i + 2], &p[2 * i]); memset(r, 0, sizeof(*r)); for (i = 0;;) { u8 ch = ((u8 *)b)[15 - i]; be128_xor(r, r, &p[ 0 + !(ch & 0x80)]); be128_xor(r, r, &p[ 2 + !(ch & 0x40)]); be128_xor(r, r, &p[ 4 + !(ch & 0x20)]); be128_xor(r, r, &p[ 6 + !(ch & 0x10)]); be128_xor(r, r, &p[ 8 + !(ch & 0x08)]); be128_xor(r, r, &p[10 + !(ch & 0x04)]); be128_xor(r, r, &p[12 + !(ch & 0x02)]); be128_xor(r, r, &p[14 + !(ch & 0x01)]); if (++i >= 16) break; gf128mul_x8_lle_ti(r); /* use the time invariant version */ } } EXPORT_SYMBOL(gf128mul_lle); /* This version uses 64k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key value in GF(2^128). If we consider a GF(2^128) value in the buffer's lowest byte, we can construct a table of the 256 16 byte values that result from the 256 values of this byte. This requires 4096 bytes. But we also need tables for each of the 16 higher bytes in the buffer as well, which makes 64 kbytes in total. */ /* additional explanation * t[0][BYTE] contains g*BYTE * t[1][BYTE] contains g*x^8*BYTE * .. * t[15][BYTE] contains g*x^120*BYTE */ struct gf128mul_64k *gf128mul_init_64k_bbe(const be128 *g) { struct gf128mul_64k *t; int i, j, k; t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) goto out; for (i = 0; i < 16; i++) { t->t[i] = kzalloc(sizeof(*t->t[i]), GFP_KERNEL); if (!t->t[i]) { gf128mul_free_64k(t); t = NULL; goto out; } } t->t[0]->t[1] = *g; for (j = 1; j <= 64; j <<= 1) gf128mul_x_bbe(&t->t[0]->t[j + j], &t->t[0]->t[j]); for (i = 0;;) { for (j = 2; j < 256; j += j) for (k = 1; k < j; ++k) be128_xor(&t->t[i]->t[j + k], &t->t[i]->t[j], &t->t[i]->t[k]); if (++i >= 16) break; for (j = 128; j > 0; j >>= 1) { t->t[i]->t[j] = t->t[i - 1]->t[j]; gf128mul_x8_bbe(&t->t[i]->t[j]); } } out: return t; } EXPORT_SYMBOL(gf128mul_init_64k_bbe); void gf128mul_free_64k(struct gf128mul_64k *t) { int i; for (i = 0; i < 16; i++) kfree_sensitive(t->t[i]); kfree_sensitive(t); } EXPORT_SYMBOL(gf128mul_free_64k); void gf128mul_64k_bbe(be128 *a, const struct gf128mul_64k *t) { u8 *ap = (u8 *)a; be128 r[1]; int i; *r = t->t[0]->t[ap[15]]; for (i = 1; i < 16; ++i) be128_xor(r, r, &t->t[i]->t[ap[15 - i]]); *a = *r; } EXPORT_SYMBOL(gf128mul_64k_bbe); /* This version uses 4k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key value in GF(2^128). If we consider a GF(2^128) value in a single byte, we can construct a table of the 256 16 byte values that result from the 256 values of this byte. This requires 4096 bytes. If we take the highest byte in the buffer and use this table to get the result, we then have to multiply by x^120 to get the final value. For the next highest byte the result has to be multiplied by x^112 and so on. But we can do this by accumulating the result in an accumulator starting with the result for the top byte. We repeatedly multiply the accumulator value by x^8 and then add in (i.e. xor) the 16 bytes of the next lower byte in the buffer, stopping when we reach the lowest byte. This requires a 4096 byte table. */ struct gf128mul_4k *gf128mul_init_4k_lle(const be128 *g) { struct gf128mul_4k *t; int j, k; t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) goto out; t->t[128] = *g; for (j = 64; j > 0; j >>= 1) gf128mul_x_lle(&t->t[j], &t->t[j+j]); for (j = 2; j < 256; j += j) for (k = 1; k < j; ++k) be128_xor(&t->t[j + k], &t->t[j], &t->t[k]); out: return t; } EXPORT_SYMBOL(gf128mul_init_4k_lle); void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t) { u8 *ap = (u8 *)a; be128 r[1]; int i = 15; *r = t->t[ap[15]]; while (i--) { gf128mul_x8_lle(r); be128_xor(r, r, &t->t[ap[i]]); } *a = *r; } EXPORT_SYMBOL(gf128mul_4k_lle); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Functions for multiplying elements of GF(2^128)"); |
| 45 5 3 40 44 24 24 24 24 24 3 3 1 1 2 2 2 1 10 1 1 1 1 1 1 1 1 1 9 8 8 7 6 5 2 5 6 4 6 4 6 6 5 5 4 3 3 5 6 6 5 3 6 16 16 11 16 11 16 9 16 9 15 8 18 18 17 17 17 16 18 48 46 47 49 46 1 2 2 1 9 5 6 18 1 1 10 2 49 8 5 8 4 2 4 34 33 25 24 3 2 6 8 3 1 34 58 52 51 51 44 1 50 45 3 45 4 45 47 43 49 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Quota code necessary even when VFS quota support is not compiled * into the kernel. The interesting stuff is over in dquot.c, here * we have symbols for initial quotactl(2) handling, the sysctl(2) * variables, etc - things needed even when quota support disabled. */ #include <linux/fs.h> #include <linux/namei.h> #include <linux/slab.h> #include <asm/current.h> #include <linux/blkdev.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/quotaops.h> #include <linux/types.h> #include <linux/mount.h> #include <linux/writeback.h> #include <linux/nospec.h> #include "compat.h" #include "../internal.h" static int check_quotactl_permission(struct super_block *sb, int type, int cmd, qid_t id) { switch (cmd) { /* these commands do not require any special privilegues */ case Q_GETFMT: case Q_SYNC: case Q_GETINFO: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XQUOTASYNC: break; /* allow to query information for dquots we "own" */ case Q_GETQUOTA: case Q_XGETQUOTA: if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) || (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id)))) break; fallthrough; default: if (!capable(CAP_SYS_ADMIN)) return -EPERM; } return security_quotactl(cmd, type, id, sb); } static void quota_sync_one(struct super_block *sb, void *arg) { int type = *(int *)arg; if (sb->s_qcop && sb->s_qcop->quota_sync && (sb->s_quota_types & (1 << type))) sb->s_qcop->quota_sync(sb, type); } static int quota_sync_all(int type) { int ret; ret = security_quotactl(Q_SYNC, type, 0, NULL); if (!ret) iterate_supers(quota_sync_one, &type); return ret; } unsigned int qtype_enforce_flag(int type) { switch (type) { case USRQUOTA: return FS_QUOTA_UDQ_ENFD; case GRPQUOTA: return FS_QUOTA_GDQ_ENFD; case PRJQUOTA: return FS_QUOTA_PDQ_ENFD; } return 0; } static int quota_quotaon(struct super_block *sb, int type, qid_t id, const struct path *path) { if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) return -ENOSYS; if (sb->s_qcop->quota_enable) return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) return PTR_ERR(path); return sb->s_qcop->quota_on(sb, type, id, path); } static int quota_quotaoff(struct super_block *sb, int type) { if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable) return -ENOSYS; if (sb->s_qcop->quota_disable) return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type)); return sb->s_qcop->quota_off(sb, type); } static int quota_getfmt(struct super_block *sb, int type, void __user *addr) { __u32 fmt; if (!sb_has_quota_active(sb, type)) return -ESRCH; fmt = sb_dqopt(sb)->info[type].dqi_format->qf_fmt_id; if (copy_to_user(addr, &fmt, sizeof(fmt))) return -EFAULT; return 0; } static int quota_getinfo(struct super_block *sb, int type, void __user *addr) { struct qc_state state; struct qc_type_state *tstate; struct if_dqinfo uinfo; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; ret = sb->s_qcop->get_state(sb, &state); if (ret) return ret; tstate = state.s_state + type; if (!(tstate->flags & QCI_ACCT_ENABLED)) return -ESRCH; memset(&uinfo, 0, sizeof(uinfo)); uinfo.dqi_bgrace = tstate->spc_timelimit; uinfo.dqi_igrace = tstate->ino_timelimit; if (tstate->flags & QCI_SYSFILE) uinfo.dqi_flags |= DQF_SYS_FILE; if (tstate->flags & QCI_ROOT_SQUASH) uinfo.dqi_flags |= DQF_ROOT_SQUASH; uinfo.dqi_valid = IIF_ALL; if (copy_to_user(addr, &uinfo, sizeof(uinfo))) return -EFAULT; return 0; } static int quota_setinfo(struct super_block *sb, int type, void __user *addr) { struct if_dqinfo info; struct qc_info qinfo; if (copy_from_user(&info, addr, sizeof(info))) return -EFAULT; if (!sb->s_qcop->set_info) return -ENOSYS; if (info.dqi_valid & ~(IIF_FLAGS | IIF_BGRACE | IIF_IGRACE)) return -EINVAL; memset(&qinfo, 0, sizeof(qinfo)); if (info.dqi_valid & IIF_FLAGS) { if (info.dqi_flags & ~DQF_SETINFO_MASK) return -EINVAL; if (info.dqi_flags & DQF_ROOT_SQUASH) qinfo.i_flags |= QCI_ROOT_SQUASH; qinfo.i_fieldmask |= QC_FLAGS; } if (info.dqi_valid & IIF_BGRACE) { qinfo.i_spc_timelimit = info.dqi_bgrace; qinfo.i_fieldmask |= QC_SPC_TIMER; } if (info.dqi_valid & IIF_IGRACE) { qinfo.i_ino_timelimit = info.dqi_igrace; qinfo.i_fieldmask |= QC_INO_TIMER; } return sb->s_qcop->set_info(sb, type, &qinfo); } static inline qsize_t qbtos(qsize_t blocks) { return blocks << QIF_DQBLKSIZE_BITS; } static inline qsize_t stoqb(qsize_t space) { return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; } static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src) { memset(dst, 0, sizeof(*dst)); dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit); dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit); dst->dqb_curspace = src->d_space; dst->dqb_ihardlimit = src->d_ino_hardlimit; dst->dqb_isoftlimit = src->d_ino_softlimit; dst->dqb_curinodes = src->d_ino_count; dst->dqb_btime = src->d_spc_timer; dst->dqb_itime = src->d_ino_timer; dst->dqb_valid = QIF_ALL; } static int quota_getquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; struct qc_dqblk fdq; struct if_dqblk idq; int ret; if (!sb->s_qcop->get_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_dqblk(sb, qid, &fdq); if (ret) return ret; copy_to_if_dqblk(&idq, &fdq); if (compat_need_64bit_alignment_fixup()) { struct compat_if_dqblk __user *compat_dqblk = addr; if (copy_to_user(compat_dqblk, &idq, sizeof(*compat_dqblk))) return -EFAULT; if (put_user(idq.dqb_valid, &compat_dqblk->dqb_valid)) return -EFAULT; } else { if (copy_to_user(addr, &idq, sizeof(idq))) return -EFAULT; } return 0; } /* * Return quota for next active quota >= this id, if any exists, * otherwise return -ENOENT via ->get_nextdqblk */ static int quota_getnextquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; struct qc_dqblk fdq; struct if_nextdqblk idq; int ret; if (!sb->s_qcop->get_nextdqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_nextdqblk(sb, &qid, &fdq); if (ret) return ret; /* struct if_nextdqblk is a superset of struct if_dqblk */ copy_to_if_dqblk((struct if_dqblk *)&idq, &fdq); idq.dqb_id = from_kqid(current_user_ns(), qid); if (copy_to_user(addr, &idq, sizeof(idq))) return -EFAULT; return 0; } static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src) { dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit); dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit); dst->d_space = src->dqb_curspace; dst->d_ino_hardlimit = src->dqb_ihardlimit; dst->d_ino_softlimit = src->dqb_isoftlimit; dst->d_ino_count = src->dqb_curinodes; dst->d_spc_timer = src->dqb_btime; dst->d_ino_timer = src->dqb_itime; dst->d_fieldmask = 0; if (src->dqb_valid & QIF_BLIMITS) dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD; if (src->dqb_valid & QIF_SPACE) dst->d_fieldmask |= QC_SPACE; if (src->dqb_valid & QIF_ILIMITS) dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD; if (src->dqb_valid & QIF_INODES) dst->d_fieldmask |= QC_INO_COUNT; if (src->dqb_valid & QIF_BTIME) dst->d_fieldmask |= QC_SPC_TIMER; if (src->dqb_valid & QIF_ITIME) dst->d_fieldmask |= QC_INO_TIMER; } static int quota_setquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct qc_dqblk fdq; struct if_dqblk idq; struct kqid qid; if (compat_need_64bit_alignment_fixup()) { struct compat_if_dqblk __user *compat_dqblk = addr; if (copy_from_user(&idq, compat_dqblk, sizeof(*compat_dqblk)) || get_user(idq.dqb_valid, &compat_dqblk->dqb_valid)) return -EFAULT; } else { if (copy_from_user(&idq, addr, sizeof(idq))) return -EFAULT; } if (!sb->s_qcop->set_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; copy_from_if_dqblk(&fdq, &idq); return sb->s_qcop->set_dqblk(sb, qid, &fdq); } static int quota_enable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; if (!sb->s_qcop->quota_enable) return -ENOSYS; return sb->s_qcop->quota_enable(sb, flags); } static int quota_disable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; if (!sb->s_qcop->quota_disable) return -ENOSYS; return sb->s_qcop->quota_disable(sb, flags); } static int quota_state_to_flags(struct qc_state *state) { int flags = 0; if (state->s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) flags |= FS_QUOTA_UDQ_ACCT; if (state->s_state[USRQUOTA].flags & QCI_LIMITS_ENFORCED) flags |= FS_QUOTA_UDQ_ENFD; if (state->s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) flags |= FS_QUOTA_GDQ_ACCT; if (state->s_state[GRPQUOTA].flags & QCI_LIMITS_ENFORCED) flags |= FS_QUOTA_GDQ_ENFD; if (state->s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) flags |= FS_QUOTA_PDQ_ACCT; if (state->s_state[PRJQUOTA].flags & QCI_LIMITS_ENFORCED) flags |= FS_QUOTA_PDQ_ENFD; return flags; } static int quota_getstate(struct super_block *sb, int type, struct fs_quota_stat *fqs) { struct qc_state state; int ret; memset(&state, 0, sizeof (struct qc_state)); ret = sb->s_qcop->get_state(sb, &state); if (ret < 0) return ret; memset(fqs, 0, sizeof(*fqs)); fqs->qs_version = FS_QSTAT_VERSION; fqs->qs_flags = quota_state_to_flags(&state); /* No quota enabled? */ if (!fqs->qs_flags) return -ENOSYS; fqs->qs_incoredqs = state.s_incoredqs; fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; /* Inodes may be allocated even if inactive; copy out if present */ if (state.s_state[USRQUOTA].ino) { fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; } if (state.s_state[GRPQUOTA].ino) { fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; } if (state.s_state[PRJQUOTA].ino) { /* * Q_XGETQSTAT doesn't have room for both group and project * quotas. So, allow the project quota values to be copied out * only if there is no group quota information available. */ if (!(state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED)) { fqs->qs_gquota.qfs_ino = state.s_state[PRJQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[PRJQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[PRJQUOTA].nextents; } } return 0; } static int compat_copy_fs_qfilestat(struct compat_fs_qfilestat __user *to, struct fs_qfilestat *from) { if (copy_to_user(to, from, sizeof(*to)) || put_user(from->qfs_nextents, &to->qfs_nextents)) return -EFAULT; return 0; } static int compat_copy_fs_quota_stat(struct compat_fs_quota_stat __user *to, struct fs_quota_stat *from) { if (put_user(from->qs_version, &to->qs_version) || put_user(from->qs_flags, &to->qs_flags) || put_user(from->qs_pad, &to->qs_pad) || compat_copy_fs_qfilestat(&to->qs_uquota, &from->qs_uquota) || compat_copy_fs_qfilestat(&to->qs_gquota, &from->qs_gquota) || put_user(from->qs_incoredqs, &to->qs_incoredqs) || put_user(from->qs_btimelimit, &to->qs_btimelimit) || put_user(from->qs_itimelimit, &to->qs_itimelimit) || put_user(from->qs_rtbtimelimit, &to->qs_rtbtimelimit) || put_user(from->qs_bwarnlimit, &to->qs_bwarnlimit) || put_user(from->qs_iwarnlimit, &to->qs_iwarnlimit)) return -EFAULT; return 0; } static int quota_getxstate(struct super_block *sb, int type, void __user *addr) { struct fs_quota_stat fqs; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; ret = quota_getstate(sb, type, &fqs); if (ret) return ret; if (compat_need_64bit_alignment_fixup()) return compat_copy_fs_quota_stat(addr, &fqs); if (copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return 0; } static int quota_getstatev(struct super_block *sb, int type, struct fs_quota_statv *fqs) { struct qc_state state; int ret; memset(&state, 0, sizeof (struct qc_state)); ret = sb->s_qcop->get_state(sb, &state); if (ret < 0) return ret; memset(fqs, 0, sizeof(*fqs)); fqs->qs_version = FS_QSTAT_VERSION; fqs->qs_flags = quota_state_to_flags(&state); /* No quota enabled? */ if (!fqs->qs_flags) return -ENOSYS; fqs->qs_incoredqs = state.s_incoredqs; fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit; fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit; fqs->qs_rtbwarnlimit = state.s_state[type].rt_spc_warnlimit; /* Inodes may be allocated even if inactive; copy out if present */ if (state.s_state[USRQUOTA].ino) { fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino; fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks; fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents; } if (state.s_state[GRPQUOTA].ino) { fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino; fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks; fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents; } if (state.s_state[PRJQUOTA].ino) { fqs->qs_pquota.qfs_ino = state.s_state[PRJQUOTA].ino; fqs->qs_pquota.qfs_nblks = state.s_state[PRJQUOTA].blocks; fqs->qs_pquota.qfs_nextents = state.s_state[PRJQUOTA].nextents; } return 0; } static int quota_getxstatev(struct super_block *sb, int type, void __user *addr) { struct fs_quota_statv fqs; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; memset(&fqs, 0, sizeof(fqs)); if (copy_from_user(&fqs, addr, 1)) /* Just read qs_version */ return -EFAULT; /* If this kernel doesn't support user specified version, fail */ switch (fqs.qs_version) { case FS_QSTATV_VERSION1: break; default: return -EINVAL; } ret = quota_getstatev(sb, type, &fqs); if (!ret && copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return ret; } /* * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them * out of there as xfsprogs rely on definitions being in that header file. So * just define same functions here for quota purposes. */ #define XFS_BB_SHIFT 9 static inline u64 quota_bbtob(u64 blocks) { return blocks << XFS_BB_SHIFT; } static inline u64 quota_btobb(u64 bytes) { return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT; } static inline s64 copy_from_xfs_dqblk_ts(const struct fs_disk_quota *d, __s32 timer, __s8 timer_hi) { if (d->d_fieldmask & FS_DQ_BIGTIME) return (u32)timer | (s64)timer_hi << 32; return timer; } static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src) { dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit); dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit); dst->d_ino_hardlimit = src->d_ino_hardlimit; dst->d_ino_softlimit = src->d_ino_softlimit; dst->d_space = quota_bbtob(src->d_bcount); dst->d_ino_count = src->d_icount; dst->d_ino_timer = copy_from_xfs_dqblk_ts(src, src->d_itimer, src->d_itimer_hi); dst->d_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_btimer, src->d_btimer_hi); dst->d_ino_warns = src->d_iwarns; dst->d_spc_warns = src->d_bwarns; dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit); dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit); dst->d_rt_space = quota_bbtob(src->d_rtbcount); dst->d_rt_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_rtbtimer, src->d_rtbtimer_hi); dst->d_rt_spc_warns = src->d_rtbwarns; dst->d_fieldmask = 0; if (src->d_fieldmask & FS_DQ_ISOFT) dst->d_fieldmask |= QC_INO_SOFT; if (src->d_fieldmask & FS_DQ_IHARD) dst->d_fieldmask |= QC_INO_HARD; if (src->d_fieldmask & FS_DQ_BSOFT) dst->d_fieldmask |= QC_SPC_SOFT; if (src->d_fieldmask & FS_DQ_BHARD) dst->d_fieldmask |= QC_SPC_HARD; if (src->d_fieldmask & FS_DQ_RTBSOFT) dst->d_fieldmask |= QC_RT_SPC_SOFT; if (src->d_fieldmask & FS_DQ_RTBHARD) dst->d_fieldmask |= QC_RT_SPC_HARD; if (src->d_fieldmask & FS_DQ_BTIMER) dst->d_fieldmask |= QC_SPC_TIMER; if (src->d_fieldmask & FS_DQ_ITIMER) dst->d_fieldmask |= QC_INO_TIMER; if (src->d_fieldmask & FS_DQ_RTBTIMER) dst->d_fieldmask |= QC_RT_SPC_TIMER; if (src->d_fieldmask & FS_DQ_BWARNS) dst->d_fieldmask |= QC_SPC_WARNS; if (src->d_fieldmask & FS_DQ_IWARNS) dst->d_fieldmask |= QC_INO_WARNS; if (src->d_fieldmask & FS_DQ_RTBWARNS) dst->d_fieldmask |= QC_RT_SPC_WARNS; if (src->d_fieldmask & FS_DQ_BCOUNT) dst->d_fieldmask |= QC_SPACE; if (src->d_fieldmask & FS_DQ_ICOUNT) dst->d_fieldmask |= QC_INO_COUNT; if (src->d_fieldmask & FS_DQ_RTBCOUNT) dst->d_fieldmask |= QC_RT_SPACE; } static void copy_qcinfo_from_xfs_dqblk(struct qc_info *dst, struct fs_disk_quota *src) { memset(dst, 0, sizeof(*dst)); dst->i_spc_timelimit = src->d_btimer; dst->i_ino_timelimit = src->d_itimer; dst->i_rt_spc_timelimit = src->d_rtbtimer; dst->i_ino_warnlimit = src->d_iwarns; dst->i_spc_warnlimit = src->d_bwarns; dst->i_rt_spc_warnlimit = src->d_rtbwarns; if (src->d_fieldmask & FS_DQ_BWARNS) dst->i_fieldmask |= QC_SPC_WARNS; if (src->d_fieldmask & FS_DQ_IWARNS) dst->i_fieldmask |= QC_INO_WARNS; if (src->d_fieldmask & FS_DQ_RTBWARNS) dst->i_fieldmask |= QC_RT_SPC_WARNS; if (src->d_fieldmask & FS_DQ_BTIMER) dst->i_fieldmask |= QC_SPC_TIMER; if (src->d_fieldmask & FS_DQ_ITIMER) dst->i_fieldmask |= QC_INO_TIMER; if (src->d_fieldmask & FS_DQ_RTBTIMER) dst->i_fieldmask |= QC_RT_SPC_TIMER; } static int quota_setxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; struct qc_dqblk qdq; struct kqid qid; if (copy_from_user(&fdq, addr, sizeof(fdq))) return -EFAULT; if (!sb->s_qcop->set_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; /* Are we actually setting timer / warning limits for all users? */ if (from_kqid(sb->s_user_ns, qid) == 0 && fdq.d_fieldmask & (FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK)) { struct qc_info qinfo; int ret; if (!sb->s_qcop->set_info) return -EINVAL; copy_qcinfo_from_xfs_dqblk(&qinfo, &fdq); ret = sb->s_qcop->set_info(sb, type, &qinfo); if (ret) return ret; /* These are already done */ fdq.d_fieldmask &= ~(FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK); } copy_from_xfs_dqblk(&qdq, &fdq); return sb->s_qcop->set_dqblk(sb, qid, &qdq); } static inline void copy_to_xfs_dqblk_ts(const struct fs_disk_quota *d, __s32 *timer_lo, __s8 *timer_hi, s64 timer) { *timer_lo = timer; if (d->d_fieldmask & FS_DQ_BIGTIME) *timer_hi = timer >> 32; } static inline bool want_bigtime(s64 timer) { return timer > S32_MAX || timer < S32_MIN; } static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src, int type, qid_t id) { memset(dst, 0, sizeof(*dst)); if (want_bigtime(src->d_ino_timer) || want_bigtime(src->d_spc_timer) || want_bigtime(src->d_rt_spc_timer)) dst->d_fieldmask |= FS_DQ_BIGTIME; dst->d_version = FS_DQUOT_VERSION; dst->d_id = id; if (type == USRQUOTA) dst->d_flags = FS_USER_QUOTA; else if (type == PRJQUOTA) dst->d_flags = FS_PROJ_QUOTA; else dst->d_flags = FS_GROUP_QUOTA; dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit); dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit); dst->d_ino_hardlimit = src->d_ino_hardlimit; dst->d_ino_softlimit = src->d_ino_softlimit; dst->d_bcount = quota_btobb(src->d_space); dst->d_icount = src->d_ino_count; copy_to_xfs_dqblk_ts(dst, &dst->d_itimer, &dst->d_itimer_hi, src->d_ino_timer); copy_to_xfs_dqblk_ts(dst, &dst->d_btimer, &dst->d_btimer_hi, src->d_spc_timer); dst->d_iwarns = src->d_ino_warns; dst->d_bwarns = src->d_spc_warns; dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit); dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit); dst->d_rtbcount = quota_btobb(src->d_rt_space); copy_to_xfs_dqblk_ts(dst, &dst->d_rtbtimer, &dst->d_rtbtimer_hi, src->d_rt_spc_timer); dst->d_rtbwarns = src->d_rt_spc_warns; } static int quota_getxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; struct qc_dqblk qdq; struct kqid qid; int ret; if (!sb->s_qcop->get_dqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_dqblk(sb, qid, &qdq); if (ret) return ret; copy_to_xfs_dqblk(&fdq, &qdq, type, id); if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } /* * Return quota for next active quota >= this id, if any exists, * otherwise return -ENOENT via ->get_nextdqblk. */ static int quota_getnextxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; struct qc_dqblk qdq; struct kqid qid; qid_t id_out; int ret; if (!sb->s_qcop->get_nextdqblk) return -ENOSYS; qid = make_kqid(current_user_ns(), type, id); if (!qid_has_mapping(sb->s_user_ns, qid)) return -EINVAL; ret = sb->s_qcop->get_nextdqblk(sb, &qid, &qdq); if (ret) return ret; id_out = from_kqid(current_user_ns(), qid); copy_to_xfs_dqblk(&fdq, &qdq, type, id_out); if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } static int quota_rmxquota(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; if (!sb->s_qcop->rm_xquota) return -ENOSYS; return sb->s_qcop->rm_xquota(sb, flags); } /* Copy parameters and call proper function */ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, void __user *addr, const struct path *path) { int ret; type = array_index_nospec(type, MAXQUOTAS); /* * Quota not supported on this fs? Check this before s_quota_types * since they needn't be set if quota is not supported at all. */ if (!sb->s_qcop) return -ENOSYS; if (!(sb->s_quota_types & (1 << type))) return -EINVAL; ret = check_quotactl_permission(sb, type, cmd, id); if (ret < 0) return ret; switch (cmd) { case Q_QUOTAON: return quota_quotaon(sb, type, id, path); case Q_QUOTAOFF: return quota_quotaoff(sb, type); case Q_GETFMT: return quota_getfmt(sb, type, addr); case Q_GETINFO: return quota_getinfo(sb, type, addr); case Q_SETINFO: return quota_setinfo(sb, type, addr); case Q_GETQUOTA: return quota_getquota(sb, type, id, addr); case Q_GETNEXTQUOTA: return quota_getnextquota(sb, type, id, addr); case Q_SETQUOTA: return quota_setquota(sb, type, id, addr); case Q_SYNC: if (!sb->s_qcop->quota_sync) return -ENOSYS; return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: return quota_enable(sb, addr); case Q_XQUOTAOFF: return quota_disable(sb, addr); case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: return quota_getxstate(sb, type, addr); case Q_XGETQSTATV: return quota_getxstatev(sb, type, addr); case Q_XSETQLIM: return quota_setxquota(sb, type, id, addr); case Q_XGETQUOTA: return quota_getxquota(sb, type, id, addr); case Q_XGETNEXTQUOTA: return quota_getnextxquota(sb, type, id, addr); case Q_XQUOTASYNC: if (sb_rdonly(sb)) return -EROFS; /* XFS quotas are fully coherent now, making this call a noop */ return 0; default: return -EINVAL; } } /* Return 1 if 'cmd' will block on frozen filesystem */ static int quotactl_cmd_write(int cmd) { /* * We cannot allow Q_GETQUOTA and Q_GETNEXTQUOTA without write access * as dquot_acquire() may allocate space for new structure and OCFS2 * needs to increment on-disk use count. */ switch (cmd) { case Q_GETFMT: case Q_GETINFO: case Q_SYNC: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETQUOTA: case Q_XGETNEXTQUOTA: case Q_XQUOTASYNC: return 0; } return 1; } /* Return true if quotactl command is manipulating quota on/off state */ static bool quotactl_cmd_onoff(int cmd) { return (cmd == Q_QUOTAON) || (cmd == Q_QUOTAOFF) || (cmd == Q_XQUOTAON) || (cmd == Q_XQUOTAOFF); } /* * look up a superblock on which quota ops will be performed * - use the name of a block device to find the superblock thereon */ static struct super_block *quotactl_block(const char __user *special, int cmd) { #ifdef CONFIG_BLOCK struct super_block *sb; struct filename *tmp = getname(special); bool excl = false, thawed = false; int error; dev_t dev; if (IS_ERR(tmp)) return ERR_CAST(tmp); error = lookup_bdev(tmp->name, &dev); putname(tmp); if (error) return ERR_PTR(error); if (quotactl_cmd_onoff(cmd)) { excl = true; thawed = true; } else if (quotactl_cmd_write(cmd)) { thawed = true; } retry: sb = user_get_super(dev, excl); if (!sb) return ERR_PTR(-ENODEV); if (thawed && sb->s_writers.frozen != SB_UNFROZEN) { if (excl) up_write(&sb->s_umount); else up_read(&sb->s_umount); /* Wait for sb to unfreeze */ sb_start_write(sb); sb_end_write(sb); put_super(sb); goto retry; } return sb; #else return ERR_PTR(-ENODEV); #endif } /* * This is the system call interface. This communicates with * the user-level programs. Currently this only supports diskquota * calls. Maybe we need to add the process quotas etc. in the future, * but we probably should use rlimits for that. */ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr) { uint cmds, type; struct super_block *sb = NULL; struct path path, *pathp = NULL; int ret; cmds = cmd >> SUBCMDSHIFT; type = cmd & SUBCMDMASK; if (type >= MAXQUOTAS) return -EINVAL; /* * As a special case Q_SYNC can be called without a specific device. * It will iterate all superblocks that have quota enabled and call * the sync action on each of them. */ if (!special) { if (cmds == Q_SYNC) return quota_sync_all(type); return -ENODEV; } /* * Path for quotaon has to be resolved before grabbing superblock * because that gets s_umount sem which is also possibly needed by path * resolution (think about autofs) and thus deadlocks could arise. */ if (cmds == Q_QUOTAON) { ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); if (ret) pathp = ERR_PTR(ret); else pathp = &path; } sb = quotactl_block(special, cmds); if (IS_ERR(sb)) { ret = PTR_ERR(sb); goto out; } ret = do_quotactl(sb, type, cmds, id, addr, pathp); if (!quotactl_cmd_onoff(cmds)) drop_super(sb); else drop_super_exclusive(sb); out: if (pathp && !IS_ERR(pathp)) path_put(pathp); return ret; } SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd, qid_t, id, void __user *, addr) { struct super_block *sb; unsigned int cmds = cmd >> SUBCMDSHIFT; unsigned int type = cmd & SUBCMDMASK; CLASS(fd_raw, f)(fd); int ret; if (fd_empty(f)) return -EBADF; if (type >= MAXQUOTAS) return -EINVAL; if (quotactl_cmd_write(cmds)) { ret = mnt_want_write(fd_file(f)->f_path.mnt); if (ret) return ret; } sb = fd_file(f)->f_path.mnt->mnt_sb; if (quotactl_cmd_onoff(cmds)) down_write(&sb->s_umount); else down_read(&sb->s_umount); ret = do_quotactl(sb, type, cmds, id, addr, ERR_PTR(-EINVAL)); if (quotactl_cmd_onoff(cmds)) up_write(&sb->s_umount); else up_read(&sb->s_umount); if (quotactl_cmd_write(cmds)) mnt_drop_write(fd_file(f)->f_path.mnt); return ret; } |
| 24 24 24 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 | // SPDX-License-Identifier: GPL-2.0-only /* * The NFC Controller Interface is the communication protocol between an * NFC Controller (NFCC) and a Device Host (DH). * This is the HCI over NCI implementation, as specified in the 10.2 * section of the NCI 1.1 specification. * * Copyright (C) 2014 STMicroelectronics SAS. All rights reserved. */ #include <linux/skbuff.h> #include "../nfc.h" #include <net/nfc/nci.h> #include <net/nfc/nci_core.h> #include <linux/nfc.h> #include <linux/kcov.h> struct nci_data { u8 conn_id; u8 pipe; u8 cmd; const u8 *data; u32 data_len; } __packed; struct nci_hci_create_pipe_params { u8 src_gate; u8 dest_host; u8 dest_gate; } __packed; struct nci_hci_create_pipe_resp { u8 src_host; u8 src_gate; u8 dest_host; u8 dest_gate; u8 pipe; } __packed; struct nci_hci_delete_pipe_noti { u8 pipe; } __packed; struct nci_hci_all_pipe_cleared_noti { u8 host; } __packed; struct nci_hcp_message { u8 header; /* type -cmd,evt,rsp- + instruction */ u8 data[]; } __packed; struct nci_hcp_packet { u8 header; /* cbit+pipe */ struct nci_hcp_message message; } __packed; #define NCI_HCI_ANY_SET_PARAMETER 0x01 #define NCI_HCI_ANY_GET_PARAMETER 0x02 #define NCI_HCI_ANY_CLOSE_PIPE 0x04 #define NCI_HCI_ADM_CLEAR_ALL_PIPE 0x14 #define NCI_HFP_NO_CHAINING 0x80 #define NCI_NFCEE_ID_HCI 0x80 #define NCI_EVT_HOT_PLUG 0x03 #define NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY 0x01 #define NCI_HCI_ADM_CREATE_PIPE 0x10 #define NCI_HCI_ADM_DELETE_PIPE 0x11 /* HCP headers */ #define NCI_HCI_HCP_PACKET_HEADER_LEN 1 #define NCI_HCI_HCP_MESSAGE_HEADER_LEN 1 #define NCI_HCI_HCP_HEADER_LEN 2 /* HCP types */ #define NCI_HCI_HCP_COMMAND 0x00 #define NCI_HCI_HCP_EVENT 0x01 #define NCI_HCI_HCP_RESPONSE 0x02 #define NCI_HCI_ADM_NOTIFY_PIPE_CREATED 0x12 #define NCI_HCI_ADM_NOTIFY_PIPE_DELETED 0x13 #define NCI_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED 0x15 #define NCI_HCI_FRAGMENT 0x7f #define NCI_HCP_HEADER(type, instr) ((((type) & 0x03) << 6) |\ ((instr) & 0x3f)) #define NCI_HCP_MSG_GET_TYPE(header) ((header & 0xc0) >> 6) #define NCI_HCP_MSG_GET_CMD(header) (header & 0x3f) #define NCI_HCP_MSG_GET_PIPE(header) (header & 0x7f) static int nci_hci_result_to_errno(u8 result) { switch (result) { case NCI_HCI_ANY_OK: return 0; case NCI_HCI_ANY_E_REG_PAR_UNKNOWN: return -EOPNOTSUPP; case NCI_HCI_ANY_E_TIMEOUT: return -ETIME; default: return -1; } } /* HCI core */ static void nci_hci_reset_pipes(struct nci_hci_dev *hdev) { int i; for (i = 0; i < NCI_HCI_MAX_PIPES; i++) { hdev->pipes[i].gate = NCI_HCI_INVALID_GATE; hdev->pipes[i].host = NCI_HCI_INVALID_HOST; } memset(hdev->gate2pipe, NCI_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe)); } static void nci_hci_reset_pipes_per_host(struct nci_dev *ndev, u8 host) { int i; for (i = 0; i < NCI_HCI_MAX_PIPES; i++) { if (ndev->hci_dev->pipes[i].host == host) { ndev->hci_dev->pipes[i].gate = NCI_HCI_INVALID_GATE; ndev->hci_dev->pipes[i].host = NCI_HCI_INVALID_HOST; } } } /* Fragment HCI data over NCI packet. * NFC Forum NCI 10.2.2 Data Exchange: * The payload of the Data Packets sent on the Logical Connection SHALL be * valid HCP packets, as defined within [ETSI_102622]. Each Data Packet SHALL * contain a single HCP packet. NCI Segmentation and Reassembly SHALL NOT be * applied to Data Messages in either direction. The HCI fragmentation mechanism * is used if required. */ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, const u8 data_type, const u8 *data, size_t data_len) { const struct nci_conn_info *conn_info; struct sk_buff *skb; int len, i, r; u8 cb = pipe; conn_info = ndev->hci_dev->conn_info; if (!conn_info) return -EPROTO; i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; skb_reserve(skb, NCI_DATA_HDR_SIZE + 2); *(u8 *)skb_push(skb, 1) = data_type; do { /* If last packet add NCI_HFP_NO_CHAINING */ if (i + conn_info->max_pkt_payload_len - (skb->len + 1) >= data_len) { cb |= NCI_HFP_NO_CHAINING; len = data_len - i; } else { len = conn_info->max_pkt_payload_len - skb->len - 1; } *(u8 *)skb_push(skb, 1) = cb; if (len > 0) skb_put_data(skb, data + i, len); r = nci_send_data(ndev, conn_info->conn_id, skb); if (r < 0) return r; i += len; if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; skb_reserve(skb, NCI_DATA_HDR_SIZE + 1); } } while (i < data_len); return i; } static void nci_hci_send_data_req(struct nci_dev *ndev, const void *opt) { const struct nci_data *data = opt; nci_hci_send_data(ndev, data->pipe, data->cmd, data->data, data->data_len); } int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event, const u8 *param, size_t param_len) { u8 pipe = ndev->hci_dev->gate2pipe[gate]; if (pipe == NCI_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; return nci_hci_send_data(ndev, pipe, NCI_HCP_HEADER(NCI_HCI_HCP_EVENT, event), param, param_len); } EXPORT_SYMBOL(nci_hci_send_event); int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd, const u8 *param, size_t param_len, struct sk_buff **skb) { const struct nci_hcp_message *message; const struct nci_conn_info *conn_info; struct nci_data data; int r; u8 pipe = ndev->hci_dev->gate2pipe[gate]; if (pipe == NCI_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; conn_info = ndev->hci_dev->conn_info; if (!conn_info) return -EPROTO; data.conn_id = conn_info->conn_id; data.pipe = pipe; data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND, cmd); data.data = param; data.data_len = param_len; r = nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK) { message = (struct nci_hcp_message *)conn_info->rx_skb->data; r = nci_hci_result_to_errno( NCI_HCP_MSG_GET_CMD(message->header)); skb_pull(conn_info->rx_skb, NCI_HCI_HCP_MESSAGE_HEADER_LEN); if (!r && skb) *skb = conn_info->rx_skb; } return r; } EXPORT_SYMBOL(nci_hci_send_cmd); int nci_hci_clear_all_pipes(struct nci_dev *ndev) { int r; r = nci_hci_send_cmd(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADM_CLEAR_ALL_PIPE, NULL, 0, NULL); if (r < 0) return r; nci_hci_reset_pipes(ndev->hci_dev); return r; } EXPORT_SYMBOL(nci_hci_clear_all_pipes); static void nci_hci_event_received(struct nci_dev *ndev, u8 pipe, u8 event, struct sk_buff *skb) { if (ndev->ops->hci_event_received) ndev->ops->hci_event_received(ndev, pipe, event, skb); } static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb) { u8 gate = ndev->hci_dev->pipes[pipe].gate; u8 status = NCI_HCI_ANY_OK | ~NCI_HCI_FRAGMENT; u8 dest_gate, new_pipe; struct nci_hci_create_pipe_resp *create_info; struct nci_hci_delete_pipe_noti *delete_info; struct nci_hci_all_pipe_cleared_noti *cleared_info; pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd); switch (cmd) { case NCI_HCI_ADM_NOTIFY_PIPE_CREATED: if (skb->len != 5) { status = NCI_HCI_ANY_E_NOK; goto exit; } create_info = (struct nci_hci_create_pipe_resp *)skb->data; dest_gate = create_info->dest_gate; new_pipe = create_info->pipe; if (new_pipe >= NCI_HCI_MAX_PIPES) { status = NCI_HCI_ANY_E_NOK; goto exit; } /* Save the new created pipe and bind with local gate, * the description for skb->data[3] is destination gate id * but since we received this cmd from host controller, we * are the destination and it is our local gate */ ndev->hci_dev->gate2pipe[dest_gate] = new_pipe; ndev->hci_dev->pipes[new_pipe].gate = dest_gate; ndev->hci_dev->pipes[new_pipe].host = create_info->src_host; break; case NCI_HCI_ANY_OPEN_PIPE: /* If the pipe is not created report an error */ if (gate == NCI_HCI_INVALID_GATE) { status = NCI_HCI_ANY_E_NOK; goto exit; } break; case NCI_HCI_ADM_NOTIFY_PIPE_DELETED: if (skb->len != 1) { status = NCI_HCI_ANY_E_NOK; goto exit; } delete_info = (struct nci_hci_delete_pipe_noti *)skb->data; if (delete_info->pipe >= NCI_HCI_MAX_PIPES) { status = NCI_HCI_ANY_E_NOK; goto exit; } ndev->hci_dev->pipes[delete_info->pipe].gate = NCI_HCI_INVALID_GATE; ndev->hci_dev->pipes[delete_info->pipe].host = NCI_HCI_INVALID_HOST; break; case NCI_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED: if (skb->len != 1) { status = NCI_HCI_ANY_E_NOK; goto exit; } cleared_info = (struct nci_hci_all_pipe_cleared_noti *)skb->data; nci_hci_reset_pipes_per_host(ndev, cleared_info->host); break; default: pr_debug("Discarded unknown cmd %x to gate %x\n", cmd, gate); break; } if (ndev->ops->hci_cmd_received) ndev->ops->hci_cmd_received(ndev, pipe, cmd, skb); exit: nci_hci_send_data(ndev, pipe, status, NULL, 0); kfree_skb(skb); } static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe, struct sk_buff *skb) { struct nci_conn_info *conn_info; conn_info = ndev->hci_dev->conn_info; if (!conn_info) goto exit; conn_info->rx_skb = skb; exit: nci_req_complete(ndev, NCI_STATUS_OK); } /* Receive hcp message for pipe, with type and cmd. * skb contains optional message data only. */ static void nci_hci_hcp_message_rx(struct nci_dev *ndev, u8 pipe, u8 type, u8 instruction, struct sk_buff *skb) { switch (type) { case NCI_HCI_HCP_RESPONSE: nci_hci_resp_received(ndev, pipe, skb); break; case NCI_HCI_HCP_COMMAND: nci_hci_cmd_received(ndev, pipe, instruction, skb); break; case NCI_HCI_HCP_EVENT: nci_hci_event_received(ndev, pipe, instruction, skb); break; default: pr_err("UNKNOWN MSG Type %d, instruction=%d\n", type, instruction); kfree_skb(skb); break; } nci_req_complete(ndev, NCI_STATUS_OK); } static void nci_hci_msg_rx_work(struct work_struct *work) { struct nci_hci_dev *hdev = container_of(work, struct nci_hci_dev, msg_rx_work); struct sk_buff *skb; const struct nci_hcp_message *message; u8 pipe, type, instruction; for (; (skb = skb_dequeue(&hdev->msg_rx_queue)); kcov_remote_stop()) { kcov_remote_start_common(skb_get_kcov_handle(skb)); pipe = NCI_HCP_MSG_GET_PIPE(skb->data[0]); skb_pull(skb, NCI_HCI_HCP_PACKET_HEADER_LEN); message = (struct nci_hcp_message *)skb->data; type = NCI_HCP_MSG_GET_TYPE(message->header); instruction = NCI_HCP_MSG_GET_CMD(message->header); skb_pull(skb, NCI_HCI_HCP_MESSAGE_HEADER_LEN); nci_hci_hcp_message_rx(hdev->ndev, pipe, type, instruction, skb); } } void nci_hci_data_received_cb(void *context, struct sk_buff *skb, int err) { struct nci_dev *ndev = (struct nci_dev *)context; struct nci_hcp_packet *packet; u8 pipe, type; struct sk_buff *hcp_skb; struct sk_buff *frag_skb; int msg_len; if (err) { nci_req_complete(ndev, err); return; } packet = (struct nci_hcp_packet *)skb->data; if ((packet->header & ~NCI_HCI_FRAGMENT) == 0) { skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb); return; } /* it's the last fragment. Does it need re-aggregation? */ if (skb_queue_len(&ndev->hci_dev->rx_hcp_frags)) { pipe = NCI_HCP_MSG_GET_PIPE(packet->header); skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb); msg_len = 0; skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) { msg_len += (frag_skb->len - NCI_HCI_HCP_PACKET_HEADER_LEN); } hcp_skb = nfc_alloc_recv_skb(NCI_HCI_HCP_PACKET_HEADER_LEN + msg_len, GFP_KERNEL); if (!hcp_skb) { nci_req_complete(ndev, -ENOMEM); return; } skb_put_u8(hcp_skb, pipe); skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) { msg_len = frag_skb->len - NCI_HCI_HCP_PACKET_HEADER_LEN; skb_put_data(hcp_skb, frag_skb->data + NCI_HCI_HCP_PACKET_HEADER_LEN, msg_len); } skb_queue_purge(&ndev->hci_dev->rx_hcp_frags); } else { packet->header &= NCI_HCI_FRAGMENT; hcp_skb = skb; } /* if this is a response, dispatch immediately to * unblock waiting cmd context. Otherwise, enqueue to dispatch * in separate context where handler can also execute command. */ packet = (struct nci_hcp_packet *)hcp_skb->data; type = NCI_HCP_MSG_GET_TYPE(packet->message.header); if (type == NCI_HCI_HCP_RESPONSE) { pipe = NCI_HCP_MSG_GET_PIPE(packet->header); skb_pull(hcp_skb, NCI_HCI_HCP_PACKET_HEADER_LEN); nci_hci_hcp_message_rx(ndev, pipe, type, NCI_STATUS_OK, hcp_skb); } else { skb_queue_tail(&ndev->hci_dev->msg_rx_queue, hcp_skb); schedule_work(&ndev->hci_dev->msg_rx_work); } } int nci_hci_open_pipe(struct nci_dev *ndev, u8 pipe) { struct nci_data data; const struct nci_conn_info *conn_info; conn_info = ndev->hci_dev->conn_info; if (!conn_info) return -EPROTO; data.conn_id = conn_info->conn_id; data.pipe = pipe; data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND, NCI_HCI_ANY_OPEN_PIPE); data.data = NULL; data.data_len = 0; return nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); } EXPORT_SYMBOL(nci_hci_open_pipe); static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host, u8 dest_gate, int *result) { u8 pipe; struct sk_buff *skb; struct nci_hci_create_pipe_params params; const struct nci_hci_create_pipe_resp *resp; pr_debug("gate=%d\n", dest_gate); params.src_gate = NCI_HCI_ADMIN_GATE; params.dest_host = dest_host; params.dest_gate = dest_gate; *result = nci_hci_send_cmd(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADM_CREATE_PIPE, (u8 *)¶ms, sizeof(params), &skb); if (*result < 0) return NCI_HCI_INVALID_PIPE; resp = (struct nci_hci_create_pipe_resp *)skb->data; pipe = resp->pipe; kfree_skb(skb); pr_debug("pipe created=%d\n", pipe); if (pipe >= NCI_HCI_MAX_PIPES) pipe = NCI_HCI_INVALID_PIPE; return pipe; } static int nci_hci_delete_pipe(struct nci_dev *ndev, u8 pipe) { return nci_hci_send_cmd(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADM_DELETE_PIPE, &pipe, 1, NULL); } int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx, const u8 *param, size_t param_len) { const struct nci_hcp_message *message; const struct nci_conn_info *conn_info; struct nci_data data; int r; u8 *tmp; u8 pipe = ndev->hci_dev->gate2pipe[gate]; pr_debug("idx=%d to gate %d\n", idx, gate); if (pipe == NCI_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; conn_info = ndev->hci_dev->conn_info; if (!conn_info) return -EPROTO; tmp = kmalloc(1 + param_len, GFP_KERNEL); if (!tmp) return -ENOMEM; *tmp = idx; memcpy(tmp + 1, param, param_len); data.conn_id = conn_info->conn_id; data.pipe = pipe; data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND, NCI_HCI_ANY_SET_PARAMETER); data.data = tmp; data.data_len = param_len + 1; r = nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK) { message = (struct nci_hcp_message *)conn_info->rx_skb->data; r = nci_hci_result_to_errno( NCI_HCP_MSG_GET_CMD(message->header)); skb_pull(conn_info->rx_skb, NCI_HCI_HCP_MESSAGE_HEADER_LEN); } kfree(tmp); return r; } EXPORT_SYMBOL(nci_hci_set_param); int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx, struct sk_buff **skb) { const struct nci_hcp_message *message; const struct nci_conn_info *conn_info; struct nci_data data; int r; u8 pipe = ndev->hci_dev->gate2pipe[gate]; pr_debug("idx=%d to gate %d\n", idx, gate); if (pipe == NCI_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; conn_info = ndev->hci_dev->conn_info; if (!conn_info) return -EPROTO; data.conn_id = conn_info->conn_id; data.pipe = pipe; data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND, NCI_HCI_ANY_GET_PARAMETER); data.data = &idx; data.data_len = 1; r = nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK) { message = (struct nci_hcp_message *)conn_info->rx_skb->data; r = nci_hci_result_to_errno( NCI_HCP_MSG_GET_CMD(message->header)); skb_pull(conn_info->rx_skb, NCI_HCI_HCP_MESSAGE_HEADER_LEN); if (!r && skb) *skb = conn_info->rx_skb; } return r; } EXPORT_SYMBOL(nci_hci_get_param); int nci_hci_connect_gate(struct nci_dev *ndev, u8 dest_host, u8 dest_gate, u8 pipe) { bool pipe_created = false; int r; if (pipe == NCI_HCI_DO_NOT_OPEN_PIPE) return 0; if (ndev->hci_dev->gate2pipe[dest_gate] != NCI_HCI_INVALID_PIPE) return -EADDRINUSE; if (pipe != NCI_HCI_INVALID_PIPE) goto open_pipe; switch (dest_gate) { case NCI_HCI_LINK_MGMT_GATE: pipe = NCI_HCI_LINK_MGMT_PIPE; break; case NCI_HCI_ADMIN_GATE: pipe = NCI_HCI_ADMIN_PIPE; break; default: pipe = nci_hci_create_pipe(ndev, dest_host, dest_gate, &r); if (pipe == NCI_HCI_INVALID_PIPE) return r; pipe_created = true; break; } open_pipe: r = nci_hci_open_pipe(ndev, pipe); if (r < 0) { if (pipe_created) { if (nci_hci_delete_pipe(ndev, pipe) < 0) { /* TODO: Cannot clean by deleting pipe... * -> inconsistent state */ } } return r; } ndev->hci_dev->pipes[pipe].gate = dest_gate; ndev->hci_dev->pipes[pipe].host = dest_host; ndev->hci_dev->gate2pipe[dest_gate] = pipe; return 0; } EXPORT_SYMBOL(nci_hci_connect_gate); static int nci_hci_dev_connect_gates(struct nci_dev *ndev, u8 gate_count, const struct nci_hci_gate *gates) { int r; while (gate_count--) { r = nci_hci_connect_gate(ndev, gates->dest_host, gates->gate, gates->pipe); if (r < 0) return r; gates++; } return 0; } int nci_hci_dev_session_init(struct nci_dev *ndev) { struct nci_conn_info *conn_info; struct sk_buff *skb; int r; ndev->hci_dev->count_pipes = 0; ndev->hci_dev->expected_pipes = 0; conn_info = ndev->hci_dev->conn_info; if (!conn_info) return -EPROTO; conn_info->data_exchange_cb = nci_hci_data_received_cb; conn_info->data_exchange_cb_context = ndev; nci_hci_reset_pipes(ndev->hci_dev); if (ndev->hci_dev->init_data.gates[0].gate != NCI_HCI_ADMIN_GATE) return -EPROTO; r = nci_hci_connect_gate(ndev, ndev->hci_dev->init_data.gates[0].dest_host, ndev->hci_dev->init_data.gates[0].gate, ndev->hci_dev->init_data.gates[0].pipe); if (r < 0) return r; r = nci_hci_get_param(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY, &skb); if (r < 0) return r; if (skb->len && skb->len == strlen(ndev->hci_dev->init_data.session_id) && !memcmp(ndev->hci_dev->init_data.session_id, skb->data, skb->len) && ndev->ops->hci_load_session) { /* Restore gate<->pipe table from some proprietary location. */ r = ndev->ops->hci_load_session(ndev); } else { r = nci_hci_clear_all_pipes(ndev); if (r < 0) goto exit; r = nci_hci_dev_connect_gates(ndev, ndev->hci_dev->init_data.gate_count, ndev->hci_dev->init_data.gates); if (r < 0) goto exit; r = nci_hci_set_param(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY, ndev->hci_dev->init_data.session_id, strlen(ndev->hci_dev->init_data.session_id)); } exit: kfree_skb(skb); return r; } EXPORT_SYMBOL(nci_hci_dev_session_init); struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev) { struct nci_hci_dev *hdev; hdev = kzalloc(sizeof(*hdev), GFP_KERNEL); if (!hdev) return NULL; skb_queue_head_init(&hdev->rx_hcp_frags); INIT_WORK(&hdev->msg_rx_work, nci_hci_msg_rx_work); skb_queue_head_init(&hdev->msg_rx_queue); hdev->ndev = ndev; return hdev; } void nci_hci_deallocate(struct nci_dev *ndev) { kfree(ndev->hci_dev); } |
| 112 136 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_SEQADJ_H #define _NF_CONNTRACK_SEQADJ_H #include <net/netfilter/nf_conntrack_extend.h> /** * struct nf_ct_seqadj - sequence number adjustment information * * @correction_pos: position of the last TCP sequence number modification * @offset_before: sequence number offset before last modification * @offset_after: sequence number offset after last modification */ struct nf_ct_seqadj { u32 correction_pos; s32 offset_before; s32 offset_after; }; struct nf_conn_seqadj { struct nf_ct_seqadj seq[IP_CT_DIR_MAX]; }; static inline struct nf_conn_seqadj *nfct_seqadj(const struct nf_conn *ct) { return nf_ct_ext_find(ct, NF_CT_EXT_SEQADJ); } static inline struct nf_conn_seqadj *nfct_seqadj_ext_add(struct nf_conn *ct) { return nf_ct_ext_add(ct, NF_CT_EXT_SEQADJ, GFP_ATOMIC); } int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo, __be32 seq, s32 off); void nf_ct_tcp_seqadj_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); int nf_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int protoff); s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir, u32 seq); #endif /* _NF_CONNTRACK_SEQADJ_H */ |
| 8 12 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright 2006, Johannes Berg <johannes@sipsolutions.net> */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/leds.h> #include "ieee80211_i.h" #define MAC80211_BLINK_DELAY 50 /* ms */ static inline void ieee80211_led_rx(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_LEDS if (!atomic_read(&local->rx_led_active)) return; led_trigger_blink_oneshot(&local->rx_led, MAC80211_BLINK_DELAY, MAC80211_BLINK_DELAY, 0); #endif } static inline void ieee80211_led_tx(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_LEDS if (!atomic_read(&local->tx_led_active)) return; led_trigger_blink_oneshot(&local->tx_led, MAC80211_BLINK_DELAY, MAC80211_BLINK_DELAY, 0); #endif } #ifdef CONFIG_MAC80211_LEDS void ieee80211_led_assoc(struct ieee80211_local *local, bool associated); void ieee80211_led_radio(struct ieee80211_local *local, bool enabled); void ieee80211_alloc_led_names(struct ieee80211_local *local); void ieee80211_free_led_names(struct ieee80211_local *local); void ieee80211_led_init(struct ieee80211_local *local); void ieee80211_led_exit(struct ieee80211_local *local); void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, unsigned int types_on, unsigned int types_off); #else static inline void ieee80211_led_assoc(struct ieee80211_local *local, bool associated) { } static inline void ieee80211_led_radio(struct ieee80211_local *local, bool enabled) { } static inline void ieee80211_alloc_led_names(struct ieee80211_local *local) { } static inline void ieee80211_free_led_names(struct ieee80211_local *local) { } static inline void ieee80211_led_init(struct ieee80211_local *local) { } static inline void ieee80211_led_exit(struct ieee80211_local *local) { } static inline void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, unsigned int types_on, unsigned int types_off) { } #endif static inline void ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, int bytes) { #ifdef CONFIG_MAC80211_LEDS if (atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->tx_bytes += bytes; #endif } static inline void ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, int bytes) { #ifdef CONFIG_MAC80211_LEDS if (atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->rx_bytes += bytes; #endif } |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DEVICE_DEVRES_H_ #define _DEVICE_DEVRES_H_ #include <linux/err.h> #include <linux/gfp_types.h> #include <linux/numa.h> #include <linux/overflow.h> #include <linux/stdarg.h> #include <linux/types.h> #include <asm/bug.h> struct device; struct device_node; struct resource; /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); void * __malloc __devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name); #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void * __alloc_size(2) devm_kmalloc(struct device *dev, size_t size, gfp_t gfp); void * __must_check __realloc_size(3) devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp); static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } static inline __realloc_size(3, 4) void * __must_check devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return devm_krealloc(dev, p, bytes, flags); } void devm_kfree(struct device *dev, const void *p); void * __realloc_size(3) devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); const void * devm_kmemdup_const(struct device *dev, const void *src, size_t len, gfp_t gfp); static inline void *devm_kmemdup_array(struct device *dev, const void *src, size_t n, size_t size, gfp_t flags) { return devm_kmemdup(dev, src, size_mul(size, n), flags); } char * __malloc devm_kstrdup(struct device *dev, const char *s, gfp_t gfp); const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); char * __printf(3, 0) __malloc devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap); char * __printf(3, 4) __malloc devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); #ifdef CONFIG_HAS_IOMEM void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); #else static inline void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) { return IOMEM_ERR_PTR(-EINVAL); } static inline void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) { return IOMEM_ERR_PTR(-EINVAL); } static inline void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size) { return IOMEM_ERR_PTR(-EINVAL); } #endif /* allows to add/remove a custom action to devres stack */ int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data); /** * devm_remove_action() - removes previously added custom action * @dev: Device that owns the action * @action: Function implementing the action * @data: Pointer to data passed to @action implementation * * Removes instance of @action previously added by devm_add_action(). * Both action and data should match one of the existing entries. */ static inline void devm_remove_action(struct device *dev, void (*action)(void *), void *data) { WARN_ON(devm_remove_action_nowarn(dev, action, data)); } void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); #define devm_add_action(dev, action, data) \ __devm_add_action(dev, action, data, #action) static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data, const char *name) { int ret; ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } #define devm_add_action_or_reset(dev, action, data) \ __devm_add_action_or_reset(dev, action, data, #action) bool devm_is_action_added(struct device *dev, void (*action)(void *), void *data); #endif /* _DEVICE_DEVRES_H_ */ |
| 22 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions related to Power Management Quality of Service (PM QoS). * * Copyright (C) 2020 Intel Corporation * * Authors: * Mark Gross <mgross@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> */ #ifndef _LINUX_PM_QOS_H #define _LINUX_PM_QOS_H #include <linux/plist.h> #include <linux/notifier.h> #include <linux/device.h> enum pm_qos_flags_status { PM_QOS_FLAGS_UNDEFINED = -1, PM_QOS_FLAGS_NONE, PM_QOS_FLAGS_SOME, PM_QOS_FLAGS_ALL, }; #define PM_QOS_DEFAULT_VALUE (-1) #define PM_QOS_LATENCY_ANY S32_MAX #define PM_QOS_LATENCY_ANY_NS ((s64)PM_QOS_LATENCY_ANY * NSEC_PER_USEC) #define PM_QOS_CPU_LATENCY_DEFAULT_VALUE (2000 * USEC_PER_SEC) #define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 #define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 #define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE FREQ_QOS_MAX_DEFAULT_VALUE #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) enum pm_qos_type { PM_QOS_UNITIALIZED, PM_QOS_MAX, /* return the largest value */ PM_QOS_MIN, /* return the smallest value */ }; /* * Note: The lockless read path depends on the CPU accessing target_value * or effective_flags atomically. Atomic access is only guaranteed on all CPU * types linux supports for 32 bit quantites */ struct pm_qos_constraints { struct plist_head list; s32 target_value; /* Do not change to 64 bit */ s32 default_value; s32 no_constraint_value; enum pm_qos_type type; struct blocking_notifier_head *notifiers; }; struct pm_qos_request { struct plist_node node; struct pm_qos_constraints *qos; }; struct pm_qos_flags_request { struct list_head node; s32 flags; /* Do not change to 64 bit */ }; struct pm_qos_flags { struct list_head list; s32 effective_flags; /* Do not change to 64 bit */ }; #define FREQ_QOS_MIN_DEFAULT_VALUE 0 #define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX enum freq_qos_req_type { FREQ_QOS_MIN = 1, FREQ_QOS_MAX, }; struct freq_constraints { struct pm_qos_constraints min_freq; struct blocking_notifier_head min_freq_notifiers; struct pm_qos_constraints max_freq; struct blocking_notifier_head max_freq_notifiers; }; struct freq_qos_request { enum freq_qos_req_type type; struct plist_node pnode; struct freq_constraints *qos; }; enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, DEV_PM_QOS_MIN_FREQUENCY, DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; struct dev_pm_qos_request { enum dev_pm_qos_req_type type; union { struct plist_node pnode; struct pm_qos_flags_request flr; struct freq_qos_request freq; } data; struct device *dev; }; struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; struct freq_constraints freq; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; struct dev_pm_qos_request *flags_req; }; /* Action requested to pm_qos_update_target */ enum pm_qos_req_action { PM_QOS_ADD_REQ, /* Add a new request */ PM_QOS_UPDATE_REQ, /* Update an existing request */ PM_QOS_REMOVE_REQ /* Remove an existing request */ }; static inline int dev_pm_qos_request_active(struct dev_pm_qos_request *req) { return req->dev != NULL; } s32 pm_qos_read_value(struct pm_qos_constraints *c); int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, enum pm_qos_req_action action, int value); bool pm_qos_update_flags(struct pm_qos_flags *pqf, struct pm_qos_flags_request *req, enum pm_qos_req_action action, s32 val); #ifdef CONFIG_CPU_IDLE s32 cpu_latency_qos_limit(void); bool cpu_latency_qos_request_active(struct pm_qos_request *req); void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value); void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value); void cpu_latency_qos_remove_request(struct pm_qos_request *req); #else static inline s32 cpu_latency_qos_limit(void) { return INT_MAX; } static inline bool cpu_latency_qos_request_active(struct pm_qos_request *req) { return false; } static inline void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value) {} static inline void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value) {} static inline void cpu_latency_qos_remove_request(struct pm_qos_request *req) {} #endif #ifdef CONFIG_PM enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask); enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask); s32 __dev_pm_qos_resume_latency(struct device *dev); s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type); int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value); int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value); int dev_pm_qos_remove_request(struct dev_pm_qos_request *req); int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type); int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type); void dev_pm_qos_constraints_init(struct device *dev); void dev_pm_qos_constraints_destroy(struct device *dev); int dev_pm_qos_add_ancestor_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value); int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value); void dev_pm_qos_hide_latency_limit(struct device *dev); int dev_pm_qos_expose_flags(struct device *dev, s32 value); void dev_pm_qos_hide_flags(struct device *dev); int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set); s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev); int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val); int dev_pm_qos_expose_latency_tolerance(struct device *dev); void dev_pm_qos_hide_latency_tolerance(struct device *dev); static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return dev->power.qos->resume_latency_req->data.pnode.prio; } static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return dev->power.qos->flags_req->data.flr.flags; } static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) { return IS_ERR_OR_NULL(dev->power.qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&dev->power.qos->resume_latency); } #else static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) { return PM_QOS_FLAGS_UNDEFINED; } static inline enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) { return PM_QOS_FLAGS_UNDEFINED; } static inline s32 __dev_pm_qos_resume_latency(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } static inline s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) { switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; case DEV_PM_QOS_MIN_FREQUENCY: return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; case DEV_PM_QOS_MAX_FREQUENCY: return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; } } static inline int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { return 0; } static inline int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { return 0; } static inline int dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { return 0; } static inline int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { return 0; } static inline int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { return 0; } static inline void dev_pm_qos_constraints_init(struct device *dev) { dev->power.power_state = PMSG_ON; } static inline void dev_pm_qos_constraints_destroy(struct device *dev) { dev->power.power_state = PMSG_INVALID; } static inline int dev_pm_qos_add_ancestor_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { return 0; } static inline int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value) { return 0; } static inline void dev_pm_qos_hide_latency_limit(struct device *dev) {} static inline int dev_pm_qos_expose_flags(struct device *dev, s32 value) { return 0; } static inline void dev_pm_qos_hide_flags(struct device *dev) {} static inline int dev_pm_qos_update_flags(struct device *dev, s32 m, bool set) { return 0; } static inline s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev) { return PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; } static inline int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) { return 0; } static inline int dev_pm_qos_expose_latency_tolerance(struct device *dev) { return 0; } static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {} static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; } static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } #endif static inline int freq_qos_request_active(struct freq_qos_request *req) { return !IS_ERR_OR_NULL(req->qos); } void freq_constraints_init(struct freq_constraints *qos); s32 freq_qos_read_value(struct freq_constraints *qos, enum freq_qos_req_type type); int freq_qos_add_request(struct freq_constraints *qos, struct freq_qos_request *req, enum freq_qos_req_type type, s32 value); int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); int freq_qos_remove_request(struct freq_qos_request *req); int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value); int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, struct notifier_block *notifier); int freq_qos_remove_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, struct notifier_block *notifier); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/wireless/sysfs.c */ #include <linux/device.h> #include <linux/rtnetlink.h> #include <net/cfg802154.h> #include "core.h" #include "sysfs.h" #include "rdev-ops.h" static inline struct cfg802154_registered_device * dev_to_rdev(struct device *dev) { return container_of(dev, struct cfg802154_registered_device, wpan_phy.dev); } #define SHOW_FMT(name, fmt, member) \ static ssize_t name ## _show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ return sprintf(buf, fmt "\n", dev_to_rdev(dev)->member); \ } \ static DEVICE_ATTR_RO(name) SHOW_FMT(index, "%d", wpan_phy_idx); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wpan_phy *wpan_phy = &dev_to_rdev(dev)->wpan_phy; return sprintf(buf, "%s\n", dev_name(&wpan_phy->dev)); } static DEVICE_ATTR_RO(name); static void wpan_phy_release(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); cfg802154_dev_free(rdev); } static struct attribute *pmib_attrs[] = { &dev_attr_index.attr, &dev_attr_name.attr, NULL, }; ATTRIBUTE_GROUPS(pmib); #ifdef CONFIG_PM_SLEEP static int wpan_phy_suspend(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); int ret = 0; if (rdev->ops->suspend) { rtnl_lock(); ret = rdev_suspend(rdev); rtnl_unlock(); } return ret; } static int wpan_phy_resume(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); int ret = 0; if (rdev->ops->resume) { rtnl_lock(); ret = rdev_resume(rdev); rtnl_unlock(); } return ret; } static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume); #define WPAN_PHY_PM_OPS (&wpan_phy_pm_ops) #else #define WPAN_PHY_PM_OPS NULL #endif const struct class wpan_phy_class = { .name = "ieee802154", .dev_release = wpan_phy_release, .dev_groups = pmib_groups, .pm = WPAN_PHY_PM_OPS, }; int wpan_phy_sysfs_init(void) { return class_register(&wpan_phy_class); } void wpan_phy_sysfs_exit(void) { class_unregister(&wpan_phy_class); } |
| 6 6 4 4 6 5 2 5 2 5 1 5 1 5 5 6 2 1 2 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * inode.c - basic inode and dentry operations. * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. * * Please see Documentation/filesystems/configfs.rst for more * information. */ #undef DEBUG #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/sched.h> #include <linux/lockdep.h> #include <linux/slab.h> #include <linux/configfs.h> #include "configfs_internal.h" #ifdef CONFIG_LOCKDEP static struct lock_class_key default_group_class[MAX_LOCK_DEPTH]; #endif static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode * inode = d_inode(dentry); struct configfs_dirent * sd = dentry->d_fsdata; struct iattr * sd_iattr; unsigned int ia_valid = iattr->ia_valid; int error; if (!sd) return -EINVAL; sd_iattr = sd->s_iattr; if (!sd_iattr) { /* setting attributes for the first time, allocate now */ sd_iattr = kzalloc(sizeof(struct iattr), GFP_KERNEL); if (!sd_iattr) return -ENOMEM; /* assign default attributes */ sd_iattr->ia_mode = sd->s_mode; sd_iattr->ia_uid = GLOBAL_ROOT_UID; sd_iattr->ia_gid = GLOBAL_ROOT_GID; sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = current_time(inode); sd->s_iattr = sd_iattr; } /* attributes were changed atleast once in past */ error = simple_setattr(idmap, dentry, iattr); if (error) return error; if (ia_valid & ATTR_UID) sd_iattr->ia_uid = iattr->ia_uid; if (ia_valid & ATTR_GID) sd_iattr->ia_gid = iattr->ia_gid; if (ia_valid & ATTR_ATIME) sd_iattr->ia_atime = iattr->ia_atime; if (ia_valid & ATTR_MTIME) sd_iattr->ia_mtime = iattr->ia_mtime; if (ia_valid & ATTR_CTIME) sd_iattr->ia_ctime = iattr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = iattr->ia_mode; if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) mode &= ~S_ISGID; sd_iattr->ia_mode = sd->s_mode = mode; } return error; } static inline void set_default_inode_attr(struct inode * inode, umode_t mode) { inode->i_mode = mode; simple_inode_init_ts(inode); } static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) { inode->i_mode = iattr->ia_mode; inode->i_uid = iattr->ia_uid; inode->i_gid = iattr->ia_gid; inode_set_atime_to_ts(inode, iattr->ia_atime); inode_set_mtime_to_ts(inode, iattr->ia_mtime); inode_set_ctime_to_ts(inode, iattr->ia_ctime); } struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, struct super_block *s) { struct inode * inode = new_inode(s); if (inode) { inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &ram_aops; inode->i_op = &configfs_inode_operations; if (sd->s_iattr) { /* sysfs_dirent has non-default attributes * get them for the new inode from persistent copy * in sysfs_dirent */ set_inode_attr(inode, sd->s_iattr); } else set_default_inode_attr(inode, mode); } return inode; } #ifdef CONFIG_LOCKDEP static void configfs_set_inode_lock_class(struct configfs_dirent *sd, struct inode *inode) { int depth = sd->s_depth; if (depth > 0) { if (depth <= ARRAY_SIZE(default_group_class)) { lockdep_set_class(&inode->i_rwsem, &default_group_class[depth - 1]); } else { /* * In practice the maximum level of locking depth is * already reached. Just inform about possible reasons. */ pr_info("Too many levels of inodes for the locking correctness validator.\n"); pr_info("Spurious warnings may appear.\n"); } } } #else /* CONFIG_LOCKDEP */ static void configfs_set_inode_lock_class(struct configfs_dirent *sd, struct inode *inode) { } #endif /* CONFIG_LOCKDEP */ struct inode *configfs_create(struct dentry *dentry, umode_t mode) { struct inode *inode = NULL; struct configfs_dirent *sd; struct inode *p_inode; if (!dentry) return ERR_PTR(-ENOENT); if (d_really_is_positive(dentry)) return ERR_PTR(-EEXIST); sd = dentry->d_fsdata; inode = configfs_new_inode(mode, sd, dentry->d_sb); if (!inode) return ERR_PTR(-ENOMEM); p_inode = d_inode(dentry->d_parent); inode_set_mtime_to_ts(p_inode, inode_set_ctime_current(p_inode)); configfs_set_inode_lock_class(sd, inode); return inode; } /* * Get the name for corresponding element represented by the given configfs_dirent */ const unsigned char * configfs_get_name(struct configfs_dirent *sd) { struct configfs_attribute *attr; BUG_ON(!sd || !sd->s_element); /* These always have a dentry, so use that */ if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) return sd->s_dentry->d_name.name; if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) { attr = sd->s_element; return attr->ca_name; } return NULL; } /* * Unhashes the dentry corresponding to given configfs_dirent * Called with parent inode's i_mutex held. */ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent) { struct dentry * dentry = sd->s_dentry; if (dentry) { spin_lock(&dentry->d_lock); if (simple_positive(dentry)) { dget_dlock(dentry); __d_drop(dentry); spin_unlock(&dentry->d_lock); simple_unlink(d_inode(parent), dentry); } else spin_unlock(&dentry->d_lock); } } |
| 175 9 9 4 4 3 3 3 3 3 8 175 32 27 20 20 20 19 18 9 9 10 10 31 11 4 31 11 2 11 12 12 12 12 2 2 2 2 12 10 10 11 11 11 11 2 31 31 31 31 1 2 28 28 13 11 27 27 10 2 13 12 2 21 28 31 14 14 13 14 470 25 25 25 23 23 23 23 23 23 23 3 3 320 320 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * This module enables kernel and guest-mode vCPU access to guest physical * memory with suitable invalidation mechanisms. * * Copyright © 2021 Amazon.com, Inc. or its affiliates. * * Authors: * David Woodhouse <dwmw2@infradead.org> */ #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/highmem.h> #include <linux/module.h> #include <linux/errno.h> #include "kvm_mm.h" /* * MMU notifier 'invalidate_range_start' hook. */ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, unsigned long end) { struct gfn_to_pfn_cache *gpc; spin_lock(&kvm->gpc_lock); list_for_each_entry(gpc, &kvm->gpc_list, list) { read_lock_irq(&gpc->lock); /* Only a single page so no need to care about length */ if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) && gpc->uhva >= start && gpc->uhva < end) { read_unlock_irq(&gpc->lock); /* * There is a small window here where the cache could * be modified, and invalidation would no longer be * necessary. Hence check again whether invalidation * is still necessary once the write lock has been * acquired. */ write_lock_irq(&gpc->lock); if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) && gpc->uhva >= start && gpc->uhva < end) gpc->valid = false; write_unlock_irq(&gpc->lock); continue; } read_unlock_irq(&gpc->lock); } spin_unlock(&kvm->gpc_lock); } static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva, unsigned long len) { unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : offset_in_page(gpa); /* * The cached access must fit within a single page. The 'len' argument * to activate() and refresh() exists only to enforce that. */ return offset + len <= PAGE_SIZE; } bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(gpc->kvm); if (!gpc->active) return false; /* * If the page was cached from a memslot, make sure the memslots have * not been re-configured. */ if (!kvm_is_error_gpa(gpc->gpa) && gpc->generation != slots->generation) return false; if (kvm_is_error_hva(gpc->uhva)) return false; if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) return false; if (!gpc->valid) return false; return true; } static void *gpc_map(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return kmap(pfn_to_page(pfn)); #ifdef CONFIG_HAS_IOMEM return memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #else return NULL; #endif } static void gpc_unmap(kvm_pfn_t pfn, void *khva) { /* Unmap the old pfn/page if it was mapped before. */ if (is_error_noslot_pfn(pfn) || !khva) return; if (pfn_valid(pfn)) { kunmap(pfn_to_page(pfn)); return; } #ifdef CONFIG_HAS_IOMEM memunmap(khva); #endif } static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq) { /* * mn_active_invalidate_count acts for all intents and purposes * like mmu_invalidate_in_progress here; but the latter cannot * be used here because the invalidation of caches in the * mmu_notifier event occurs _before_ mmu_invalidate_in_progress * is elevated. * * Note, it does not matter that mn_active_invalidate_count * is not protected by gpc->lock. It is guaranteed to * be elevated before the mmu_notifier acquires gpc->lock, and * isn't dropped until after mmu_invalidate_seq is updated. */ if (kvm->mn_active_invalidate_count) return true; /* * Ensure mn_active_invalidate_count is read before * mmu_invalidate_seq. This pairs with the smp_wmb() in * mmu_notifier_invalidate_range_end() to guarantee either the * old (non-zero) value of mn_active_invalidate_count or the * new (incremented) value of mmu_invalidate_seq is observed. */ smp_rmb(); return kvm->mmu_invalidate_seq != mmu_seq; } static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc) { /* Note, the new page offset may be different than the old! */ void *old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva); kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT; void *new_khva = NULL; unsigned long mmu_seq; struct page *page; struct kvm_follow_pfn kfp = { .slot = gpc->memslot, .gfn = gpa_to_gfn(gpc->gpa), .flags = FOLL_WRITE, .hva = gpc->uhva, .refcounted_page = &page, }; lockdep_assert_held(&gpc->refresh_lock); lockdep_assert_held_write(&gpc->lock); /* * Invalidate the cache prior to dropping gpc->lock, the gpa=>uhva * assets have already been updated and so a concurrent check() from a * different task may not fail the gpa/uhva/generation checks. */ gpc->valid = false; do { mmu_seq = gpc->kvm->mmu_invalidate_seq; smp_rmb(); write_unlock_irq(&gpc->lock); /* * If the previous iteration "failed" due to an mmu_notifier * event, release the pfn and unmap the kernel virtual address * from the previous attempt. Unmapping might sleep, so this * needs to be done after dropping the lock. Opportunistically * check for resched while the lock isn't held. */ if (new_pfn != KVM_PFN_ERR_FAULT) { /* * Keep the mapping if the previous iteration reused * the existing mapping and didn't create a new one. */ if (new_khva != old_khva) gpc_unmap(new_pfn, new_khva); kvm_release_page_unused(page); cond_resched(); } new_pfn = hva_to_pfn(&kfp); if (is_error_noslot_pfn(new_pfn)) goto out_error; /* * Obtain a new kernel mapping if KVM itself will access the * pfn. Note, kmap() and memremap() can both sleep, so this * too must be done outside of gpc->lock! */ if (new_pfn == gpc->pfn) new_khva = old_khva; else new_khva = gpc_map(new_pfn); if (!new_khva) { kvm_release_page_unused(page); goto out_error; } write_lock_irq(&gpc->lock); /* * Other tasks must wait for _this_ refresh to complete before * attempting to refresh. */ WARN_ON_ONCE(gpc->valid); } while (mmu_notifier_retry_cache(gpc->kvm, mmu_seq)); gpc->valid = true; gpc->pfn = new_pfn; gpc->khva = new_khva + offset_in_page(gpc->uhva); /* * Put the reference to the _new_ page. The page is now tracked by the * cache and can be safely migrated, swapped, etc... as the cache will * invalidate any mappings in response to relevant mmu_notifier events. */ kvm_release_page_clean(page); return 0; out_error: write_lock_irq(&gpc->lock); return -EFAULT; } static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva) { unsigned long page_offset; bool unmap_old = false; unsigned long old_uhva; kvm_pfn_t old_pfn; bool hva_change = false; void *old_khva; int ret; /* Either gpa or uhva must be valid, but not both */ if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva))) return -EINVAL; lockdep_assert_held(&gpc->refresh_lock); write_lock_irq(&gpc->lock); if (!gpc->active) { ret = -EINVAL; goto out_unlock; } old_pfn = gpc->pfn; old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva); old_uhva = PAGE_ALIGN_DOWN(gpc->uhva); if (kvm_is_error_gpa(gpa)) { page_offset = offset_in_page(uhva); gpc->gpa = INVALID_GPA; gpc->memslot = NULL; gpc->uhva = PAGE_ALIGN_DOWN(uhva); if (gpc->uhva != old_uhva) hva_change = true; } else { struct kvm_memslots *slots = kvm_memslots(gpc->kvm); page_offset = offset_in_page(gpa); if (gpc->gpa != gpa || gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva)) { gfn_t gfn = gpa_to_gfn(gpa); gpc->gpa = gpa; gpc->generation = slots->generation; gpc->memslot = __gfn_to_memslot(slots, gfn); gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn); if (kvm_is_error_hva(gpc->uhva)) { ret = -EFAULT; goto out; } /* * Even if the GPA and/or the memslot generation changed, the * HVA may still be the same. */ if (gpc->uhva != old_uhva) hva_change = true; } else { gpc->uhva = old_uhva; } } /* Note: the offset must be correct before calling hva_to_pfn_retry() */ gpc->uhva += page_offset; /* * If the userspace HVA changed or the PFN was already invalid, * drop the lock and do the HVA to PFN lookup again. */ if (!gpc->valid || hva_change) { ret = hva_to_pfn_retry(gpc); } else { /* * If the HVA→PFN mapping was already valid, don't unmap it. * But do update gpc->khva because the offset within the page * may have changed. */ gpc->khva = old_khva + page_offset; ret = 0; goto out_unlock; } out: /* * Invalidate the cache and purge the pfn/khva if the refresh failed. * Some/all of the uhva, gpa, and memslot generation info may still be * valid, leave it as is. */ if (ret) { gpc->valid = false; gpc->pfn = KVM_PFN_ERR_FAULT; gpc->khva = NULL; } /* Detect a pfn change before dropping the lock! */ unmap_old = (old_pfn != gpc->pfn); out_unlock: write_unlock_irq(&gpc->lock); if (unmap_old) gpc_unmap(old_pfn, old_khva); return ret; } int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) { unsigned long uhva; guard(mutex)(&gpc->refresh_lock); if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) return -EINVAL; /* * If the GPA is valid then ignore the HVA, as a cache can be GPA-based * or HVA-based, not both. For GPA-based caches, the HVA will be * recomputed during refresh if necessary. */ uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD; return __kvm_gpc_refresh(gpc, gpc->gpa, uhva); } void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) { rwlock_init(&gpc->lock); mutex_init(&gpc->refresh_lock); gpc->kvm = kvm; gpc->pfn = KVM_PFN_ERR_FAULT; gpc->gpa = INVALID_GPA; gpc->uhva = KVM_HVA_ERR_BAD; gpc->active = gpc->valid = false; } static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva, unsigned long len) { struct kvm *kvm = gpc->kvm; if (!kvm_gpc_is_valid_len(gpa, uhva, len)) return -EINVAL; guard(mutex)(&gpc->refresh_lock); if (!gpc->active) { if (KVM_BUG_ON(gpc->valid, kvm)) return -EIO; spin_lock(&kvm->gpc_lock); list_add(&gpc->list, &kvm->gpc_list); spin_unlock(&kvm->gpc_lock); /* * Activate the cache after adding it to the list, a concurrent * refresh must not establish a mapping until the cache is * reachable by mmu_notifier events. */ write_lock_irq(&gpc->lock); gpc->active = true; write_unlock_irq(&gpc->lock); } return __kvm_gpc_refresh(gpc, gpa, uhva); } int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) { /* * Explicitly disallow INVALID_GPA so that the magic value can be used * by KVM to differentiate between GPA-based and HVA-based caches. */ if (WARN_ON_ONCE(kvm_is_error_gpa(gpa))) return -EINVAL; return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len); } int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long uhva, unsigned long len) { if (!access_ok((void __user *)uhva, len)) return -EINVAL; return __kvm_gpc_activate(gpc, INVALID_GPA, uhva, len); } void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc) { struct kvm *kvm = gpc->kvm; kvm_pfn_t old_pfn; void *old_khva; guard(mutex)(&gpc->refresh_lock); if (gpc->active) { /* * Deactivate the cache before removing it from the list, KVM * must stall mmu_notifier events until all users go away, i.e. * until gpc->lock is dropped and refresh is guaranteed to fail. */ write_lock_irq(&gpc->lock); gpc->active = false; gpc->valid = false; /* * Leave the GPA => uHVA cache intact, it's protected by the * memslot generation. The PFN lookup needs to be redone every * time as mmu_notifier protection is lost when the cache is * removed from the VM's gpc_list. */ old_khva = gpc->khva - offset_in_page(gpc->khva); gpc->khva = NULL; old_pfn = gpc->pfn; gpc->pfn = KVM_PFN_ERR_FAULT; write_unlock_irq(&gpc->lock); spin_lock(&kvm->gpc_lock); list_del(&gpc->list); spin_unlock(&kvm->gpc_lock); gpc_unmap(old_pfn, old_khva); } } |
| 12 16 15 14 20 20 21 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright (C) Jonathan Naylor G4KLX (g4klx@g4klx.demon.co.uk) * Copyright (C) 2002 Ralf Baechle DO1GRB (ralf@gnu.org) */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/tcp_states.h> #include <linux/uaccess.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <net/netrom.h> static void nr_heartbeat_expiry(struct timer_list *); static void nr_t1timer_expiry(struct timer_list *); static void nr_t2timer_expiry(struct timer_list *); static void nr_t4timer_expiry(struct timer_list *); static void nr_idletimer_expiry(struct timer_list *); void nr_init_timers(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); timer_setup(&nr->t1timer, nr_t1timer_expiry, 0); timer_setup(&nr->t2timer, nr_t2timer_expiry, 0); timer_setup(&nr->t4timer, nr_t4timer_expiry, 0); timer_setup(&nr->idletimer, nr_idletimer_expiry, 0); /* initialized by sock_init_data */ sk->sk_timer.function = nr_heartbeat_expiry; } void nr_start_t1timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1); } void nr_start_t2timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2); } void nr_start_t4timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4); } void nr_start_idletimer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); if (nr->idle > 0) sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle); } void nr_start_heartbeat(struct sock *sk) { sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void nr_stop_t1timer(struct sock *sk) { sk_stop_timer(sk, &nr_sk(sk)->t1timer); } void nr_stop_t2timer(struct sock *sk) { sk_stop_timer(sk, &nr_sk(sk)->t2timer); } void nr_stop_t4timer(struct sock *sk) { sk_stop_timer(sk, &nr_sk(sk)->t4timer); } void nr_stop_idletimer(struct sock *sk) { sk_stop_timer(sk, &nr_sk(sk)->idletimer); } void nr_stop_heartbeat(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); } int nr_t1timer_running(struct sock *sk) { return timer_pending(&nr_sk(sk)->t1timer); } static void nr_heartbeat_expiry(struct timer_list *t) { struct sock *sk = timer_container_of(sk, t, sk_timer); struct nr_sock *nr = nr_sk(sk); bh_lock_sock(sk); switch (nr->state) { case NR_STATE_0: /* Magic here: If we listen() and a new link dies before it is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { if (sk->sk_state == TCP_LISTEN) sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; } break; case NR_STATE_3: /* * Check for the state of the receive buffer. */ if (atomic_read(&sk->sk_rmem_alloc) < (sk->sk_rcvbuf / 2) && (nr->condition & NR_COND_OWN_RX_BUSY)) { nr->condition &= ~NR_COND_OWN_RX_BUSY; nr->condition &= ~NR_COND_ACK_PENDING; nr->vl = nr->vr; nr_write_internal(sk, NR_INFOACK); break; } break; } nr_start_heartbeat(sk); bh_unlock_sock(sk); out: sock_put(sk); } static void nr_t2timer_expiry(struct timer_list *t) { struct nr_sock *nr = timer_container_of(nr, t, t2timer); struct sock *sk = &nr->sock; bh_lock_sock(sk); if (nr->condition & NR_COND_ACK_PENDING) { nr->condition &= ~NR_COND_ACK_PENDING; nr_enquiry_response(sk); } bh_unlock_sock(sk); sock_put(sk); } static void nr_t4timer_expiry(struct timer_list *t) { struct nr_sock *nr = timer_container_of(nr, t, t4timer); struct sock *sk = &nr->sock; bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); sock_put(sk); } static void nr_idletimer_expiry(struct timer_list *t) { struct nr_sock *nr = timer_container_of(nr, t, idletimer); struct sock *sk = &nr->sock; bh_lock_sock(sk); nr_clear_queues(sk); nr->n2count = 0; nr_write_internal(sk, NR_DISCREQ); nr->state = NR_STATE_2; nr_start_t1timer(sk); nr_stop_t2timer(sk); nr_stop_t4timer(sk); sk->sk_state = TCP_CLOSE; sk->sk_err = 0; sk->sk_shutdown |= SEND_SHUTDOWN; if (!sock_flag(sk, SOCK_DEAD)) { sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); sock_put(sk); } static void nr_t1timer_expiry(struct timer_list *t) { struct nr_sock *nr = timer_container_of(nr, t, t1timer); struct sock *sk = &nr->sock; bh_lock_sock(sk); switch (nr->state) { case NR_STATE_1: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); goto out; } else { nr->n2count++; nr_write_internal(sk, NR_CONNREQ); } break; case NR_STATE_2: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); goto out; } else { nr->n2count++; nr_write_internal(sk, NR_DISCREQ); } break; case NR_STATE_3: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); goto out; } else { nr->n2count++; nr_requeue_frames(sk); } break; } nr_start_t1timer(sk); out: bh_unlock_sock(sk); sock_put(sk); } |
| 4 29 29 29 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/prandom.h * * Include file for the fast pseudo-random 32-bit * generation. */ #ifndef _LINUX_PRANDOM_H #define _LINUX_PRANDOM_H #include <linux/types.h> #include <linux/once.h> #include <linux/percpu.h> #include <linux/random.h> struct rnd_state { __u32 s1, s2, s3, s4; }; u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); #define prandom_init_once(pcpu_state) \ DO_ONCE(prandom_seed_full_state, (pcpu_state)) /* * Handle minimum values for seeds */ static inline u32 __seed(u32 x, u32 m) { return (x < m) ? x + m : x; } /** * prandom_seed_state - set seed for prandom_u32_state(). * @state: pointer to state structure to receive the seed. * @seed: arbitrary 64-bit value to use as a seed. */ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { u32 i = ((seed >> 32) ^ (seed << 10) ^ seed) & 0xffffffffUL; state->s1 = __seed(i, 2U); state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); } /* Pseudo random number generator from numerical recipes. */ static inline u32 next_pseudo_random32(u32 seed) { return seed * 1664525 + 1013904223; } #endif |
| 19 49 13 8 91 5 26 18781 68 36 5 1562 130 126 16 11 1167 958 929 81 633 82 235 1356 71 18 732 44 12 41 47 294 62 551 22 49 39 120 40 90 9 77 7261 810 574 608 61 162 53 387 62 87 219 41 1363 5714 597 237 253 225 241 82 135 28 38 38 18 137 637 4 44 3 72 51 11 2216 7380 8397 8 10699 1835 1631 137 119 299 69 34 3421 3054 263 987 6 1178 541 45 1 38 33 99 62 26 9 1 25 25 28 8 43 85 22 17 94 388 10 116 72 14 30 29 21 49 1 42 31 21 1 45 10557 11 1 7 8 12 9 15 198 2258 2155 359 989 964 183 209 14099 1913 63 49 1408 3447 170 10998 1 10967 2966 63 144 145 2 158 14 99 374 11 162 11 2 9 4 41 7 231 6 370 253 539 3 5346 279 1331 274 1926 383 15 4 60 35 572 49 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Security Module Hook declarations. * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2016 Mellanox Techonologies * Copyright (C) 2020 Google LLC. */ /* * The macro LSM_HOOK is used to define the data structures required by * the LSM framework using the pattern: * * LSM_HOOK(<return_type>, <default_value>, <hook_name>, args...) * * struct security_hook_heads { * #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; * #include <linux/lsm_hook_defs.h> * #undef LSM_HOOK * }; */ LSM_HOOK(int, 0, binder_set_context_mgr, const struct cred *mgr) LSM_HOOK(int, 0, binder_transaction, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from, const struct cred *to) LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from, const struct cred *to, const struct file *file) LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child, unsigned int mode) LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent) LSM_HOOK(int, 0, capget, const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, const struct super_block *sb) LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, const struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, const struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_submount, struct fs_context *fc, struct super_block *reference) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_delete, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts) LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts) LSM_HOOK(int, 0, sb_mnt_opts_compat, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_remount, struct super_block *sb, void *mnt_opts) LSM_HOOK(int, 0, sb_kern_mount, const struct super_block *sb) LSM_HOOK(int, 0, sb_show_options, struct seq_file *m, struct super_block *sb) LSM_HOOK(int, 0, sb_statfs, struct dentry *dentry) LSM_HOOK(int, 0, sb_mount, const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) LSM_HOOK(int, 0, sb_umount, struct vfsmount *mnt, int flags) LSM_HOOK(int, 0, sb_pivotroot, const struct path *old_path, const struct path *new_path) LSM_HOOK(int, 0, sb_set_mnt_opts, struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, struct lsm_context *cp) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, const struct qstr *name, const struct cred *old, struct cred *new) #ifdef CONFIG_SECURITY_PATH LSM_HOOK(int, 0, path_unlink, const struct path *dir, struct dentry *dentry) LSM_HOOK(int, 0, path_mkdir, const struct path *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, path_rmdir, const struct path *dir, struct dentry *dentry) LSM_HOOK(int, 0, path_mknod, const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) LSM_HOOK(void, LSM_RET_VOID, path_post_mknod, struct mnt_idmap *idmap, struct dentry *dentry) LSM_HOOK(int, 0, path_truncate, const struct path *path) LSM_HOOK(int, 0, path_symlink, const struct path *dir, struct dentry *dentry, const char *old_name) LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) #endif /* CONFIG_SECURITY_PATH */ /* Needed for inode based security check */ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask, unsigned int obj_type) LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security_rcu, void *inode_security) LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) LSM_HOOK(int, 0, inode_init_security_anon, struct inode *inode, const struct qstr *name, const struct inode *context_inode) LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(void, LSM_RET_VOID, inode_post_create_tmpfile, struct mnt_idmap *idmap, struct inode *inode) LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) LSM_HOOK(int, 0, inode_unlink, struct inode *dir, struct dentry *dentry) LSM_HOOK(int, 0, inode_symlink, struct inode *dir, struct dentry *dentry, const char *old_name) LSM_HOOK(int, 0, inode_mkdir, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, inode_rmdir, struct inode *dir, struct dentry *dentry) LSM_HOOK(int, 0, inode_mknod, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) LSM_HOOK(int, 0, inode_rename, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, inode_readlink, struct dentry *dentry) LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, bool rcu) LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) LSM_HOOK(int, 0, inode_getattr, const struct path *path) LSM_HOOK(int, 0, inode_xattr_skipcap, const char *name) LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name) LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct file_kattr *fa) LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct file_kattr *fa) LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(int, 0, inode_get_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(void, LSM_RET_VOID, inode_post_remove_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) LSM_HOOK(int, 0, inode_killpriv, struct mnt_idmap *idmap, struct dentry *dentry) LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) LSM_HOOK(void, LSM_RET_VOID, inode_getlsmprop, struct inode *inode, struct lsm_prop *prop) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, const char *name) LSM_HOOK(int, 0, inode_setintegrity, const struct inode *inode, enum lsm_integrity_type type, const void *value, size_t size) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) LSM_HOOK(int, 0, file_alloc_security, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_release, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file) LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(int, 0, mmap_addr, unsigned long addr) LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd) LSM_HOOK(int, 0, file_fcntl, struct file *file, unsigned int cmd, unsigned long arg) LSM_HOOK(void, LSM_RET_VOID, file_set_fowner, struct file *file) LSM_HOOK(int, 0, file_send_sigiotask, struct task_struct *tsk, struct fown_struct *fown, int sig) LSM_HOOK(int, 0, file_receive, struct file *file) LSM_HOOK(int, 0, file_open, struct file *file) LSM_HOOK(int, 0, file_post_open, struct file *file, int mask) LSM_HOOK(int, 0, file_truncate, struct file *file) LSM_HOOK(int, 0, task_alloc, struct task_struct *task, u64 clone_flags) LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task) LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred) LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, gfp_t gfp) LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, const struct cred *old) LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, cred_getlsmprop, const struct cred *c, struct lsm_prop *prop) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents) LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size, enum kernel_load_data_id id, char *description) LSM_HOOK(int, 0, kernel_read_file, struct file *file, enum kernel_read_file_id id, bool contents) LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old, int flags) LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, int flags) LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) LSM_HOOK(void, LSM_RET_VOID, current_getlsmprop_subj, struct lsm_prop *prop) LSM_HOOK(void, LSM_RET_VOID, task_getlsmprop_obj, struct task_struct *p, struct lsm_prop *prop) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) LSM_HOOK(int, 0, task_prlimit, const struct cred *cred, const struct cred *tcred, unsigned int flags) LSM_HOOK(int, 0, task_setrlimit, struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) LSM_HOOK(int, 0, task_setscheduler, struct task_struct *p) LSM_HOOK(int, 0, task_getscheduler, struct task_struct *p) LSM_HOOK(int, 0, task_movememory, struct task_struct *p) LSM_HOOK(int, 0, task_kill, struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) LSM_HOOK(int, -ENOSYS, task_prctl, int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) LSM_HOOK(void, LSM_RET_VOID, ipc_getlsmprop, struct kern_ipc_perm *ipcp, struct lsm_prop *prop) LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, msg_queue_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, msg_queue_associate, struct kern_ipc_perm *perm, int msqflg) LSM_HOOK(int, 0, msg_queue_msgctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, msg_queue_msgsnd, struct kern_ipc_perm *perm, struct msg_msg *msg, int msqflg) LSM_HOOK(int, 0, msg_queue_msgrcv, struct kern_ipc_perm *perm, struct msg_msg *msg, struct task_struct *target, long type, int mode) LSM_HOOK(int, 0, shm_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, shm_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, shm_associate, struct kern_ipc_perm *perm, int shmflg) LSM_HOOK(int, 0, shm_shmctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, shm_shmat, struct kern_ipc_perm *perm, char __user *shmaddr, int shmflg) LSM_HOOK(int, 0, sem_alloc_security, struct kern_ipc_perm *perm) LSM_HOOK(void, LSM_RET_VOID, sem_free_security, struct kern_ipc_perm *perm) LSM_HOOK(int, 0, sem_associate, struct kern_ipc_perm *perm, int semflg) LSM_HOOK(int, 0, sem_semctl, struct kern_ipc_perm *perm, int cmd) LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops, unsigned nsops, int alter) LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, struct lsm_context *cp) LSM_HOOK(int, -EOPNOTSUPP, lsmprop_to_secctx, struct lsm_prop *prop, struct lsm_context *cp) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, struct lsm_context *cp) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, struct lsm_context *cp) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) #endif /* CONFIG_SECURITY && CONFIG_WATCH_QUEUE */ #if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS) LSM_HOOK(int, 0, watch_key, struct key *key) #endif /* CONFIG_SECURITY && CONFIG_KEY_NOTIFICATIONS */ #ifdef CONFIG_SECURITY_NETWORK LSM_HOOK(int, 0, unix_stream_connect, struct sock *sock, struct sock *other, struct sock *newsk) LSM_HOOK(int, 0, unix_may_send, struct socket *sock, struct socket *other) LSM_HOOK(int, 0, socket_create, int family, int type, int protocol, int kern) LSM_HOOK(int, 0, socket_post_create, struct socket *sock, int family, int type, int protocol, int kern) LSM_HOOK(int, 0, socket_socketpair, struct socket *socka, struct socket *sockb) LSM_HOOK(int, 0, socket_bind, struct socket *sock, struct sockaddr *address, int addrlen) LSM_HOOK(int, 0, socket_connect, struct socket *sock, struct sockaddr *address, int addrlen) LSM_HOOK(int, 0, socket_listen, struct socket *sock, int backlog) LSM_HOOK(int, 0, socket_accept, struct socket *sock, struct socket *newsock) LSM_HOOK(int, 0, socket_sendmsg, struct socket *sock, struct msghdr *msg, int size) LSM_HOOK(int, 0, socket_recvmsg, struct socket *sock, struct msghdr *msg, int size, int flags) LSM_HOOK(int, 0, socket_getsockname, struct socket *sock) LSM_HOOK(int, 0, socket_getpeername, struct socket *sock) LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk, struct sock *newsk) LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent) LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb, struct request_sock *req) LSM_HOOK(void, LSM_RET_VOID, inet_csk_clone, struct sock *newsk, const struct request_sock *req) LSM_HOOK(void, LSM_RET_VOID, inet_conn_established, struct sock *sk, struct sk_buff *skb) LSM_HOOK(int, 0, secmark_relabel_packet, u32 secid) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void) LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req, struct flowi_common *flic) LSM_HOOK(int, 0, tun_dev_alloc_security, void *security) LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) LSM_HOOK(int, 0, tun_dev_open, void *security) LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey) LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name, u8 port_num) LSM_HOOK(int, 0, ib_alloc_security, void *sec) #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK(int, 0, xfrm_policy_alloc_security, struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) LSM_HOOK(int, 0, xfrm_policy_clone_security, struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx) LSM_HOOK(void, LSM_RET_VOID, xfrm_policy_free_security, struct xfrm_sec_ctx *ctx) LSM_HOOK(int, 0, xfrm_policy_delete_security, struct xfrm_sec_ctx *ctx) LSM_HOOK(int, 0, xfrm_state_alloc, struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid) LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, int ckall) #endif /* CONFIG_SECURITY_NETWORK_XFRM */ /* key management security hooks */ #ifdef CONFIG_KEYS LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, struct key *key, const void *payload, size_t payload_len, unsigned long flags, bool create) #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) LSM_HOOK(int, 0, audit_rule_match, struct lsm_prop *prop, u32 field, u32 op, void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token, bool kernel) LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token, bool kernel) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, const struct path *path) LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) #ifdef CONFIG_PERF_EVENTS LSM_HOOK(int, 0, perf_event_open, int type) LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) LSM_HOOK(int, 0, uring_allowed, void) #endif /* CONFIG_IO_URING */ LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void) LSM_HOOK(int, 0, bdev_alloc_security, struct block_device *bdev) LSM_HOOK(void, LSM_RET_VOID, bdev_free_security, struct block_device *bdev) LSM_HOOK(int, 0, bdev_setintegrity, struct block_device *bdev, enum lsm_integrity_type type, const void *value, size_t size) |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <net/macsec.h> #include "netdevsim.h" static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci) { int i; for (i = 0; i < NSIM_MACSEC_MAX_SECY_COUNT; i++) { if (ns->macsec.nsim_secy[i].sci == sci) return i; } return -1; } static int nsim_macsec_find_rxsc(struct nsim_secy *ns_secy, sci_t sci) { int i; for (i = 0; i < NSIM_MACSEC_MAX_RXSC_COUNT; i++) { if (ns_secy->nsim_rxsc[i].sci == sci) return i; } return -1; } static int nsim_macsec_add_secy(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; if (ns->macsec.nsim_secy_count == NSIM_MACSEC_MAX_SECY_COUNT) return -ENOSPC; for (idx = 0; idx < NSIM_MACSEC_MAX_SECY_COUNT; idx++) { if (!ns->macsec.nsim_secy[idx].used) break; } if (idx == NSIM_MACSEC_MAX_SECY_COUNT) { netdev_err(ctx->netdev, "%s: nsim_secy_count not full but all SecYs used\n", __func__); return -ENOSPC; } netdev_dbg(ctx->netdev, "%s: adding new secy with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->secy->sci), idx); ns->macsec.nsim_secy[idx].used = true; ns->macsec.nsim_secy[idx].nsim_rxsc_count = 0; ns->macsec.nsim_secy[idx].sci = ctx->secy->sci; ns->macsec.nsim_secy_count++; return 0; } static int nsim_macsec_upd_secy(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: updating secy with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->secy->sci), idx); return 0; } static int nsim_macsec_del_secy(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: removing SecY with SCI %016llx at index %d\n", __func__, sci_to_cpu(ctx->secy->sci), idx); ns->macsec.nsim_secy[idx].used = false; memset(&ns->macsec.nsim_secy[idx], 0, sizeof(ns->macsec.nsim_secy[idx])); ns->macsec.nsim_secy_count--; return 0; } static int nsim_macsec_add_rxsc(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; if (secy->nsim_rxsc_count == NSIM_MACSEC_MAX_RXSC_COUNT) return -ENOSPC; for (idx = 0; idx < NSIM_MACSEC_MAX_RXSC_COUNT; idx++) { if (!secy->nsim_rxsc[idx].used) break; } if (idx == NSIM_MACSEC_MAX_RXSC_COUNT) netdev_err(ctx->netdev, "%s: nsim_rxsc_count not full but all RXSCs used\n", __func__); netdev_dbg(ctx->netdev, "%s: adding new rxsc with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->rx_sc->sci), idx); secy->nsim_rxsc[idx].used = true; secy->nsim_rxsc[idx].sci = ctx->rx_sc->sci; secy->nsim_rxsc_count++; return 0; } static int nsim_macsec_upd_rxsc(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->rx_sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: updating RXSC with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->rx_sc->sci), idx); return 0; } static int nsim_macsec_del_rxsc(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->rx_sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->rx_sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: removing RXSC with sci %016llx at index %d\n", __func__, sci_to_cpu(ctx->rx_sc->sci), idx); secy->nsim_rxsc[idx].used = false; memset(&secy->nsim_rxsc[idx], 0, sizeof(secy->nsim_rxsc[idx])); secy->nsim_rxsc_count--; return 0; } static int nsim_macsec_add_rxsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_upd_rxsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_del_rxsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); struct nsim_secy *secy; int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } secy = &ns->macsec.nsim_secy[idx]; idx = nsim_macsec_find_rxsc(secy, ctx->sa.rx_sa->sc->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in RXSC table\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: RXSC with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->sa.rx_sa->sc->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_add_txsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_upd_txsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num); return 0; } static int nsim_macsec_del_txsa(struct macsec_context *ctx) { struct netdevsim *ns = netdev_priv(ctx->netdev); int idx; idx = nsim_macsec_find_secy(ns, ctx->secy->sci); if (idx < 0) { netdev_err(ctx->netdev, "%s: sci %016llx not found in secy table\n", __func__, sci_to_cpu(ctx->secy->sci)); return -ENOENT; } netdev_dbg(ctx->netdev, "%s: SECY with sci %016llx, AN %u\n", __func__, sci_to_cpu(ctx->secy->sci), ctx->sa.assoc_num); return 0; } static const struct macsec_ops nsim_macsec_ops = { .mdo_add_secy = nsim_macsec_add_secy, .mdo_upd_secy = nsim_macsec_upd_secy, .mdo_del_secy = nsim_macsec_del_secy, .mdo_add_rxsc = nsim_macsec_add_rxsc, .mdo_upd_rxsc = nsim_macsec_upd_rxsc, .mdo_del_rxsc = nsim_macsec_del_rxsc, .mdo_add_rxsa = nsim_macsec_add_rxsa, .mdo_upd_rxsa = nsim_macsec_upd_rxsa, .mdo_del_rxsa = nsim_macsec_del_rxsa, .mdo_add_txsa = nsim_macsec_add_txsa, .mdo_upd_txsa = nsim_macsec_upd_txsa, .mdo_del_txsa = nsim_macsec_del_txsa, }; void nsim_macsec_init(struct netdevsim *ns) { ns->netdev->macsec_ops = &nsim_macsec_ops; ns->netdev->features |= NETIF_F_HW_MACSEC; memset(&ns->macsec, 0, sizeof(ns->macsec)); } void nsim_macsec_teardown(struct netdevsim *ns) { } |
| 26 16 30 42 39 18 11 5 18 5 28 22 28 27 26 5 5 5 11 11 13 42 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __BPF_MPROG_H #define __BPF_MPROG_H #include <linux/bpf.h> /* bpf_mprog framework: * * bpf_mprog is a generic layer for multi-program attachment. In-kernel users * of the bpf_mprog don't need to care about the dependency resolution * internals, they can just consume it with few API calls. Currently available * dependency directives are BPF_F_{BEFORE,AFTER} which enable insertion of * a BPF program or BPF link relative to an existing BPF program or BPF link * inside the multi-program array as well as prepend and append behavior if * no relative object was specified, see corresponding selftests for concrete * examples (e.g. tc_links and tc_opts test cases of test_progs). * * Usage of bpf_mprog_{attach,detach,query}() core APIs with pseudo code: * * Attach case: * * struct bpf_mprog_entry *entry, *entry_new; * int ret; * * // bpf_mprog user-side lock * // fetch active @entry from attach location * [...] * ret = bpf_mprog_attach(entry, &entry_new, [...]); * if (!ret) { * if (entry != entry_new) { * // swap @entry to @entry_new at attach location * // ensure there are no inflight users of @entry: * synchronize_rcu(); * } * bpf_mprog_commit(entry); * } else { * // error path, bail out, propagate @ret * } * // bpf_mprog user-side unlock * * Detach case: * * struct bpf_mprog_entry *entry, *entry_new; * int ret; * * // bpf_mprog user-side lock * // fetch active @entry from attach location * [...] * ret = bpf_mprog_detach(entry, &entry_new, [...]); * if (!ret) { * // all (*) marked is optional and depends on the use-case * // whether bpf_mprog_bundle should be freed or not * if (!bpf_mprog_total(entry_new)) (*) * entry_new = NULL (*) * // swap @entry to @entry_new at attach location * // ensure there are no inflight users of @entry: * synchronize_rcu(); * bpf_mprog_commit(entry); * if (!entry_new) (*) * // free bpf_mprog_bundle (*) * } else { * // error path, bail out, propagate @ret * } * // bpf_mprog user-side unlock * * Query case: * * struct bpf_mprog_entry *entry; * int ret; * * // bpf_mprog user-side lock * // fetch active @entry from attach location * [...] * ret = bpf_mprog_query(attr, uattr, entry); * // bpf_mprog user-side unlock * * Data/fast path: * * struct bpf_mprog_entry *entry; * struct bpf_mprog_fp *fp; * struct bpf_prog *prog; * int ret = [...]; * * rcu_read_lock(); * // fetch active @entry from attach location * [...] * bpf_mprog_foreach_prog(entry, fp, prog) { * ret = bpf_prog_run(prog, [...]); * // process @ret from program * } * [...] * rcu_read_unlock(); * * bpf_mprog locking considerations: * * bpf_mprog_{attach,detach,query}() must be protected by an external lock * (like RTNL in case of tcx). * * bpf_mprog_entry pointer can be an __rcu annotated pointer (in case of tcx * the netdevice has tcx_ingress and tcx_egress __rcu pointer) which gets * updated via rcu_assign_pointer() pointing to the active bpf_mprog_entry of * the bpf_mprog_bundle. * * Fast path accesses the active bpf_mprog_entry within RCU critical section * (in case of tcx it runs in NAPI which provides RCU protection there, * other users might need explicit rcu_read_lock()). The bpf_mprog_commit() * assumes that for the old bpf_mprog_entry there are no inflight users * anymore. * * The READ_ONCE()/WRITE_ONCE() pairing for bpf_mprog_fp's prog access is for * the replacement case where we don't swap the bpf_mprog_entry. */ #define bpf_mprog_foreach_tuple(entry, fp, cp, t) \ for (fp = &entry->fp_items[0], cp = &entry->parent->cp_items[0];\ ({ \ t.prog = READ_ONCE(fp->prog); \ t.link = cp->link; \ t.prog; \ }); \ fp++, cp++) #define bpf_mprog_foreach_prog(entry, fp, p) \ for (fp = &entry->fp_items[0]; \ (p = READ_ONCE(fp->prog)); \ fp++) #define BPF_MPROG_MAX 64 struct bpf_mprog_fp { struct bpf_prog *prog; }; struct bpf_mprog_cp { struct bpf_link *link; }; struct bpf_mprog_entry { struct bpf_mprog_fp fp_items[BPF_MPROG_MAX]; struct bpf_mprog_bundle *parent; }; struct bpf_mprog_bundle { struct bpf_mprog_entry a; struct bpf_mprog_entry b; struct bpf_mprog_cp cp_items[BPF_MPROG_MAX]; struct bpf_prog *ref; atomic64_t revision; u32 count; }; struct bpf_tuple { struct bpf_prog *prog; struct bpf_link *link; }; static inline struct bpf_mprog_entry * bpf_mprog_peer(const struct bpf_mprog_entry *entry) { if (entry == &entry->parent->a) return &entry->parent->b; else return &entry->parent->a; } static inline void bpf_mprog_bundle_init(struct bpf_mprog_bundle *bundle) { BUILD_BUG_ON(sizeof(bundle->a.fp_items[0]) > sizeof(u64)); BUILD_BUG_ON(ARRAY_SIZE(bundle->a.fp_items) != ARRAY_SIZE(bundle->cp_items)); memset(bundle, 0, sizeof(*bundle)); atomic64_set(&bundle->revision, 1); bundle->a.parent = bundle; bundle->b.parent = bundle; } static inline void bpf_mprog_inc(struct bpf_mprog_entry *entry) { entry->parent->count++; } static inline void bpf_mprog_dec(struct bpf_mprog_entry *entry) { entry->parent->count--; } static inline int bpf_mprog_max(void) { return ARRAY_SIZE(((struct bpf_mprog_entry *)NULL)->fp_items) - 1; } static inline int bpf_mprog_total(struct bpf_mprog_entry *entry) { int total = entry->parent->count; WARN_ON_ONCE(total > bpf_mprog_max()); return total; } static inline bool bpf_mprog_exists(struct bpf_mprog_entry *entry, struct bpf_prog *prog) { const struct bpf_mprog_fp *fp; const struct bpf_prog *tmp; bpf_mprog_foreach_prog(entry, fp, tmp) { if (tmp == prog) return true; } return false; } static inline void bpf_mprog_mark_for_release(struct bpf_mprog_entry *entry, struct bpf_tuple *tuple) { WARN_ON_ONCE(entry->parent->ref); if (!tuple->link) entry->parent->ref = tuple->prog; } static inline void bpf_mprog_complete_release(struct bpf_mprog_entry *entry) { /* In the non-link case prog deletions can only drop the reference * to the prog after the bpf_mprog_entry got swapped and the * bpf_mprog ensured that there are no inflight users anymore. * * Paired with bpf_mprog_mark_for_release(). */ if (entry->parent->ref) { bpf_prog_put(entry->parent->ref); entry->parent->ref = NULL; } } static inline void bpf_mprog_revision_new(struct bpf_mprog_entry *entry) { atomic64_inc(&entry->parent->revision); } static inline void bpf_mprog_commit(struct bpf_mprog_entry *entry) { bpf_mprog_complete_release(entry); bpf_mprog_revision_new(entry); } static inline u64 bpf_mprog_revision(struct bpf_mprog_entry *entry) { return atomic64_read(&entry->parent->revision); } static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst, struct bpf_mprog_entry *src) { memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items)); } static inline void bpf_mprog_entry_clear(struct bpf_mprog_entry *dst) { memset(dst->fp_items, 0, sizeof(dst->fp_items)); } static inline void bpf_mprog_clear_all(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new) { struct bpf_mprog_entry *peer; peer = bpf_mprog_peer(entry); bpf_mprog_entry_clear(peer); peer->parent->count = 0; *entry_new = peer; } static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx) { int total = bpf_mprog_total(entry); memmove(entry->fp_items + idx + 1, entry->fp_items + idx, (total - idx) * sizeof(struct bpf_mprog_fp)); memmove(entry->parent->cp_items + idx + 1, entry->parent->cp_items + idx, (total - idx) * sizeof(struct bpf_mprog_cp)); } static inline void bpf_mprog_entry_shrink(struct bpf_mprog_entry *entry, int idx) { /* Total array size is needed in this case to enure the NULL * entry is copied at the end. */ int total = ARRAY_SIZE(entry->fp_items); memmove(entry->fp_items + idx, entry->fp_items + idx + 1, (total - idx - 1) * sizeof(struct bpf_mprog_fp)); memmove(entry->parent->cp_items + idx, entry->parent->cp_items + idx + 1, (total - idx - 1) * sizeof(struct bpf_mprog_cp)); } static inline void bpf_mprog_read(struct bpf_mprog_entry *entry, u32 idx, struct bpf_mprog_fp **fp, struct bpf_mprog_cp **cp) { *fp = &entry->fp_items[idx]; *cp = &entry->parent->cp_items[idx]; } static inline void bpf_mprog_write(struct bpf_mprog_fp *fp, struct bpf_mprog_cp *cp, struct bpf_tuple *tuple) { WRITE_ONCE(fp->prog, tuple->prog); cp->link = tuple->link; } int bpf_mprog_attach(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_prog *prog_new, struct bpf_link *link, struct bpf_prog *prog_old, u32 flags, u32 id_or_fd, u64 revision); int bpf_mprog_detach(struct bpf_mprog_entry *entry, struct bpf_mprog_entry **entry_new, struct bpf_prog *prog, struct bpf_link *link, u32 flags, u32 id_or_fd, u64 revision); int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct bpf_mprog_entry *entry); static inline bool bpf_mprog_supported(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_SCHED_CLS: return true; default: return false; } } #endif /* __BPF_MPROG_H */ |
| 5 5 7 7 7 4 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/options.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Option parsing */ #include <linux/string.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/nls.h> #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/slab.h> #include "hfsplus_fs.h" enum { opt_creator, opt_type, opt_umask, opt_uid, opt_gid, opt_part, opt_session, opt_nls, opt_decompose, opt_barrier, opt_force, }; static const struct fs_parameter_spec hfs_param_spec[] = { fsparam_string ("creator", opt_creator), fsparam_string ("type", opt_type), fsparam_u32oct ("umask", opt_umask), fsparam_u32 ("uid", opt_uid), fsparam_u32 ("gid", opt_gid), fsparam_u32 ("part", opt_part), fsparam_u32 ("session", opt_session), fsparam_string ("nls", opt_nls), fsparam_flag_no ("decompose", opt_decompose), fsparam_flag_no ("barrier", opt_barrier), fsparam_flag ("force", opt_force), {} }; /* Initialize an options object to reasonable defaults */ void hfsplus_fill_defaults(struct hfsplus_sb_info *opts) { if (!opts) return; opts->creator = HFSPLUS_DEF_CR_TYPE; opts->type = HFSPLUS_DEF_CR_TYPE; opts->umask = current_umask(); opts->uid = current_uid(); opts->gid = current_gid(); opts->part = -1; opts->session = -1; } /* Parse options from mount. Returns nonzero errno on failure */ int hfsplus_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hfsplus_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; int opt; /* * Only the force option is examined during remount, all others * are ignored. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE && strncmp(param->key, "force", 5)) return 0; opt = fs_parse(fc, hfs_param_spec, param, &result); if (opt < 0) return opt; switch (opt) { case opt_creator: if (strlen(param->string) != 4) { pr_err("creator requires a 4 character value\n"); return -EINVAL; } memcpy(&sbi->creator, param->string, 4); break; case opt_type: if (strlen(param->string) != 4) { pr_err("type requires a 4 character value\n"); return -EINVAL; } memcpy(&sbi->type, param->string, 4); break; case opt_umask: sbi->umask = (umode_t)result.uint_32; break; case opt_uid: sbi->uid = result.uid; set_bit(HFSPLUS_SB_UID, &sbi->flags); break; case opt_gid: sbi->gid = result.gid; set_bit(HFSPLUS_SB_GID, &sbi->flags); break; case opt_part: sbi->part = result.uint_32; break; case opt_session: sbi->session = result.uint_32; break; case opt_nls: if (sbi->nls) { pr_err("unable to change nls mapping\n"); return -EINVAL; } sbi->nls = load_nls(param->string); if (!sbi->nls) { pr_err("unable to load nls mapping \"%s\"\n", param->string); return -EINVAL; } break; case opt_decompose: if (result.negated) set_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags); else clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags); break; case opt_barrier: if (result.negated) set_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags); else clear_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags); break; case opt_force: set_bit(HFSPLUS_SB_FORCE, &sbi->flags); break; default: return -EINVAL; } return 0; } int hfsplus_show_options(struct seq_file *seq, struct dentry *root) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(root->d_sb); if (sbi->creator != HFSPLUS_DEF_CR_TYPE) seq_show_option_n(seq, "creator", (char *)&sbi->creator, 4); if (sbi->type != HFSPLUS_DEF_CR_TYPE) seq_show_option_n(seq, "type", (char *)&sbi->type, 4); seq_printf(seq, ",umask=%o,uid=%u,gid=%u", sbi->umask, from_kuid_munged(&init_user_ns, sbi->uid), from_kgid_munged(&init_user_ns, sbi->gid)); if (sbi->part >= 0) seq_printf(seq, ",part=%u", sbi->part); if (sbi->session >= 0) seq_printf(seq, ",session=%u", sbi->session); if (sbi->nls) seq_printf(seq, ",nls=%s", sbi->nls->charset); if (test_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags)) seq_puts(seq, ",nodecompose"); if (test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags)) seq_puts(seq, ",nobarrier"); return 0; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 80 80 80 80 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/stats.c * * procfs-based user access to generic RPC statistics. The stats files * reside in /proc/net/rpc. * * The read routines assume that the buffer passed in is just big enough. * If you implement an RPC service that has its own stats routine which * appends the generic RPC stats, make sure you don't exceed the PAGE_SIZE * limit. * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/metrics.h> #include <linux/rcupdate.h> #include <trace/events/sunrpc.h> #include "netns.h" #define RPCDBG_FACILITY RPCDBG_MISC /* * Get RPC client stats */ static int rpc_proc_show(struct seq_file *seq, void *v) { const struct rpc_stat *statp = seq->private; const struct rpc_program *prog = statp->program; unsigned int i, j; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u\n", statp->rpccnt, statp->rpcretrans, statp->rpcauthrefresh); for (i = 0; i < prog->nrvers; i++) { const struct rpc_version *vers = prog->version[i]; if (!vers) continue; seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; } static int rpc_proc_open(struct inode *inode, struct file *file) { return single_open(file, rpc_proc_show, pde_data(inode)); } static const struct proc_ops rpc_proc_ops = { .proc_open = rpc_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = single_release, }; /* * Get RPC server stats */ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { const struct svc_program *prog = statp->program; const struct svc_version *vers; unsigned int i, j, k; unsigned long count; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u %u %u\n", statp->rpccnt, statp->rpcbadfmt+statp->rpcbadauth+statp->rpcbadclnt, statp->rpcbadfmt, statp->rpcbadauth, statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { vers = prog->pg_vers[i]; if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); for (j = 0; j < vers->vs_nproc; j++) { count = 0; for_each_possible_cpu(k) count += per_cpu(vers->vs_count[j], k); seq_printf(seq, " %lu", count); } seq_putc(seq, '\n'); } } EXPORT_SYMBOL_GPL(svc_seq_show); /** * rpc_alloc_iostats - allocate an rpc_iostats structure * @clnt: RPC program, version, and xprt * */ struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { struct rpc_iostats *stats; int i; stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL); if (stats) { for (i = 0; i < clnt->cl_maxproc; i++) spin_lock_init(&stats[i].om_lock); } return stats; } EXPORT_SYMBOL_GPL(rpc_alloc_iostats); /** * rpc_free_iostats - release an rpc_iostats structure * @stats: doomed rpc_iostats structure * */ void rpc_free_iostats(struct rpc_iostats *stats) { kfree(stats); } EXPORT_SYMBOL_GPL(rpc_free_iostats); /** * rpc_count_iostats_metrics - tally up per-task stats * @task: completed rpc_task * @op_metrics: stat structure for OP that will accumulate stats from @task */ void rpc_count_iostats_metrics(const struct rpc_task *task, struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; ktime_t backlog, execute, now; if (!op_metrics || !req) return; now = ktime_get(); spin_lock(&op_metrics->om_lock); op_metrics->om_ops++; /* kernel API: om_ops must never become larger than om_ntrans */ op_metrics->om_ntrans += max(req->rq_ntrans, 1); op_metrics->om_timeouts += task->tk_timeouts; op_metrics->om_bytes_sent += req->rq_xmit_bytes_sent; op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd; backlog = 0; if (ktime_to_ns(req->rq_xtime)) { backlog = ktime_sub(req->rq_xtime, task->tk_start); op_metrics->om_queue = ktime_add(op_metrics->om_queue, backlog); } op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); execute = ktime_sub(now, task->tk_start); op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute); if (task->tk_status < 0) op_metrics->om_error_status++; spin_unlock(&op_metrics->om_lock); trace_rpc_stats_latency(req->rq_task, backlog, req->rq_rtt, execute); } EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); /** * rpc_count_iostats - tally up per-task stats * @task: completed rpc_task * @stats: array of stat structures * * Uses the statidx from @task */ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) { rpc_count_iostats_metrics(task, &stats[task->tk_msg.rpc_proc->p_statidx]); } EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); else if (op == 0) seq_printf(seq, "\t NULL: "); else seq_printf(seq, "\t%12u: ", op); } static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b) { a->om_ops += b->om_ops; a->om_ntrans += b->om_ntrans; a->om_timeouts += b->om_timeouts; a->om_bytes_sent += b->om_bytes_sent; a->om_bytes_recv += b->om_bytes_recv; a->om_queue = ktime_add(a->om_queue, b->om_queue); a->om_rtt = ktime_add(a->om_rtt, b->om_rtt); a->om_execute = ktime_add(a->om_execute, b->om_execute); a->om_error_status += b->om_error_status; } static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats, int op, const struct rpc_procinfo *procs) { _print_name(seq, op, procs); seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %llu %lu\n", stats->om_ops, stats->om_ntrans, stats->om_timeouts, stats->om_bytes_sent, stats->om_bytes_recv, ktime_to_ms(stats->om_queue), ktime_to_ms(stats->om_rtt), ktime_to_ms(stats->om_execute), stats->om_error_status); } static int do_print_stats(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *seqv) { struct seq_file *seq = seqv; xprt->ops->print_stats(xprt, seq); return 0; } void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) { unsigned int op, maxproc = clnt->cl_maxproc; if (!clnt->cl_metrics) return; seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); seq_printf(seq, "p/v: %u/%u (%s)\n", clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name); rpc_clnt_iterate_for_each_xprt(clnt, do_print_stats, seq); seq_printf(seq, "\tper-op statistics\n"); for (op = 0; op < maxproc; op++) { struct rpc_iostats stats = {}; struct rpc_clnt *next = clnt; do { _add_rpc_iostats(&stats, &next->cl_metrics[op]); if (next == next->cl_parent) break; next = next->cl_parent; } while (next); _print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo); } } EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); /* * Register/unregister RPC proc files */ static inline struct proc_dir_entry * do_register(struct net *net, const char *name, void *data, const struct proc_ops *proc_ops) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc/%s\n", name); sn = net_generic(net, sunrpc_net_id); return proc_create_data(name, 0, sn->proc_net_rpc, proc_ops, data); } struct proc_dir_entry * rpc_proc_register(struct net *net, struct rpc_stat *statp) { return do_register(net, statp->program->name, statp, &rpc_proc_ops); } EXPORT_SYMBOL_GPL(rpc_proc_register); void rpc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(rpc_proc_unregister); struct proc_dir_entry * svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops) { return do_register(net, statp->program->pg_name, net, proc_ops); } EXPORT_SYMBOL_GPL(svc_proc_register); void svc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(svc_proc_unregister); int rpc_proc_init(struct net *net) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc\n"); sn = net_generic(net, sunrpc_net_id); sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net); if (sn->proc_net_rpc == NULL) return -ENOMEM; return 0; } void rpc_proc_exit(struct net *net) { dprintk("RPC: unregistering /proc/net/rpc\n"); remove_proc_entry("rpc", net->proc_net); } |
| 42 3 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 | // SPDX-License-Identifier: GPL-2.0-or-later // Copyright (c) 2020, Nikolay Aleksandrov <nikolay@nvidia.com> #include <linux/err.h> #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/netdevice.h> #include <linux/netfilter_bridge.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif #include "br_private.h" #include "br_private_mcast_eht.h" static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr); static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, bool allow_zero_src); static struct net_bridge_group_eht_host * br_multicast_eht_host_lookup(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct rb_node *node = pg->eht_host_tree.rb_node; while (node) { struct net_bridge_group_eht_host *this; int result; this = rb_entry(node, struct net_bridge_group_eht_host, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static int br_multicast_eht_host_filter_mode(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_host *eht_host; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (!eht_host) return MCAST_INCLUDE; return eht_host->filter_mode; } static struct net_bridge_group_eht_set_entry * br_multicast_eht_set_entry_lookup(struct net_bridge_group_eht_set *eht_set, union net_bridge_eht_addr *h_addr) { struct rb_node *node = eht_set->entry_tree.rb_node; while (node) { struct net_bridge_group_eht_set_entry *this; int result; this = rb_entry(node, struct net_bridge_group_eht_set_entry, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static struct net_bridge_group_eht_set * br_multicast_eht_set_lookup(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr) { struct rb_node *node = pg->eht_set_tree.rb_node; while (node) { struct net_bridge_group_eht_set *this; int result; this = rb_entry(node, struct net_bridge_group_eht_set, rb_node); result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static void __eht_destroy_host(struct net_bridge_group_eht_host *eht_host) { WARN_ON(!hlist_empty(&eht_host->set_entries)); br_multicast_eht_hosts_dec(eht_host->pg); rb_erase(&eht_host->rb_node, &eht_host->pg->eht_host_tree); RB_CLEAR_NODE(&eht_host->rb_node); kfree(eht_host); } static void br_multicast_destroy_eht_set_entry(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_eht_set_entry *set_h; set_h = container_of(gc, struct net_bridge_group_eht_set_entry, mcast_gc); WARN_ON(!RB_EMPTY_NODE(&set_h->rb_node)); timer_shutdown_sync(&set_h->timer); kfree(set_h); } static void br_multicast_destroy_eht_set(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_eht_set *eht_set; eht_set = container_of(gc, struct net_bridge_group_eht_set, mcast_gc); WARN_ON(!RB_EMPTY_NODE(&eht_set->rb_node)); WARN_ON(!RB_EMPTY_ROOT(&eht_set->entry_tree)); timer_shutdown_sync(&eht_set->timer); kfree(eht_set); } static void __eht_del_set_entry(struct net_bridge_group_eht_set_entry *set_h) { struct net_bridge_group_eht_host *eht_host = set_h->h_parent; union net_bridge_eht_addr zero_addr; rb_erase(&set_h->rb_node, &set_h->eht_set->entry_tree); RB_CLEAR_NODE(&set_h->rb_node); hlist_del_init(&set_h->host_list); memset(&zero_addr, 0, sizeof(zero_addr)); if (memcmp(&set_h->h_addr, &zero_addr, sizeof(zero_addr))) eht_host->num_entries--; hlist_add_head(&set_h->mcast_gc.gc_node, &set_h->br->mcast_gc_list); queue_work(system_long_wq, &set_h->br->mcast_gc_work); if (hlist_empty(&eht_host->set_entries)) __eht_destroy_host(eht_host); } static void br_multicast_del_eht_set(struct net_bridge_group_eht_set *eht_set) { struct net_bridge_group_eht_set_entry *set_h; struct rb_node *node; while ((node = rb_first(&eht_set->entry_tree))) { set_h = rb_entry(node, struct net_bridge_group_eht_set_entry, rb_node); __eht_del_set_entry(set_h); } rb_erase(&eht_set->rb_node, &eht_set->pg->eht_set_tree); RB_CLEAR_NODE(&eht_set->rb_node); hlist_add_head(&eht_set->mcast_gc.gc_node, &eht_set->br->mcast_gc_list); queue_work(system_long_wq, &eht_set->br->mcast_gc_work); } void br_multicast_eht_clean_sets(struct net_bridge_port_group *pg) { struct net_bridge_group_eht_set *eht_set; struct rb_node *node; while ((node = rb_first(&pg->eht_set_tree))) { eht_set = rb_entry(node, struct net_bridge_group_eht_set, rb_node); br_multicast_del_eht_set(eht_set); } } static void br_multicast_eht_set_entry_expired(struct timer_list *t) { struct net_bridge_group_eht_set_entry *set_h = timer_container_of(set_h, t, timer); struct net_bridge *br = set_h->br; spin_lock(&br->multicast_lock); if (RB_EMPTY_NODE(&set_h->rb_node) || timer_pending(&set_h->timer)) goto out; br_multicast_del_eht_set_entry(set_h->eht_set->pg, &set_h->eht_set->src_addr, &set_h->h_addr); out: spin_unlock(&br->multicast_lock); } static void br_multicast_eht_set_expired(struct timer_list *t) { struct net_bridge_group_eht_set *eht_set = timer_container_of(eht_set, t, timer); struct net_bridge *br = eht_set->br; spin_lock(&br->multicast_lock); if (RB_EMPTY_NODE(&eht_set->rb_node) || timer_pending(&eht_set->timer)) goto out; br_multicast_del_eht_set(eht_set); out: spin_unlock(&br->multicast_lock); } static struct net_bridge_group_eht_host * __eht_lookup_create_host(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, unsigned char filter_mode) { struct rb_node **link = &pg->eht_host_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_host *eht_host; while (*link) { struct net_bridge_group_eht_host *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_host, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } if (br_multicast_eht_hosts_over_limit(pg)) return NULL; eht_host = kzalloc(sizeof(*eht_host), GFP_ATOMIC); if (!eht_host) return NULL; memcpy(&eht_host->h_addr, h_addr, sizeof(*h_addr)); INIT_HLIST_HEAD(&eht_host->set_entries); eht_host->pg = pg; eht_host->filter_mode = filter_mode; rb_link_node(&eht_host->rb_node, parent, link); rb_insert_color(&eht_host->rb_node, &pg->eht_host_tree); br_multicast_eht_hosts_inc(pg); return eht_host; } static struct net_bridge_group_eht_set_entry * __eht_lookup_create_set_entry(struct net_bridge *br, struct net_bridge_group_eht_set *eht_set, struct net_bridge_group_eht_host *eht_host, bool allow_zero_src) { struct rb_node **link = &eht_set->entry_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_set_entry *set_h; while (*link) { struct net_bridge_group_eht_set_entry *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_set_entry, rb_node); result = memcmp(&eht_host->h_addr, &this->h_addr, sizeof(union net_bridge_eht_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } /* always allow auto-created zero entry */ if (!allow_zero_src && eht_host->num_entries >= PG_SRC_ENT_LIMIT) return NULL; set_h = kzalloc(sizeof(*set_h), GFP_ATOMIC); if (!set_h) return NULL; memcpy(&set_h->h_addr, &eht_host->h_addr, sizeof(union net_bridge_eht_addr)); set_h->mcast_gc.destroy = br_multicast_destroy_eht_set_entry; set_h->eht_set = eht_set; set_h->h_parent = eht_host; set_h->br = br; timer_setup(&set_h->timer, br_multicast_eht_set_entry_expired, 0); hlist_add_head(&set_h->host_list, &eht_host->set_entries); rb_link_node(&set_h->rb_node, parent, link); rb_insert_color(&set_h->rb_node, &eht_set->entry_tree); /* we must not count the auto-created zero entry otherwise we won't be * able to track the full list of PG_SRC_ENT_LIMIT entries */ if (!allow_zero_src) eht_host->num_entries++; return set_h; } static struct net_bridge_group_eht_set * __eht_lookup_create_set(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr) { struct rb_node **link = &pg->eht_set_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_set *eht_set; while (*link) { struct net_bridge_group_eht_set *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_set, rb_node); result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } eht_set = kzalloc(sizeof(*eht_set), GFP_ATOMIC); if (!eht_set) return NULL; memcpy(&eht_set->src_addr, src_addr, sizeof(*src_addr)); eht_set->mcast_gc.destroy = br_multicast_destroy_eht_set; eht_set->pg = pg; eht_set->br = pg->key.port->br; eht_set->entry_tree = RB_ROOT; timer_setup(&eht_set->timer, br_multicast_eht_set_expired, 0); rb_link_node(&eht_set->rb_node, parent, link); rb_insert_color(&eht_set->rb_node, &pg->eht_set_tree); return eht_set; } static void br_multicast_ip_src_to_eht_addr(const struct br_ip *src, union net_bridge_eht_addr *dest) { switch (src->proto) { case htons(ETH_P_IP): dest->ip4 = src->src.ip4; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): memcpy(&dest->ip6, &src->src.ip6, sizeof(struct in6_addr)); break; #endif } } static void br_eht_convert_host_filter_mode(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, int filter_mode) { struct net_bridge_group_eht_host *eht_host; union net_bridge_eht_addr zero_addr; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (eht_host) eht_host->filter_mode = filter_mode; memset(&zero_addr, 0, sizeof(zero_addr)); switch (filter_mode) { case MCAST_INCLUDE: br_multicast_del_eht_set_entry(pg, &zero_addr, h_addr); break; case MCAST_EXCLUDE: br_multicast_create_eht_set_entry(brmctx, pg, &zero_addr, h_addr, MCAST_EXCLUDE, true); break; } } static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, bool allow_zero_src) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_host *eht_host; struct net_bridge *br = pg->key.port->br; struct net_bridge_group_eht_set *eht_set; union net_bridge_eht_addr zero_addr; memset(&zero_addr, 0, sizeof(zero_addr)); if (!allow_zero_src && !memcmp(src_addr, &zero_addr, sizeof(zero_addr))) return; eht_set = __eht_lookup_create_set(pg, src_addr); if (!eht_set) return; eht_host = __eht_lookup_create_host(pg, h_addr, filter_mode); if (!eht_host) goto fail_host; set_h = __eht_lookup_create_set_entry(br, eht_set, eht_host, allow_zero_src); if (!set_h) goto fail_set_entry; mod_timer(&set_h->timer, jiffies + br_multicast_gmi(brmctx)); mod_timer(&eht_set->timer, jiffies + br_multicast_gmi(brmctx)); return; fail_set_entry: if (hlist_empty(&eht_host->set_entries)) __eht_destroy_host(eht_host); fail_host: if (RB_EMPTY_ROOT(&eht_set->entry_tree)) br_multicast_del_eht_set(eht_set); } static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_set *eht_set; bool set_deleted = false; eht_set = br_multicast_eht_set_lookup(pg, src_addr); if (!eht_set) goto out; set_h = br_multicast_eht_set_entry_lookup(eht_set, h_addr); if (!set_h) goto out; __eht_del_set_entry(set_h); if (RB_EMPTY_ROOT(&eht_set->entry_tree)) { br_multicast_del_eht_set(eht_set); set_deleted = true; } out: return set_deleted; } static void br_multicast_del_eht_host(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_host *eht_host; struct hlist_node *tmp; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (!eht_host) return; hlist_for_each_entry_safe(set_h, tmp, &eht_host->set_entries, host_list) br_multicast_del_eht_set_entry(set_h->eht_set->pg, &set_h->eht_set->src_addr, &set_h->h_addr); } /* create new set entries from reports */ static void __eht_create_set_entries(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int filter_mode) { union net_bridge_eht_addr eht_src_addr; u32 src_idx; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); br_multicast_create_eht_set_entry(brmctx, pg, &eht_src_addr, h_addr, filter_mode, false); } } /* delete existing set entries and their (S,G) entries if they were the last */ static bool __eht_del_set_entries(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { union net_bridge_eht_addr eht_src_addr; struct net_bridge_group_src *src_ent; bool changed = false; struct br_ip src_ip; u32 src_idx; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, h_addr)) continue; memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); src_ent = br_multicast_find_group_src(pg, &src_ip); if (!src_ent) continue; br_multicast_del_group_src(src_ent, true); changed = true; } return changed; } static bool br_multicast_eht_allow(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { bool changed = false; switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE); break; case MCAST_EXCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, addr_size); break; } return changed; } static bool br_multicast_eht_block(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { bool changed = false; switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, addr_size); break; case MCAST_EXCLUDE: __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE); break; } return changed; } /* flush_entries is true when changing mode */ static bool __eht_inc_exc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, unsigned char filter_mode, bool to_report) { bool changed = false, flush_entries = to_report; union net_bridge_eht_addr eht_src_addr; if (br_multicast_eht_host_filter_mode(pg, h_addr) != filter_mode) flush_entries = true; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); /* if we're changing mode del host and its entries */ if (flush_entries) br_multicast_del_eht_host(pg, h_addr); __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, filter_mode); /* we can be missing sets only if we've deleted some entries */ if (flush_entries) { struct net_bridge_group_eht_set *eht_set; struct net_bridge_group_src *src_ent; struct hlist_node *tmp; hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { br_multicast_ip_src_to_eht_addr(&src_ent->addr, &eht_src_addr); if (!br_multicast_eht_set_lookup(pg, &eht_src_addr)) { br_multicast_del_group_src(src_ent, true); changed = true; continue; } /* this is an optimization for TO_INCLUDE where we lower * the set's timeout to LMQT to catch timeout hosts: * - host A (timing out): set entries X, Y * - host B: set entry Z (new from current TO_INCLUDE) * sends BLOCK Z after LMQT but host A's EHT * entries still exist (unless lowered to LMQT * so they can timeout with the S,Gs) * => we wait another LMQT, when we can just delete the * group immediately */ if (!(src_ent->flags & BR_SGRP_F_SEND) || filter_mode != MCAST_INCLUDE || !to_report) continue; eht_set = br_multicast_eht_set_lookup(pg, &eht_src_addr); if (!eht_set) continue; mod_timer(&eht_set->timer, jiffies + br_multicast_lmqt(brmctx)); } } return changed; } static bool br_multicast_eht_inc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, bool to_report) { bool changed; changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE, to_report); br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_INCLUDE); return changed; } static bool br_multicast_eht_exc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, bool to_report) { bool changed; changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE, to_report); br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_EXCLUDE); return changed; } static bool __eht_ip4_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, int grec_type) { bool changed = false, to_report = false; switch (grec_type) { case IGMPV3_ALLOW_NEW_SOURCES: br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_BLOCK_OLD_SOURCES: changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_INCLUDE: changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; case IGMPV3_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_EXCLUDE: changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; } return changed; } #if IS_ENABLED(CONFIG_IPV6) static bool __eht_ip6_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, int grec_type) { bool changed = false, to_report = false; switch (grec_type) { case MLD2_ALLOW_NEW_SOURCES: br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_BLOCK_OLD_SOURCES: changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_INCLUDE: changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; case MLD2_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_EXCLUDE: changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; } return changed; } #endif /* true means an entry was deleted */ bool br_multicast_eht_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool eht_enabled = !!(pg->key.port->flags & BR_MULTICAST_FAST_LEAVE); union net_bridge_eht_addr eht_host_addr; bool changed = false; if (!eht_enabled) goto out; memset(&eht_host_addr, 0, sizeof(eht_host_addr)); memcpy(&eht_host_addr, h_addr, addr_size); if (addr_size == sizeof(__be32)) changed = __eht_ip4_handle(brmctx, pg, &eht_host_addr, srcs, nsrcs, grec_type); #if IS_ENABLED(CONFIG_IPV6) else changed = __eht_ip6_handle(brmctx, pg, &eht_host_addr, srcs, nsrcs, grec_type); #endif out: return changed; } int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, u32 eht_hosts_limit) { struct net_bridge *br = p->br; if (!eht_hosts_limit) return -EINVAL; spin_lock_bh(&br->multicast_lock); p->multicast_eht_hosts_limit = eht_hosts_limit; spin_unlock_bh(&br->multicast_lock); return 0; } |
| 80 80 80 80 80 80 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * smc_sysctl.c: sysctl interface to SMC subsystem. * * Copyright (c) 2022, Alibaba Inc. * * Author: Tony Lu <tonylu@linux.alibaba.com> * */ #include <linux/init.h> #include <linux/sysctl.h> #include <net/net_namespace.h> #include "smc.h" #include "smc_core.h" #include "smc_llc.h" #include "smc_sysctl.h" static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; static int max_sndbuf = INT_MAX / 2; static int max_rcvbuf = INT_MAX / 2; static const int net_smc_wmem_init = (64 * 1024); static const int net_smc_rmem_init = (64 * 1024); static int links_per_lgr_min = SMC_LINKS_ADD_LNK_MIN; static int links_per_lgr_max = SMC_LINKS_ADD_LNK_MAX; static int conns_per_lgr_min = SMC_CONN_PER_LGR_MIN; static int conns_per_lgr_max = SMC_CONN_PER_LGR_MAX; static struct ctl_table smc_table[] = { { .procname = "autocorking_size", .data = &init_net.smc.sysctl_autocorking_size, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec, }, { .procname = "smcr_buf_type", .data = &init_net.smc.sysctl_smcr_buf_type, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "smcr_testlink_time", .data = &init_net.smc.sysctl_smcr_testlink_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "wmem", .data = &init_net.smc.sysctl_wmem, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, .extra2 = &max_sndbuf, }, { .procname = "rmem", .data = &init_net.smc.sysctl_rmem, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, .extra2 = &max_rcvbuf, }, { .procname = "smcr_max_links_per_lgr", .data = &init_net.smc.sysctl_max_links_per_lgr, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &links_per_lgr_min, .extra2 = &links_per_lgr_max, }, { .procname = "smcr_max_conns_per_lgr", .data = &init_net.smc.sysctl_max_conns_per_lgr, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &conns_per_lgr_min, .extra2 = &conns_per_lgr_max, }, { .procname = "limit_smc_hs", .data = &init_net.smc.limit_smc_hs, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; int __net_init smc_sysctl_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(smc_table); struct ctl_table *table; table = smc_table; if (!net_eq(net, &init_net)) { int i; table = kmemdup(table, sizeof(smc_table), GFP_KERNEL); if (!table) goto err_alloc; for (i = 0; i < table_size; i++) table[i].data += (void *)net - (void *)&init_net; } net->smc.smc_hdr = register_net_sysctl_sz(net, "net/smc", table, table_size); if (!net->smc.smc_hdr) goto err_reg; net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER; net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER; /* disable handshake limitation by default */ net->smc.limit_smc_hs = 0; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } void __net_exit smc_sysctl_net_exit(struct net *net) { const struct ctl_table *table; table = net->smc.smc_hdr->ctl_table_arg; unregister_net_sysctl_table(net->smc.smc_hdr); if (!net_eq(net, &init_net)) kfree(table); } |
| 10 10 10 10 10 24 24 24 24 24 24 24 24 24 10 10 24 24 24 24 24 24 24 24 10 10 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 |