| 3 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Sound core. This file is composed of two parts. sound_class * which is common to both OSS and ALSA and OSS sound core which * is used OSS or emulation of it. */ /* * First, the common part. */ #include <linux/module.h> #include <linux/device.h> #include <linux/err.h> #include <linux/kdev_t.h> #include <linux/major.h> #include <sound/core.h> #ifdef CONFIG_SOUND_OSS_CORE static int __init init_oss_soundcore(void); static void cleanup_oss_soundcore(void); #else static inline int init_oss_soundcore(void) { return 0; } static inline void cleanup_oss_soundcore(void) { } #endif MODULE_DESCRIPTION("Core sound module"); MODULE_AUTHOR("Alan Cox"); MODULE_LICENSE("GPL"); static char *sound_devnode(const struct device *dev, umode_t *mode) { if (MAJOR(dev->devt) == SOUND_MAJOR) return NULL; return kasprintf(GFP_KERNEL, "snd/%s", dev_name(dev)); } const struct class sound_class = { .name = "sound", .devnode = sound_devnode, }; EXPORT_SYMBOL(sound_class); static int __init init_soundcore(void) { int rc; rc = init_oss_soundcore(); if (rc) return rc; rc = class_register(&sound_class); if (rc) { cleanup_oss_soundcore(); return rc; } return 0; } static void __exit cleanup_soundcore(void) { cleanup_oss_soundcore(); class_unregister(&sound_class); } subsys_initcall(init_soundcore); module_exit(cleanup_soundcore); #ifdef CONFIG_SOUND_OSS_CORE /* * OSS sound core handling. Breaks out sound functions to submodules * * Author: Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * -------------------- * * Top level handler for the sound subsystem. Various devices can * plug into this. The fact they don't all go via OSS doesn't mean * they don't have to implement the OSS API. There is a lot of logic * to keeping much of the OSS weight out of the code in a compatibility * module, but it's up to the driver to rember to load it... * * The code provides a set of functions for registration of devices * by type. This is done rather than providing a single call so that * we can hide any future changes in the internals (eg when we go to * 32bit dev_t) from the modules and their interface. * * Secondly we need to allocate the dsp, dsp16 and audio devices as * one. Thus we misuse the chains a bit to simplify this. * * Thirdly to make it more fun and for 2.3.x and above we do all * of this using fine grained locking. * * FIXME: we have to resolve modules and fine grained load/unload * locking at some point in 2.3.x. */ #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sound.h> #include <linux/kmod.h> #define SOUND_STEP 16 struct sound_unit { int unit_minor; const struct file_operations *unit_fops; struct sound_unit *next; char name[32]; }; /* * By default, OSS sound_core claims full legacy minor range (0-255) * of SOUND_MAJOR to trap open attempts to any sound minor and * requests modules using custom sound-slot/service-* module aliases. * The only benefit of doing this is allowing use of custom module * aliases instead of the standard char-major-* ones. This behavior * prevents alternative OSS implementation and is scheduled to be * removed. * * CONFIG_SOUND_OSS_CORE_PRECLAIM and soundcore.preclaim_oss kernel * parameter are added to allow distros and developers to try and * switch to alternative implementations without needing to rebuild * the kernel in the meantime. If preclaim_oss is non-zero, the * kernel will behave the same as before. All SOUND_MAJOR minors are * preclaimed and the custom module aliases along with standard chrdev * ones are emitted if a missing device is opened. If preclaim_oss is * zero, sound_core only grabs what's actually in use and for missing * devices only the standard chrdev aliases are requested. * * All these clutters are scheduled to be removed along with * sound-slot/service-* module aliases. */ static int preclaim_oss = IS_ENABLED(CONFIG_SOUND_OSS_CORE_PRECLAIM); module_param(preclaim_oss, int, 0444); static int soundcore_open(struct inode *, struct file *); static const struct file_operations soundcore_fops = { /* We must have an owner or the module locking fails */ .owner = THIS_MODULE, .open = soundcore_open, .llseek = noop_llseek, }; /* * Low level list operator. Scan the ordered list, find a hole and * join into it. Called with the lock asserted */ static int __sound_insert_unit(struct sound_unit * s, struct sound_unit **list, const struct file_operations *fops, int index, int low, int top) { int n=low; if (index < 0) { /* first free */ while (*list && (*list)->unit_minor<n) list=&((*list)->next); while(n<top) { /* Found a hole ? */ if(*list==NULL || (*list)->unit_minor>n) break; list=&((*list)->next); n+=SOUND_STEP; } if(n>=top) return -ENOENT; } else { n = low+(index*16); while (*list) { if ((*list)->unit_minor==n) return -EBUSY; if ((*list)->unit_minor>n) break; list=&((*list)->next); } } /* * Fill it in */ s->unit_minor=n; s->unit_fops=fops; /* * Link it */ s->next=*list; *list=s; return n; } /* * Remove a node from the chain. Called with the lock asserted */ static struct sound_unit *__sound_remove_unit(struct sound_unit **list, int unit) { while(*list) { struct sound_unit *p=*list; if(p->unit_minor==unit) { *list=p->next; return p; } list=&(p->next); } printk(KERN_ERR "Sound device %d went missing!\n", unit); return NULL; } /* * This lock guards the sound loader list. */ static DEFINE_SPINLOCK(sound_loader_lock); /* * Allocate the controlling structure and add it to the sound driver * list. Acquires locks as needed */ static int sound_insert_unit(struct sound_unit **list, const struct file_operations *fops, int index, int low, int top, const char *name, umode_t mode, struct device *dev) { struct sound_unit *s = kmalloc(sizeof(*s), GFP_KERNEL); int r; if (!s) return -ENOMEM; spin_lock(&sound_loader_lock); retry: r = __sound_insert_unit(s, list, fops, index, low, top); spin_unlock(&sound_loader_lock); if (r < 0) goto fail; else if (r < SOUND_STEP) sprintf(s->name, "sound/%s", name); else sprintf(s->name, "sound/%s%d", name, r / SOUND_STEP); if (!preclaim_oss) { /* * Something else might have grabbed the minor. If * first free slot is requested, rescan with @low set * to the next unit; otherwise, -EBUSY. */ r = __register_chrdev(SOUND_MAJOR, s->unit_minor, 1, s->name, &soundcore_fops); if (r < 0) { spin_lock(&sound_loader_lock); __sound_remove_unit(list, s->unit_minor); if (index < 0) { low = s->unit_minor + SOUND_STEP; goto retry; } spin_unlock(&sound_loader_lock); r = -EBUSY; goto fail; } } device_create(&sound_class, dev, MKDEV(SOUND_MAJOR, s->unit_minor), NULL, "%s", s->name+6); return s->unit_minor; fail: kfree(s); return r; } /* * Remove a unit. Acquires locks as needed. The drivers MUST have * completed the removal before their file operations become * invalid. */ static void sound_remove_unit(struct sound_unit **list, int unit) { struct sound_unit *p; spin_lock(&sound_loader_lock); p = __sound_remove_unit(list, unit); spin_unlock(&sound_loader_lock); if (p) { if (!preclaim_oss) __unregister_chrdev(SOUND_MAJOR, p->unit_minor, 1, p->name); device_destroy(&sound_class, MKDEV(SOUND_MAJOR, p->unit_minor)); kfree(p); } } /* * Allocations * * 0 *16 Mixers * 1 *8 Sequencers * 2 *16 Midi * 3 *16 DSP * 4 *16 SunDSP * 5 *16 DSP16 * 6 -- sndstat (obsolete) * 7 *16 unused * 8 -- alternate sequencer (see above) * 9 *16 raw synthesizer access * 10 *16 unused * 11 *16 unused * 12 *16 unused * 13 *16 unused * 14 *16 unused * 15 *16 unused */ static struct sound_unit *chains[SOUND_STEP]; /** * register_sound_special_device - register a special sound node * @fops: File operations for the driver * @unit: Unit number to allocate * @dev: device pointer * * Allocate a special sound device by minor number from the sound * subsystem. * * Return: The allocated number is returned on success. On failure, * a negative error code is returned. */ int register_sound_special_device(const struct file_operations *fops, int unit, struct device *dev) { const int chain = unit % SOUND_STEP; int max_unit = 256; const char *name; char _name[16]; switch (chain) { case 0: name = "mixer"; break; case 1: name = "sequencer"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 2: name = "midi"; break; case 3: name = "dsp"; break; case 4: name = "audio"; break; case 5: name = "dspW"; break; case 8: name = "sequencer2"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 9: name = "dmmidi"; break; case 10: name = "dmfm"; break; case 12: name = "adsp"; break; case 13: name = "amidi"; break; case 14: name = "admmidi"; break; default: { __unknown: sprintf(_name, "unknown%d", chain); if (unit >= SOUND_STEP) strcat(_name, "-"); name = _name; } break; } return sound_insert_unit(&chains[chain], fops, -1, unit, max_unit, name, 0600, dev); } EXPORT_SYMBOL(register_sound_special_device); int register_sound_special(const struct file_operations *fops, int unit) { return register_sound_special_device(fops, unit, NULL); } EXPORT_SYMBOL(register_sound_special); /** * register_sound_mixer - register a mixer device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a mixer device. Unit is the number of the mixer requested. * Pass -1 to request the next free mixer unit. * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_mixer(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[0], fops, dev, 0, 128, "mixer", 0600, NULL); } EXPORT_SYMBOL(register_sound_mixer); /* * DSP's are registered as a triple. Register only one and cheat * in open - see below. */ /** * register_sound_dsp - register a DSP device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a DSP device. Unit is the number of the DSP requested. * Pass -1 to request the next free DSP unit. * * This function allocates both the audio and dsp device entries together * and will always allocate them as a matching pair - eg dsp3/audio3 * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_dsp(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[3], fops, dev, 3, 131, "dsp", 0600, NULL); } EXPORT_SYMBOL(register_sound_dsp); /** * unregister_sound_special - unregister a special sound device * @unit: unit number to allocate * * Release a sound device that was allocated with * register_sound_special(). The unit passed is the return value from * the register function. */ void unregister_sound_special(int unit) { sound_remove_unit(&chains[unit % SOUND_STEP], unit); } EXPORT_SYMBOL(unregister_sound_special); /** * unregister_sound_mixer - unregister a mixer * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_mixer(). * The unit passed is the return value from the register function. */ void unregister_sound_mixer(int unit) { sound_remove_unit(&chains[0], unit); } EXPORT_SYMBOL(unregister_sound_mixer); /** * unregister_sound_dsp - unregister a DSP device * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_dsp(). * The unit passed is the return value from the register function. * * Both of the allocated units are released together automatically. */ void unregister_sound_dsp(int unit) { sound_remove_unit(&chains[3], unit); } EXPORT_SYMBOL(unregister_sound_dsp); static struct sound_unit *__look_for_unit(int chain, int unit) { struct sound_unit *s; s=chains[chain]; while(s && s->unit_minor <= unit) { if(s->unit_minor==unit) return s; s=s->next; } return NULL; } static int soundcore_open(struct inode *inode, struct file *file) { int chain; int unit = iminor(inode); struct sound_unit *s; const struct file_operations *new_fops = NULL; chain=unit&0x0F; if(chain==4 || chain==5) /* dsp/audio/dsp16 */ { unit&=0xF0; unit|=3; chain=3; } spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); if (preclaim_oss && !new_fops) { spin_unlock(&sound_loader_lock); /* * Please, don't change this order or code. * For ALSA slot means soundcard and OSS emulation code * comes as add-on modules which aren't depend on * ALSA toplevel modules for soundcards, thus we need * load them at first. [Jaroslav Kysela <perex@jcu.cz>] */ request_module("sound-slot-%i", unit>>4); request_module("sound-service-%i-%i", unit>>4, chain); /* * sound-slot/service-* module aliases are scheduled * for removal in favor of the standard char-major-* * module aliases. For the time being, generate both * the legacy and standard module aliases to ease * transition. */ if (request_module("char-major-%d-%d", SOUND_MAJOR, unit) > 0) request_module("char-major-%d", SOUND_MAJOR); spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); } spin_unlock(&sound_loader_lock); if (!new_fops) return -ENODEV; /* * We rely upon the fact that we can't be unloaded while the * subdriver is there. */ replace_fops(file, new_fops); if (!file->f_op->open) return -ENODEV; return file->f_op->open(inode, file); } MODULE_ALIAS_CHARDEV_MAJOR(SOUND_MAJOR); static void cleanup_oss_soundcore(void) { /* We have nothing to really do here - we know the lists must be empty */ unregister_chrdev(SOUND_MAJOR, "sound"); } static int __init init_oss_soundcore(void) { if (preclaim_oss && register_chrdev(SOUND_MAJOR, "sound", &soundcore_fops) < 0) { printk(KERN_ERR "soundcore: sound device already in use.\n"); return -EBUSY; } return 0; } #endif /* CONFIG_SOUND_OSS_CORE */ |
| 4 4 4 4 4 4 4 1 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 | /* * This file implement the Wireless Extensions proc API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ /* * The /proc/net/wireless file is a human readable user-space interface * exporting various wireless specific statistics from the wireless devices. * This is the most popular part of the Wireless Extensions ;-) * * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). * The content of the file is basically the content of "struct iw_statistics". */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/wireless.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/iw_handler.h> #include <net/wext.h> static void wireless_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); static struct iw_statistics nullstats = {}; /* show device if it's wireless regardless of current stats */ if (!stats) { #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) stats = &nullstats; #endif #ifdef CONFIG_CFG80211 if (dev->ieee80211_ptr) stats = &nullstats; #endif } if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " "%6d %6d %6d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & IW_QUAL_QUAL_UPDATED ? '.' : ' ', ((__s32) stats->qual.level) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_LEVEL_UPDATED ? '.' : ' ', ((__s32) stats->qual.noise) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_NOISE_UPDATED ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); if (stats != &nullstats) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } /* ---------------------------------------------------------------- */ /* * Print info for /proc/net/wireless (print all entries) */ static int wireless_dev_seq_show(struct seq_file *seq, void *v) { might_sleep(); if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" " face | tus | link level noise | nwid " "crypt frag retry misc | beacon | %d\n", WIRELESS_EXT); else wireless_seq_printf_stats(seq, v); return 0; } static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; rtnl_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; for_each_netdev(net, dev) if (off++ == *pos) return dev; return NULL; } static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); ++*pos; return v == SEQ_START_TOKEN ? first_net_device(net) : next_net_device(v); } static void wireless_dev_seq_stop(struct seq_file *seq, void *v) { rtnl_unlock(); } static const struct seq_operations wireless_seq_ops = { .start = wireless_dev_seq_start, .next = wireless_dev_seq_next, .stop = wireless_dev_seq_stop, .show = wireless_dev_seq_show, }; int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_create_net("wireless", 0444, net->proc_net, &wireless_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } void __net_exit wext_proc_exit(struct net *net) { remove_proc_entry("wireless", net->proc_net); } |
| 5 5 3 1 1 1 1 2 5 5 5 5 5 1 5 5 5 3 2 3 2 2 3 3 3 5 5 5 3 3 5 5 5 4 4 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to mapping data to requests */ #include <linux/kernel.h> #include <linux/sched/task_stack.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/uio.h> #include "blk.h" struct bio_map_data { bool is_our_pages : 1; bool is_null_mapped : 1; struct iov_iter iter; struct iovec iov[]; }; static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data, gfp_t gfp_mask) { struct bio_map_data *bmd; if (data->nr_segs > UIO_MAXIOV) return NULL; bmd = kmalloc(struct_size(bmd, iov, data->nr_segs), gfp_mask); if (!bmd) return NULL; bmd->iter = *data; if (iter_is_iovec(data)) { memcpy(bmd->iov, iter_iov(data), sizeof(struct iovec) * data->nr_segs); bmd->iter.__iov = bmd->iov; } return bmd; } /** * bio_copy_from_iter - copy all pages from iov_iter to bio * @bio: The &struct bio which describes the I/O as destination * @iter: iov_iter as source * * Copy all pages from iov_iter to bio. * Returns 0 on success, or error on failure. */ static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { ssize_t ret; ret = copy_page_from_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, iter); if (!iov_iter_count(iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; } /** * bio_copy_to_iter - copy all pages from bio to iov_iter * @bio: The &struct bio which describes the I/O as source * @iter: iov_iter as destination * * Copy all pages from bio to iov_iter. * Returns 0 on success, or error on failure. */ static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { ssize_t ret; ret = copy_page_to_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, &iter); if (!iov_iter_count(&iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; } /** * bio_uncopy_user - finish previously mapped bio * @bio: bio being terminated * * Free pages allocated from bio_copy_user_iov() and write back data * to user space in case of a read. */ static int bio_uncopy_user(struct bio *bio) { struct bio_map_data *bmd = bio->bi_private; int ret = 0; if (!bmd->is_null_mapped) { /* * if we're in a workqueue, the request is orphaned, so * don't copy into a random user address space, just free * and return -EINTR so user space doesn't expect any data. */ if (!current->mm) ret = -EINTR; else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); } kfree(bmd); return ret; } static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, struct iov_iter *iter, gfp_t gfp_mask) { struct bio_map_data *bmd; struct page *page; struct bio *bio; int i = 0, ret; int nr_pages; unsigned int len = iter->count; unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0; bmd = bio_alloc_map_data(iter, gfp_mask); if (!bmd) return -ENOMEM; /* * We need to do a deep copy of the iov_iter including the iovecs. * The caller provided iov might point to an on-stack or otherwise * shortlived one. */ bmd->is_our_pages = !map_data; bmd->is_null_mapped = (map_data && map_data->null_mapped); nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE)); ret = -ENOMEM; bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) goto out_bmd; bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq)); if (map_data) { nr_pages = 1U << map_data->page_order; i = map_data->offset / PAGE_SIZE; } while (len) { unsigned int bytes = PAGE_SIZE; bytes -= offset; if (bytes > len) bytes = len; if (map_data) { if (i == map_data->nr_entries * nr_pages) { ret = -ENOMEM; goto cleanup; } page = map_data->pages[i / nr_pages]; page += (i % nr_pages); i++; } else { page = alloc_page(GFP_NOIO | gfp_mask); if (!page) { ret = -ENOMEM; goto cleanup; } } if (bio_add_pc_page(rq->q, bio, page, bytes, offset) < bytes) { if (!map_data) __free_page(page); break; } len -= bytes; offset = 0; } if (map_data) map_data->offset += bio->bi_iter.bi_size; /* * success */ if (iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) { ret = bio_copy_from_iter(bio, iter); if (ret) goto cleanup; } else if (map_data && map_data->from_user) { struct iov_iter iter2 = *iter; /* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */ iter2.data_source = ITER_SOURCE; ret = bio_copy_from_iter(bio, &iter2); if (ret) goto cleanup; } else { if (bmd->is_our_pages) zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } bio->bi_private = bmd; ret = blk_rq_append_bio(rq, bio); if (ret) goto cleanup; return 0; cleanup: if (!map_data) bio_free_pages(bio); bio_uninit(bio); kfree(bio); out_bmd: kfree(bmd); return ret; } static void blk_mq_map_bio_put(struct bio *bio) { if (bio->bi_opf & REQ_ALLOC_CACHE) { bio_put(bio); } else { bio_uninit(bio); kfree(bio); } } static struct bio *blk_rq_map_bio_alloc(struct request *rq, unsigned int nr_vecs, gfp_t gfp_mask) { struct bio *bio; if (rq->cmd_flags & REQ_ALLOC_CACHE && (nr_vecs <= BIO_INLINE_VECS)) { bio = bio_alloc_bioset(NULL, nr_vecs, rq->cmd_flags, gfp_mask, &fs_bio_set); if (!bio) return NULL; } else { bio = bio_kmalloc(nr_vecs, gfp_mask); if (!bio) return NULL; bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq)); } return bio; } static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { iov_iter_extraction_t extraction_flags = 0; unsigned int max_sectors = queue_max_hw_sectors(rq->q); unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); struct bio *bio; int ret; int j; if (!iov_iter_count(iter)) return -EINVAL; bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); if (bio == NULL) return -ENOMEM; if (blk_queue_pci_p2pdma(rq->q)) extraction_flags |= ITER_ALLOW_P2PDMA; if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); while (iov_iter_count(iter)) { struct page *stack_pages[UIO_FASTIOV]; struct page **pages = stack_pages; ssize_t bytes; size_t offs; int npages; if (nr_vecs > ARRAY_SIZE(stack_pages)) pages = NULL; bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX, nr_vecs, extraction_flags, &offs); if (unlikely(bytes <= 0)) { ret = bytes ? bytes : -EFAULT; goto out_unmap; } npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE); if (unlikely(offs & queue_dma_alignment(rq->q))) j = 0; else { for (j = 0; j < npages; j++) { struct page *page = pages[j]; unsigned int n = PAGE_SIZE - offs; bool same_page = false; if (n > bytes) n = bytes; if (!bio_add_hw_page(rq->q, bio, page, n, offs, max_sectors, &same_page)) break; if (same_page) bio_release_page(bio, page); bytes -= n; offs = 0; } } /* * release the pages we didn't map into the bio, if any */ while (j < npages) bio_release_page(bio, pages[j++]); if (pages != stack_pages) kvfree(pages); /* couldn't stuff something into bio? */ if (bytes) { iov_iter_revert(iter, bytes); break; } } ret = blk_rq_append_bio(rq, bio); if (ret) goto out_unmap; return 0; out_unmap: bio_release_pages(bio, false); blk_mq_map_bio_put(bio); return ret; } static void bio_invalidate_vmalloc_pages(struct bio *bio) { #ifdef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE if (bio->bi_private && !op_is_write(bio_op(bio))) { unsigned long i, len = 0; for (i = 0; i < bio->bi_vcnt; i++) len += bio->bi_io_vec[i].bv_len; invalidate_kernel_vmap_range(bio->bi_private, len); } #endif } static void bio_map_kern_endio(struct bio *bio) { bio_invalidate_vmalloc_pages(bio); bio_uninit(bio); kfree(bio); } /** * bio_map_kern - map kernel address into bio * @q: the struct request_queue for the bio * @data: pointer to buffer to map * @len: length in bytes * @gfp_mask: allocation flags for bio allocation * * Map the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ static struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len, gfp_t gfp_mask) { unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = kaddr >> PAGE_SHIFT; const int nr_pages = end - start; bool is_vmalloc = is_vmalloc_addr(data); struct page *page; int offset, i; struct bio *bio; bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); if (is_vmalloc) { flush_kernel_vmap_range(data, len); bio->bi_private = data; } offset = offset_in_page(kaddr); for (i = 0; i < nr_pages; i++) { unsigned int bytes = PAGE_SIZE - offset; if (len <= 0) break; if (bytes > len) bytes = len; if (!is_vmalloc) page = virt_to_page(data); else page = vmalloc_to_page(data); if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { /* we don't support partial mappings */ bio_uninit(bio); kfree(bio); return ERR_PTR(-EINVAL); } data += bytes; len -= bytes; offset = 0; } bio->bi_end_io = bio_map_kern_endio; return bio; } static void bio_copy_kern_endio(struct bio *bio) { bio_free_pages(bio); bio_uninit(bio); kfree(bio); } static void bio_copy_kern_endio_read(struct bio *bio) { char *p = bio->bi_private; struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { memcpy_from_bvec(p, bvec); p += bvec->bv_len; } bio_copy_kern_endio(bio); } /** * bio_copy_kern - copy kernel address into bio * @q: the struct request_queue for the bio * @data: pointer to buffer to copy * @len: length in bytes * @gfp_mask: allocation flags for bio and page allocation * @reading: data direction is READ * * copy the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ static struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len, gfp_t gfp_mask, int reading) { unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = kaddr >> PAGE_SHIFT; struct bio *bio; void *p = data; int nr_pages = 0; /* * Overflow, abort */ if (end < start) return ERR_PTR(-EINVAL); nr_pages = end - start; bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); while (len) { struct page *page; unsigned int bytes = PAGE_SIZE; if (bytes > len) bytes = len; page = alloc_page(GFP_NOIO | __GFP_ZERO | gfp_mask); if (!page) goto cleanup; if (!reading) memcpy(page_address(page), p, bytes); if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) break; len -= bytes; p += bytes; } if (reading) { bio->bi_end_io = bio_copy_kern_endio_read; bio->bi_private = data; } else { bio->bi_end_io = bio_copy_kern_endio; } return bio; cleanup: bio_free_pages(bio); bio_uninit(bio); kfree(bio); return ERR_PTR(-ENOMEM); } /* * Append a bio to a passthrough request. Only works if the bio can be merged * into the request based on the driver constraints. */ int blk_rq_append_bio(struct request *rq, struct bio *bio) { struct bvec_iter iter; struct bio_vec bv; unsigned int nr_segs = 0; bio_for_each_bvec(bv, bio, iter) nr_segs++; if (!rq->bio) { blk_rq_bio_prep(rq, bio, nr_segs); } else { if (!ll_back_merge_fn(rq, bio, nr_segs)) return -EINVAL; rq->biotail->bi_next = bio; rq->biotail = bio; rq->__data_len += (bio)->bi_iter.bi_size; bio_crypt_free_ctx(bio); } return 0; } EXPORT_SYMBOL(blk_rq_append_bio); /* Prepare bio for passthrough IO given ITER_BVEC iter */ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) { struct request_queue *q = rq->q; size_t nr_iter = iov_iter_count(iter); size_t nr_segs = iter->nr_segs; struct bio_vec *bvecs, *bvprvp = NULL; const struct queue_limits *lim = &q->limits; unsigned int nsegs = 0, bytes = 0; struct bio *bio; size_t i; if (!nr_iter || (nr_iter >> SECTOR_SHIFT) > queue_max_hw_sectors(q)) return -EINVAL; if (nr_segs > queue_max_segments(q)) return -EINVAL; /* no iovecs to alloc, as we already have a BVEC iterator */ bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL); if (bio == NULL) return -ENOMEM; bio_iov_bvec_set(bio, (struct iov_iter *)iter); blk_rq_bio_prep(rq, bio, nr_segs); /* loop to perform a bunch of sanity checks */ bvecs = (struct bio_vec *)iter->bvec; for (i = 0; i < nr_segs; i++) { struct bio_vec *bv = &bvecs[i]; /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, fallback to copy. */ if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv->bv_offset)) { blk_mq_map_bio_put(bio); return -EREMOTEIO; } /* check full condition */ if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len) goto put_bio; if (bytes + bv->bv_len > nr_iter) goto put_bio; if (bv->bv_offset + bv->bv_len > PAGE_SIZE) goto put_bio; nsegs++; bytes += bv->bv_len; bvprvp = bv; } return 0; put_bio: blk_mq_map_bio_put(bio); return -EINVAL; } /** * blk_rq_map_user_iov - map user data to a request, for passthrough requests * @q: request queue where request should be inserted * @rq: request to map data to * @map_data: pointer to the rq_map_data holding pages (if necessary) * @iter: iovec iterator * @gfp_mask: memory allocation flags * * Description: * Data will be mapped directly for zero copy I/O, if possible. Otherwise * a kernel bounce buffer is used. * * A matching blk_rq_unmap_user() must be issued at the end of I/O, while * still in process context. */ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { bool copy = false, map_bvec = false; unsigned long align = blk_lim_dma_alignment_and_pad(&q->limits); struct bio *bio = NULL; struct iov_iter i; int ret = -EINVAL; if (map_data) copy = true; else if (blk_queue_may_bounce(q)) copy = true; else if (iov_iter_alignment(iter) & align) copy = true; else if (iov_iter_is_bvec(iter)) map_bvec = true; else if (!user_backed_iter(iter)) copy = true; else if (queue_virt_boundary(q)) copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter); if (map_bvec) { ret = blk_rq_map_user_bvec(rq, iter); if (!ret) return 0; if (ret != -EREMOTEIO) goto fail; /* fall back to copying the data on limits mismatches */ copy = true; } i = *iter; do { if (copy) ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask); else ret = bio_map_user_iov(rq, &i, gfp_mask); if (ret) goto unmap_rq; if (!bio) bio = rq->bio; } while (iov_iter_count(&i)); return 0; unmap_rq: blk_rq_unmap_user(bio); fail: rq->bio = NULL; return ret; } EXPORT_SYMBOL(blk_rq_map_user_iov); int blk_rq_map_user(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, void __user *ubuf, unsigned long len, gfp_t gfp_mask) { struct iov_iter i; int ret = import_ubuf(rq_data_dir(rq), ubuf, len, &i); if (unlikely(ret < 0)) return ret; return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask); } EXPORT_SYMBOL(blk_rq_map_user); int blk_rq_map_user_io(struct request *req, struct rq_map_data *map_data, void __user *ubuf, unsigned long buf_len, gfp_t gfp_mask, bool vec, int iov_count, bool check_iter_count, int rw) { int ret = 0; if (vec) { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov = fast_iov; struct iov_iter iter; ret = import_iovec(rw, ubuf, iov_count ? iov_count : buf_len, UIO_FASTIOV, &iov, &iter); if (ret < 0) return ret; if (iov_count) { /* SG_IO howto says that the shorter of the two wins */ iov_iter_truncate(&iter, buf_len); if (check_iter_count && !iov_iter_count(&iter)) { kfree(iov); return -EINVAL; } } ret = blk_rq_map_user_iov(req->q, req, map_data, &iter, gfp_mask); kfree(iov); } else if (buf_len) { ret = blk_rq_map_user(req->q, req, map_data, ubuf, buf_len, gfp_mask); } return ret; } EXPORT_SYMBOL(blk_rq_map_user_io); /** * blk_rq_unmap_user - unmap a request with user data * @bio: start of bio list * * Description: * Unmap a rq previously mapped by blk_rq_map_user(). The caller must * supply the original rq->bio from the blk_rq_map_user() return, since * the I/O completion may have changed rq->bio. */ int blk_rq_unmap_user(struct bio *bio) { struct bio *next_bio; int ret = 0, ret2; while (bio) { if (bio->bi_private) { ret2 = bio_uncopy_user(bio); if (ret2 && !ret) ret = ret2; } else { bio_release_pages(bio, bio_data_dir(bio) == READ); } if (bio_integrity(bio)) bio_integrity_unmap_user(bio); next_bio = bio; bio = bio->bi_next; blk_mq_map_bio_put(next_bio); } return ret; } EXPORT_SYMBOL(blk_rq_unmap_user); /** * blk_rq_map_kern - map kernel data to a request, for passthrough requests * @q: request queue where request should be inserted * @rq: request to fill * @kbuf: the kernel buffer * @len: length of user data * @gfp_mask: memory allocation flags * * Description: * Data will be mapped directly if possible. Otherwise a bounce * buffer is used. Can be called multiple times to append multiple * buffers. */ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { int reading = rq_data_dir(rq) == READ; unsigned long addr = (unsigned long) kbuf; struct bio *bio; int ret; if (len > (queue_max_hw_sectors(q) << 9)) return -EINVAL; if (!len || !kbuf) return -EINVAL; if (!blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf) || blk_queue_may_bounce(q)) bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading); else bio = bio_map_kern(q, kbuf, len, gfp_mask); if (IS_ERR(bio)) return PTR_ERR(bio); bio->bi_opf &= ~REQ_OP_MASK; bio->bi_opf |= req_op(rq); ret = blk_rq_append_bio(rq, bio); if (unlikely(ret)) { bio_uninit(bio); kfree(bio); } return ret; } EXPORT_SYMBOL(blk_rq_map_kern); |
| 3 3 1 1 1 3 3 1 1 1 10 10 10 10 10 2 2 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 1 3 3 2 3 3 1 1 1 2 1 2 2 1 2 1 1 2 1 3 1 2 1 2 3 3 3 3 1 2 1 3 1 3 1 1 1 1 1 1 1 1 2 1 1 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. */ #include <linux/completion.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rbtree.h> #include <linux/igmp.h> #include <linux/xarray.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/module.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netevent.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip_fib.h> #include <net/ip6_route.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> #include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> #include <rdma/iw_cm.h> #include "core_priv.h" #include "cma_priv.h" #include "cma_trace.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("Generic RDMA CM Agent"); MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24) #define CMA_IBOE_PACKET_LIFETIME 16 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", [RDMA_CM_EVENT_ADDR_ERROR] = "address error", [RDMA_CM_EVENT_ROUTE_RESOLVED] = "route resolved ", [RDMA_CM_EVENT_ROUTE_ERROR] = "route error", [RDMA_CM_EVENT_CONNECT_REQUEST] = "connect request", [RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response", [RDMA_CM_EVENT_CONNECT_ERROR] = "connect error", [RDMA_CM_EVENT_UNREACHABLE] = "unreachable", [RDMA_CM_EVENT_REJECTED] = "rejected", [RDMA_CM_EVENT_ESTABLISHED] = "established", [RDMA_CM_EVENT_DISCONNECTED] = "disconnected", [RDMA_CM_EVENT_DEVICE_REMOVAL] = "device removal", [RDMA_CM_EVENT_MULTICAST_JOIN] = "multicast join", [RDMA_CM_EVENT_MULTICAST_ERROR] = "multicast error", [RDMA_CM_EVENT_ADDR_CHANGE] = "address change", [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ? cma_events[index] : "unrecognized event"; } EXPORT_SYMBOL(rdma_event_msg); const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return ibcm_reject_msg(reason); if (rdma_protocol_iwarp(id->device, id->port_num)) return iwcm_reject_msg(reason); WARN_ON_ONCE(1); return "unrecognized transport"; } EXPORT_SYMBOL(rdma_reject_msg); /** * rdma_is_consumer_reject - return true if the consumer rejected the connect * request. * @id: Communication identifier that received the REJECT event. * @reason: Value returned in the REJECT event status field. */ static bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return reason == IB_CM_REJ_CONSUMER_DEFINED; if (rdma_protocol_iwarp(id->device, id->port_num)) return reason == -ECONNREFUSED; WARN_ON_ONCE(1); return false; } const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len) { const void *p; if (rdma_is_consumer_reject(id, ev->status)) { *data_len = ev->param.conn.private_data_len; p = ev->param.conn.private_data; } else { *data_len = 0; p = NULL; } return p; } EXPORT_SYMBOL(rdma_consumer_reject_data); /** * rdma_iw_cm_id() - return the iw_cm_id pointer for this cm_id. * @id: Communication Identifier */ struct iw_cm_id *rdma_iw_cm_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); if (id->device->node_type == RDMA_NODE_RNIC) return id_priv->cm_id.iw; return NULL; } EXPORT_SYMBOL(rdma_iw_cm_id); /** * rdma_res_to_id() - return the rdma_cm_id pointer for this restrack. * @res: rdma resource tracking entry pointer */ struct rdma_cm_id *rdma_res_to_id(struct rdma_restrack_entry *res) { struct rdma_id_private *id_priv = container_of(res, struct rdma_id_private, res); return &id_priv->id; } EXPORT_SYMBOL(rdma_res_to_id); static int cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device, void *client_data); static struct ib_client cma_client = { .name = "cma", .add = cma_add_one, .remove = cma_remove_one }; static struct ib_sa_client sa_client; static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct rb_root id_table = RB_ROOT; /* Serialize operations of id_table tree */ static DEFINE_SPINLOCK(id_table_lock); static struct workqueue_struct *cma_wq; static unsigned int cma_pernet_id; struct cma_pernet { struct xarray tcp_ps; struct xarray udp_ps; struct xarray ipoib_ps; struct xarray ib_ps; }; static struct cma_pernet *cma_pernet(struct net *net) { return net_generic(net, cma_pernet_id); } static struct xarray *cma_pernet_xa(struct net *net, enum rdma_ucm_port_space ps) { struct cma_pernet *pernet = cma_pernet(net); switch (ps) { case RDMA_PS_TCP: return &pernet->tcp_ps; case RDMA_PS_UDP: return &pernet->udp_ps; case RDMA_PS_IPOIB: return &pernet->ipoib_ps; case RDMA_PS_IB: return &pernet->ib_ps; default: return NULL; } } struct id_table_entry { struct list_head id_list; struct rb_node rb_node; }; struct cma_device { struct list_head list; struct ib_device *device; struct completion comp; refcount_t refcount; struct list_head id_list; enum ib_gid_type *default_gid_type; u8 *default_roce_tos; }; struct rdma_bind_list { enum rdma_ucm_port_space ps; struct hlist_head owners; unsigned short port; }; static int cma_ps_alloc(struct net *net, enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_insert(xa, snum, bind_list, GFP_KERNEL); } static struct rdma_bind_list *cma_ps_find(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_load(xa, snum); } static void cma_ps_remove(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); xa_erase(xa, snum); } enum { CMA_OPTION_AFONLY, }; void cma_dev_get(struct cma_device *cma_dev) { refcount_inc(&cma_dev->refcount); } void cma_dev_put(struct cma_device *cma_dev) { if (refcount_dec_and_test(&cma_dev->refcount)) complete(&cma_dev->comp); } struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter filter, void *cookie) { struct cma_device *cma_dev; struct cma_device *found_cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) if (filter(cma_dev->device, cookie)) { found_cma_dev = cma_dev; break; } if (found_cma_dev) cma_dev_get(found_cma_dev); mutex_unlock(&lock); return found_cma_dev; } int cma_get_default_gid_type(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_gid_type(struct cma_device *cma_dev, u32 port, enum ib_gid_type default_gid_type) { unsigned long supported_gids; if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; if (default_gid_type == IB_GID_TYPE_IB && rdma_protocol_roce_eth_encap(cma_dev->device, port)) default_gid_type = IB_GID_TYPE_ROCE; supported_gids = roce_gid_type_mask_support(cma_dev->device, port); if (!(supported_gids & 1 << default_gid_type)) return -EINVAL; cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)] = default_gid_type; return 0; } int cma_get_default_roce_tos(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_roce_tos(struct cma_device *cma_dev, u32 port, u8 default_roce_tos) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] = default_roce_tos; return 0; } struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) { return cma_dev->device; } /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. * We do this by disabling removal notification while a callback is in process, * and reporting it after the callback completes. */ struct cma_multicast { struct rdma_id_private *id_priv; union { struct ib_sa_multicast *sa_mc; struct { struct work_struct work; struct rdma_cm_event event; } iboe_join; }; struct list_head list; void *context; struct sockaddr_storage addr; u8 join_state; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; enum rdma_cm_state old_state; enum rdma_cm_state new_state; struct rdma_cm_event event; }; union cma_ip_addr { struct in6_addr ip6; struct { __be32 pad[3]; __be32 addr; } ip4; }; struct cma_hdr { u8 cma_version; u8 ip_version; /* IP version: 7:4 */ __be16 port; union cma_ip_addr src_addr; union cma_ip_addr dst_addr; }; #define CMA_VERSION 0x00 struct cma_req_info { struct sockaddr_storage listen_addr_storage; struct sockaddr_storage src_addr_storage; struct ib_device *device; union ib_gid local_gid; __be64 service_id; int port; bool has_gid; u16 pkey; }; static int cma_comp_exch(struct rdma_id_private *id_priv, enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; /* * The FSM uses a funny double locking where state is protected by both * the handler_mutex and the spinlock. State is not allowed to change * to/from a handler_mutex protected value without also holding * handler_mutex. */ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT) lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); if ((ret = (id_priv->state == comp))) id_priv->state = exch; spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } static inline u8 cma_get_ip_ver(const struct cma_hdr *hdr) { return hdr->ip_version >> 4; } static void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) { hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } static struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.src_addr; } static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.dst_addr; } static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool join) { struct in_device *in_dev = NULL; if (ndev) { rtnl_lock(); in_dev = __in_dev_get_rtnl(ndev); if (in_dev) { if (join) ip_mc_inc_group(in_dev, *(__be32 *)(mgid->raw + 12)); else ip_mc_dec_group(in_dev, *(__be32 *)(mgid->raw + 12)); } rtnl_unlock(); } return (in_dev) ? 0 : -ENODEV; } static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa, struct id_table_entry *entry_b) { struct rdma_id_private *id_priv = list_first_entry( &entry_b->id_list, struct rdma_id_private, id_list_entry); int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if; struct sockaddr *sb = cma_dst_addr(id_priv); if (ifindex_a != ifindex_b) return (ifindex_a > ifindex_b) ? 1 : -1; if (sa->sa_family != sb->sa_family) return sa->sa_family - sb->sa_family; if (sa->sa_family == AF_INET && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in)) { return memcmp(&((struct sockaddr_in *)sa)->sin_addr, &((struct sockaddr_in *)sb)->sin_addr, sizeof(((struct sockaddr_in *)sa)->sin_addr)); } if (sa->sa_family == AF_INET6 && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in6)) { return ipv6_addr_cmp(&((struct sockaddr_in6 *)sa)->sin6_addr, &((struct sockaddr_in6 *)sb)->sin6_addr); } return -1; } static int cma_add_id_to_tree(struct rdma_id_private *node_id_priv) { struct rb_node **new, *parent = NULL; struct id_table_entry *this, *node; unsigned long flags; int result; node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; spin_lock_irqsave(&id_table_lock, flags); new = &id_table.rb_node; while (*new) { this = container_of(*new, struct id_table_entry, rb_node); result = compare_netdev_and_ip( node_id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(node_id_priv), this); parent = *new; if (result < 0) new = &((*new)->rb_left); else if (result > 0) new = &((*new)->rb_right); else { list_add_tail(&node_id_priv->id_list_entry, &this->id_list); kfree(node); goto unlock; } } INIT_LIST_HEAD(&node->id_list); list_add_tail(&node_id_priv->id_list_entry, &node->id_list); rb_link_node(&node->rb_node, parent, new); rb_insert_color(&node->rb_node, &id_table); unlock: spin_unlock_irqrestore(&id_table_lock, flags); return 0; } static struct id_table_entry * node_from_ndev_ip(struct rb_root *root, int ifindex, struct sockaddr *sa) { struct rb_node *node = root->rb_node; struct id_table_entry *data; int result; while (node) { data = container_of(node, struct id_table_entry, rb_node); result = compare_netdev_and_ip(ifindex, sa, data); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return data; } return NULL; } static void cma_remove_id_from_tree(struct rdma_id_private *id_priv) { struct id_table_entry *data; unsigned long flags; spin_lock_irqsave(&id_table_lock, flags); if (list_empty(&id_priv->id_list_entry)) goto out; data = node_from_ndev_ip(&id_table, id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(id_priv)); if (!data) goto out; list_del_init(&id_priv->id_list_entry); if (list_empty(&data->id_list)) { rb_erase(&data->rb_node, &id_table); kfree(data); } out: spin_unlock_irqrestore(&id_table_lock, flags); } static void _cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { cma_dev_get(cma_dev); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; id_priv->id.route.addr.dev_addr.transport = rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->device_item, &cma_dev->id_list); trace_cm_id_attach(id_priv, cma_dev->device); } static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { _cma_attach_to_dev(id_priv, cma_dev); id_priv->gid_type = cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(cma_dev->device)]; } static void cma_release_dev(struct rdma_id_private *id_priv) { mutex_lock(&lock); list_del_init(&id_priv->device_item); cma_dev_put(id_priv->cma_dev); id_priv->cma_dev = NULL; id_priv->id.device = NULL; if (id_priv->id.route.addr.dev_addr.sgid_attr) { rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = NULL; } mutex_unlock(&lock); } static inline unsigned short cma_family(struct rdma_id_private *id_priv) { return id_priv->id.route.addr.src_addr.ss_family; } static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: ib_addr_get_mgid(&id_priv->id.route.addr.dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (!ret) id_priv->qkey = be32_to_cpu(rec.qkey); break; default: break; } return ret; } static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { if (!qkey || (id_priv->qkey && (id_priv->qkey != qkey))) return -EINVAL; id_priv->qkey = qkey; return 0; } static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); } static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) { int ret; if (addr->sa_family != AF_IB) { ret = rdma_translate_ip(addr, dev_addr); } else { cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); ret = 0; } return ret; } static const struct ib_gid_attr * cma_validate_port(struct ib_device *device, u32 port, enum ib_gid_type gid_type, union ib_gid *gid, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr = ERR_PTR(-ENODEV); int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) goto out; if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) goto out; /* * For drivers that do not associate more than one net device with * their gid tables, such as iWARP drivers, it is sufficient to * return the first table entry. * * Other driver classes might be included in the future. */ if (rdma_protocol_iwarp(device, port)) { sgid_attr = rdma_get_gid_attr(device, port, 0); if (IS_ERR(sgid_attr)) goto out; rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); sgid_attr = ERR_PTR(-ENODEV); } rcu_read_unlock(); goto out; } if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } else { gid_type = IB_GID_TYPE_IB; } sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev); dev_put(ndev); out: return sgid_attr; } static void cma_bind_sgid_attr(struct rdma_id_private *id_priv, const struct ib_gid_attr *sgid_attr) { WARN_ON(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = sgid_attr; } /** * cma_acquire_dev_by_src_ip - Acquire cma device, port, gid attribute * based on source ip address. * @id_priv: cm_id which should be bound to cma device * * cma_acquire_dev_by_src_ip() binds cm id to cma device, port and GID attribute * based on source IP address. It returns 0 on success or error code otherwise. * It is applicable to active and passive side cm_id. */ static int cma_acquire_dev_by_src_ip(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; union ib_gid gid, iboe_gid, *gidp; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &iboe_gid); memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { gidp = rdma_protocol_roce(cma_dev->device, port) ? &iboe_gid : &gid; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, gidp, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); cma_attach_to_dev(id_priv, cma_dev); ret = 0; goto out; } } } out: mutex_unlock(&lock); return ret; } /** * cma_ib_acquire_dev - Acquire cma device, port and SGID attribute * @id_priv: cm id to bind to cma device * @listen_id_priv: listener cm id to match against * @req: Pointer to req structure containaining incoming * request information * cma_ib_acquire_dev() acquires cma device, port and SGID attribute when * rdma device matches for listen_id and incoming request. It also verifies * that a GID table entry is present for the source address. * Returns 0 on success, or returns error code otherwise. */ static int cma_ib_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv, struct cma_req_info *req) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; enum ib_gid_type gid_type; union ib_gid gid; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; if (rdma_protocol_roce(req->device, req->port)) rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &gid); else memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); gid_type = listen_id_priv->cma_dev->default_gid_type[req->port - 1]; sgid_attr = cma_validate_port(req->device, req->port, gid_type, &gid, id_priv); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); id_priv->id.port_num = req->port; cma_bind_sgid_attr(id_priv, sgid_attr); /* Need to acquire lock to protect against reader * of cma_dev->id_list such as cma_netdev_callback() and * cma_process_remove(). */ mutex_lock(&lock); cma_attach_to_dev(id_priv, listen_id_priv->cma_dev); mutex_unlock(&lock); rdma_restrack_add(&id_priv->res); return 0; } static int cma_iw_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; union ib_gid gid; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); cma_dev = listen_id_priv->cma_dev; port = listen_id_priv->id.port_num; gid_type = listen_id_priv->gid_type; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { if (listen_id_priv->cma_dev == cma_dev && listen_id_priv->id.port_num == port) continue; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } } } out: if (!ret) { cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); } mutex_unlock(&lock); return ret; } /* * Select the source IB device and address to reach the destination IB address. */ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; struct sockaddr_ib *addr; union ib_gid gid, sgid, *dgid; unsigned int p; u16 pkey, index; enum ib_port_state port_state; int ret; int i; cma_dev = NULL; addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { rdma_for_each_port (cur_dev->device, p) { if (!rdma_cap_af_ib(cur_dev->device, p)) continue; if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) continue; if (ib_get_cached_port_state(cur_dev->device, p, &port_state)) continue; for (i = 0; i < cur_dev->device->port_data[p].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(cur_dev->device, p, i, &gid); if (ret) continue; if (!memcmp(&gid, dgid, sizeof(gid))) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } if (!cma_dev && (gid.global.subnet_prefix == dgid->global.subnet_prefix) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } } } } mutex_unlock(&lock); return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); mutex_unlock(&lock); addr = (struct sockaddr_ib *)cma_src_addr(id_priv); memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } static void cma_id_get(struct rdma_id_private *id_priv) { refcount_inc(&id_priv->refcount); } static void cma_id_put(struct rdma_id_private *id_priv) { if (refcount_dec_and_test(&id_priv->refcount)) complete(&id_priv->comp); } static struct rdma_id_private * __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const struct rdma_id_private *parent) { struct rdma_id_private *id_priv; id_priv = kzalloc(sizeof *id_priv, GFP_KERNEL); if (!id_priv) return ERR_PTR(-ENOMEM); id_priv->state = RDMA_CM_IDLE; id_priv->id.context = context; id_priv->id.event_handler = event_handler; id_priv->id.ps = ps; id_priv->id.qp_type = qp_type; id_priv->tos_set = false; id_priv->timeout_set = false; id_priv->min_rnr_timer_set = false; id_priv->gid_type = IB_GID_TYPE_IB; spin_lock_init(&id_priv->lock); mutex_init(&id_priv->qp_mutex); init_completion(&id_priv->comp); refcount_set(&id_priv->refcount, 1); mutex_init(&id_priv->handler_mutex); INIT_LIST_HEAD(&id_priv->device_item); INIT_LIST_HEAD(&id_priv->id_list_entry); INIT_LIST_HEAD(&id_priv->listen_list); INIT_LIST_HEAD(&id_priv->mc_list); get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num); id_priv->id.route.addr.dev_addr.net = get_net(net); id_priv->seq_num &= 0x00ffffff; rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID); if (parent) rdma_restrack_parent_name(&id_priv->res, &parent->res); return id_priv; } struct rdma_cm_id * __rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const char *caller) { struct rdma_id_private *ret; ret = __rdma_create_id(net, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, caller); return &ret->id; } EXPORT_SYMBOL(__rdma_create_kernel_id); struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type) { struct rdma_id_private *ret; ret = __rdma_create_id(current->nsproxy->net_ns, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, NULL); return &ret->id; } EXPORT_SYMBOL(rdma_create_user_id); static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTR; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTS; qp_attr.sq_psn = 0; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE | IB_QP_SQ_PSN); return ret; } static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; return ib_modify_qp(qp, &qp_attr, qp_attr_mask); } int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr) { struct rdma_id_private *id_priv; struct ib_qp *qp; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (id->device != pd->device) { ret = -EINVAL; goto out_err; } qp_init_attr->port_num = id->port_num; qp = ib_create_qp(pd, qp_init_attr); if (IS_ERR(qp)) { ret = PTR_ERR(qp); goto out_err; } if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); else ret = cma_init_conn_qp(id_priv, qp); if (ret) goto out_destroy; id->qp = qp; id_priv->qp_num = qp->qp_num; id_priv->srq = (qp->srq != NULL); trace_cm_qp_create(id_priv, pd, qp_init_attr, 0); return 0; out_destroy: ib_destroy_qp(qp); out_err: trace_cm_qp_create(id_priv, pd, qp_init_attr, ret); return ret; } EXPORT_SYMBOL(rdma_create_qp); void rdma_destroy_qp(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); trace_cm_qp_destroy(id_priv); mutex_lock(&id_priv->qp_mutex); ib_destroy_qp(id_priv->id.qp); id_priv->id.qp = NULL; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_destroy_qp); static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } /* Need to update QP attributes from default values. */ qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); if (ret) goto out; qp_attr.qp_state = IB_QPS_RTR; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; BUG_ON(id_priv->cma_dev->device != id_priv->id.device); if (conn_param) qp_attr.max_dest_rd_atomic = conn_param->responder_resources; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_rts(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_RTS; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; if (conn_param) qp_attr.max_rd_atomic = conn_param->initiator_depth; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_err(struct rdma_id_private *id_priv) { struct ib_qp_attr qp_attr; int ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_ERR; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; u16 pkey; if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num)) pkey = 0xffff; else pkey = ib_addr_get_pkey(dev_addr); ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, pkey, &qp_attr->pkey_index); if (ret) return ret; qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; qp_attr->qkey = id_priv->qkey; *qp_attr_mask |= IB_QP_QKEY; } else { qp_attr->qp_access_flags = 0; *qp_attr_mask |= IB_QP_ACCESS_FLAGS; } return 0; } int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_id_private *id_priv; int ret = 0; id_priv = container_of(id, struct rdma_id_private, id); if (rdma_cap_ib_cm(id->device, id->port_num)) { if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr, qp_attr_mask); if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; } else if (rdma_cap_iw_cm(id->device, id->port_num)) { if (!id_priv->cm_id.iw) { qp_attr->qp_access_flags = 0; *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask |= IB_QP_PORT; } else { ret = -ENOSYS; } if ((*qp_attr_mask & IB_QP_TIMEOUT) && id_priv->timeout_set) qp_attr->timeout = id_priv->timeout; if ((*qp_attr_mask & IB_QP_MIN_RNR_TIMER) && id_priv->min_rnr_timer_set) qp_attr->min_rnr_timer = id_priv->min_rnr_timer; return ret; } EXPORT_SYMBOL(rdma_init_qp_attr); static inline bool cma_zero_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_any(&((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_any(&((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_loopback_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_loopback( ((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_loopback( &((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_loopback( &((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_any_addr(const struct sockaddr *addr) { return cma_zero_addr(addr) || cma_loopback_addr(addr); } static int cma_addr_cmp(const struct sockaddr *src, const struct sockaddr *dst) { if (src->sa_family != dst->sa_family) return -1; switch (src->sa_family) { case AF_INET: return ((struct sockaddr_in *)src)->sin_addr.s_addr != ((struct sockaddr_in *)dst)->sin_addr.s_addr; case AF_INET6: { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)src; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst; bool link_local; if (ipv6_addr_cmp(&src_addr6->sin6_addr, &dst_addr6->sin6_addr)) return 1; link_local = ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL; /* Link local must match their scope_ids */ return link_local ? (src_addr6->sin6_scope_id != dst_addr6->sin6_scope_id) : 0; } default: return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, &((struct sockaddr_ib *) dst)->sib_addr); } } static __be16 cma_port(const struct sockaddr *addr) { struct sockaddr_ib *sib; switch (addr->sa_family) { case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; case AF_IB: sib = (struct sockaddr_ib *) addr; return htons((u16) (be64_to_cpu(sib->sib_sid) & be64_to_cpu(sib->sib_sid_mask))); default: return 0; } } static inline int cma_any_port(const struct sockaddr *addr) { return !cma_port(addr); } static void cma_save_ib_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct sa_path_rec *path) { struct sockaddr_ib *listen_ib, *ib; listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; if (src_addr) { ib = (struct sockaddr_ib *)src_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->sgid, 16); ib->sib_sid = path->service_id; ib->sib_scope_id = 0; } else { ib->sib_pkey = listen_ib->sib_pkey; ib->sib_flowinfo = listen_ib->sib_flowinfo; ib->sib_addr = listen_ib->sib_addr; ib->sib_sid = listen_ib->sib_sid; ib->sib_scope_id = listen_ib->sib_scope_id; } ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); } if (dst_addr) { ib = (struct sockaddr_ib *)dst_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->dgid, 16); } } } static void cma_save_ip4_info(struct sockaddr_in *src_addr, struct sockaddr_in *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->dst_addr.ip4.addr, .sin_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->src_addr.ip4.addr, .sin_port = hdr->port, }; } } static void cma_save_ip6_info(struct sockaddr_in6 *src_addr, struct sockaddr_in6 *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->dst_addr.ip6, .sin6_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->src_addr.ip6, .sin6_port = hdr->port, }; } } static u16 cma_port_from_service_id(__be64 service_id) { return (u16)be64_to_cpu(service_id); } static int cma_save_ip_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct ib_cm_event *ib_event, __be64 service_id) { struct cma_hdr *hdr; __be16 port; hdr = ib_event->private_data; if (hdr->cma_version != CMA_VERSION) return -EINVAL; port = htons(cma_port_from_service_id(service_id)); switch (cma_get_ip_ver(hdr)) { case 4: cma_save_ip4_info((struct sockaddr_in *)src_addr, (struct sockaddr_in *)dst_addr, hdr, port); break; case 6: cma_save_ip6_info((struct sockaddr_in6 *)src_addr, (struct sockaddr_in6 *)dst_addr, hdr, port); break; default: return -EAFNOSUPPORT; } return 0; } static int cma_save_net_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, sa_family_t sa_family, __be64 service_id) { if (sa_family == AF_IB) { if (ib_event->event == IB_CM_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, ib_event->param.req_rcvd.primary_path); else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, NULL); return 0; } return cma_save_ip_info(src_addr, dst_addr, ib_event, service_id); } static int cma_save_req_info(const struct ib_cm_event *ib_event, struct cma_req_info *req) { const struct ib_cm_req_event_param *req_param = &ib_event->param.req_rcvd; const struct ib_cm_sidr_req_event_param *sidr_param = &ib_event->param.sidr_req_rcvd; switch (ib_event->event) { case IB_CM_REQ_RECEIVED: req->device = req_param->listen_id->device; req->port = req_param->port; memcpy(&req->local_gid, &req_param->primary_path->sgid, sizeof(req->local_gid)); req->has_gid = true; req->service_id = req_param->primary_path->service_id; req->pkey = be16_to_cpu(req_param->primary_path->pkey); if (req->pkey != req_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and primary path P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", req_param->bth_pkey, req->pkey); break; case IB_CM_SIDR_REQ_RECEIVED: req->device = sidr_param->listen_id->device; req->port = sidr_param->port; req->has_gid = false; req->service_id = sidr_param->service_id; req->pkey = sidr_param->pkey; if (req->pkey != sidr_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and SIDR request payload P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", sidr_param->bth_pkey, req->pkey); break; default: return -EINVAL; } return 0; } static bool validate_ipv4_net_dev(struct net_device *net_dev, const struct sockaddr_in *dst_addr, const struct sockaddr_in *src_addr) { __be32 daddr = dst_addr->sin_addr.s_addr, saddr = src_addr->sin_addr.s_addr; struct fib_result res; struct flowi4 fl4; int err; bool ret; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || ipv4_is_lbcast(daddr) || ipv4_is_zeronet(saddr) || ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr) || ipv4_is_loopback(saddr)) return false; memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; rcu_read_lock(); err = fib_lookup(dev_net(net_dev), &fl4, &res, 0); ret = err == 0 && FIB_RES_DEV(res) == net_dev; rcu_read_unlock(); return ret; } static bool validate_ipv6_net_dev(struct net_device *net_dev, const struct sockaddr_in6 *dst_addr, const struct sockaddr_in6 *src_addr) { #if IS_ENABLED(CONFIG_IPV6) const int strict = ipv6_addr_type(&dst_addr->sin6_addr) & IPV6_ADDR_LINKLOCAL; struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr, &src_addr->sin6_addr, net_dev->ifindex, NULL, strict); bool ret; if (!rt) return false; ret = rt->rt6i_idev->dev == net_dev; ip6_rt_put(rt); return ret; #else return false; #endif } static bool validate_net_dev(struct net_device *net_dev, const struct sockaddr *daddr, const struct sockaddr *saddr) { const struct sockaddr_in *daddr4 = (const struct sockaddr_in *)daddr; const struct sockaddr_in *saddr4 = (const struct sockaddr_in *)saddr; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; const struct sockaddr_in6 *saddr6 = (const struct sockaddr_in6 *)saddr; switch (daddr->sa_family) { case AF_INET: return saddr->sa_family == AF_INET && validate_ipv4_net_dev(net_dev, daddr4, saddr4); case AF_INET6: return saddr->sa_family == AF_INET6 && validate_ipv6_net_dev(net_dev, daddr6, saddr6); default: return false; } } static struct net_device * roce_get_net_dev_by_cm_event(const struct ib_cm_event *ib_event) { const struct ib_gid_attr *sgid_attr = NULL; struct net_device *ndev; if (ib_event->event == IB_CM_REQ_RECEIVED) sgid_attr = ib_event->param.req_rcvd.ppath_sgid_attr; else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) sgid_attr = ib_event->param.sidr_req_rcvd.sgid_attr; if (!sgid_attr) return NULL; rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(sgid_attr); if (IS_ERR(ndev)) ndev = NULL; else dev_hold(ndev); rcu_read_unlock(); return ndev; } static struct net_device *cma_get_net_dev(const struct ib_cm_event *ib_event, struct cma_req_info *req) { struct sockaddr *listen_addr = (struct sockaddr *)&req->listen_addr_storage; struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage; struct net_device *net_dev; const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL; int err; err = cma_save_ip_info(listen_addr, src_addr, ib_event, req->service_id); if (err) return ERR_PTR(err); if (rdma_protocol_roce(req->device, req->port)) net_dev = roce_get_net_dev_by_cm_event(ib_event); else net_dev = ib_get_net_dev_by_params(req->device, req->port, req->pkey, gid, listen_addr); if (!net_dev) return ERR_PTR(-ENODEV); return net_dev; } static enum rdma_ucm_port_space rdma_ps_from_service_id(__be64 service_id) { return (be64_to_cpu(service_id) >> 16) & 0xffff; } static bool cma_match_private_data(struct rdma_id_private *id_priv, const struct cma_hdr *hdr) { struct sockaddr *addr = cma_src_addr(id_priv); __be32 ip4_addr; struct in6_addr ip6_addr; if (cma_any_addr(addr) && !id_priv->afonly) return true; switch (addr->sa_family) { case AF_INET: ip4_addr = ((struct sockaddr_in *)addr)->sin_addr.s_addr; if (cma_get_ip_ver(hdr) != 4) return false; if (!cma_any_addr(addr) && hdr->dst_addr.ip4.addr != ip4_addr) return false; break; case AF_INET6: ip6_addr = ((struct sockaddr_in6 *)addr)->sin6_addr; if (cma_get_ip_ver(hdr) != 6) return false; if (!cma_any_addr(addr) && memcmp(&hdr->dst_addr.ip6, &ip6_addr, sizeof(ip6_addr))) return false; break; case AF_IB: return true; default: return false; } return true; } static bool cma_protocol_roce(const struct rdma_cm_id *id) { struct ib_device *device = id->device; const u32 port_num = id->port_num ?: rdma_start_port(device); return rdma_protocol_roce(device, port_num); } static bool cma_is_req_ipv6_ll(const struct cma_req_info *req) { const struct sockaddr *daddr = (const struct sockaddr *)&req->listen_addr_storage; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; /* Returns true if the req is for IPv6 link local */ return (daddr->sa_family == AF_INET6 && (ipv6_addr_type(&daddr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)); } static bool cma_match_net_dev(const struct rdma_cm_id *id, const struct net_device *net_dev, const struct cma_req_info *req) { const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request */ return (!id->port_num || id->port_num == req->port) && (addr->src_addr.ss_family == AF_IB); /* * If the request is not for IPv6 link local, allow matching * request to any netdevice of the one or multiport rdma device. */ if (!cma_is_req_ipv6_ll(req)) return true; /* * Net namespaces must match, and if the listner is listening * on a specific netdevice than netdevice must match as well. */ if (net_eq(dev_net(net_dev), addr->dev_addr.net) && (!!addr->dev_addr.bound_dev_if == (addr->dev_addr.bound_dev_if == net_dev->ifindex))) return true; else return false; } static struct rdma_id_private *cma_find_listener( const struct rdma_bind_list *bind_list, const struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, const struct cma_req_info *req, const struct net_device *net_dev) { struct rdma_id_private *id_priv, *id_priv_dev; lockdep_assert_held(&lock); if (!bind_list) return ERR_PTR(-EINVAL); hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && cma_match_net_dev(&id_priv->id, net_dev, req)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_item) { if (id_priv_dev->id.device == cm_id->device && cma_match_net_dev(&id_priv_dev->id, net_dev, req)) return id_priv_dev; } } } return ERR_PTR(-EINVAL); } static struct rdma_id_private * cma_ib_id_from_event(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, struct cma_req_info *req, struct net_device **net_dev) { struct rdma_bind_list *bind_list; struct rdma_id_private *id_priv; int err; err = cma_save_req_info(ib_event, req); if (err) return ERR_PTR(err); *net_dev = cma_get_net_dev(ib_event, req); if (IS_ERR(*net_dev)) { if (PTR_ERR(*net_dev) == -EAFNOSUPPORT) { /* Assuming the protocol is AF_IB */ *net_dev = NULL; } else { return ERR_CAST(*net_dev); } } mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice * validation, cm_id lookup under rcu lock. * RCU lock along with netdevice state check, synchronizes with * netdevice migrating to different net namespace and also avoids * case where net namespace doesn't get deleted while lookup is in * progress. * If the device state is not IFF_UP, its properties such as ifindex * and nd_net cannot be trusted to remain valid without rcu lock. * net/core/dev.c change_net_namespace() ensures to synchronize with * ongoing operations on net device after device is closed using * synchronize_net(). */ rcu_read_lock(); if (*net_dev) { /* * If netdevice is down, it is likely that it is administratively * down or it might be migrating to different namespace. * In that case avoid further processing, as the net namespace * or ifindex may change. */ if (((*net_dev)->flags & IFF_UP) == 0) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } if (!validate_net_dev(*net_dev, (struct sockaddr *)&req->src_addr_storage, (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } } bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net, rdma_ps_from_service_id(req->service_id), cma_port_from_service_id(req->service_id)); id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; } return id_priv; } static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } static void cma_cancel_route(struct rdma_id_private *id_priv) { if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) { if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); } } static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; lockdep_assert_held(&lock); /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ list_del_init(&id_priv->listen_any_item); while (!list_empty(&id_priv->listen_list)) { dev_id_priv = list_first_entry(&id_priv->listen_list, struct rdma_id_private, listen_item); /* sync with device removal to avoid duplicate destruction */ list_del_init(&dev_id_priv->device_item); list_del_init(&dev_id_priv->listen_item); mutex_unlock(&lock); rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } } static void cma_cancel_listens(struct rdma_id_private *id_priv) { mutex_lock(&lock); _cma_cancel_listens(id_priv); mutex_unlock(&lock); } static void cma_cancel_operation(struct rdma_id_private *id_priv, enum rdma_cm_state state) { switch (state) { case RDMA_CM_ADDR_QUERY: /* * We can avoid doing the rdma_addr_cancel() based on state, * only RDMA_CM_ADDR_QUERY has a work that could still execute. * Notice that the addr_handler work could still be exiting * outside this state, however due to the interaction with the * handler_mutex the work is guaranteed not to touch id_priv * during exit. */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: cma_cancel_route(id_priv); break; case RDMA_CM_LISTEN: if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) cma_cancel_listens(id_priv); break; default: break; } } static void cma_release_port(struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list = id_priv->bind_list; struct net *net = id_priv->id.route.addr.dev_addr.net; if (!bind_list) return; mutex_lock(&lock); hlist_del(&id_priv->node); if (hlist_empty(&bind_list->owners)) { cma_ps_remove(net, bind_list->ps, bind_list->port); kfree(bind_list); } mutex_unlock(&lock); } static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (ndev && !send_only) { enum ib_gid_type gid_type; union ib_gid mgid; gid_type = id_priv->cma_dev->default_gid_type [id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; cma_iboe_set_mgid((struct sockaddr *)&mc->addr, &mgid, gid_type); cma_igmp_send(ndev, &mgid, false); } dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); } kfree(mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) { struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, list); list_del(&mc->list); destroy_mc(id_priv, mc); } } static void _destroy_id(struct rdma_id_private *id_priv, enum rdma_cm_state state) { cma_cancel_operation(id_priv, state); rdma_restrack_del(&id_priv->res); cma_remove_id_from_tree(id_priv); if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); } else if (rdma_cap_iw_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); } cma_leave_mc_groups(id_priv); cma_release_dev(id_priv); } cma_release_port(id_priv); cma_id_put(id_priv); wait_for_completion(&id_priv->comp); if (id_priv->internal_id) cma_id_put(id_priv->id.context); kfree(id_priv->id.route.path_rec); kfree(id_priv->id.route.path_rec_inbound); kfree(id_priv->id.route.path_rec_outbound); put_net(id_priv->id.route.addr.dev_addr.net); kfree(id_priv); } /* * destroy an ID from within the handler_mutex. This ensures that no other * handlers can start running concurrently. */ static void destroy_id_handler_unlock(struct rdma_id_private *id_priv) __releases(&idprv->handler_mutex) { enum rdma_cm_state state; unsigned long flags; trace_cm_id_destroy(id_priv); /* * Setting the state to destroyed under the handler mutex provides a * fence against calling handler callbacks. If this is invoked due to * the failure of a handler callback then it guarentees that no future * handlers will be called. */ lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; id_priv->state = RDMA_CM_DESTROYING; spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); _destroy_id(id_priv, state); } void rdma_destroy_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); destroy_id_handler_unlock(id_priv); } EXPORT_SYMBOL(rdma_destroy_id); static int cma_rep_recv(struct rdma_id_private *id_priv) { int ret; ret = cma_modify_qp_rtr(id_priv, NULL); if (ret) goto reject; ret = cma_modify_qp_rts(id_priv, NULL); if (ret) goto reject; trace_cm_send_rtu(id_priv); ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0); if (ret) goto reject; return 0; reject: pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret); cma_modify_qp_err(id_priv); trace_cm_send_rej(id_priv); ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, NULL, 0); return ret; } static void cma_set_rep_event_data(struct rdma_cm_event *event, const struct ib_cm_rep_event_param *rep_data, void *private_data) { event->param.conn.private_data = private_data; event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; event->param.conn.responder_resources = rep_data->responder_resources; event->param.conn.initiator_depth = rep_data->initiator_depth; event->param.conn.flow_control = rep_data->flow_control; event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; event->param.conn.srq = rep_data->srq; event->param.conn.qp_num = rep_data->remote_qpn; event->ece.vendor_id = rep_data->ece.vendor_id; event->ece.attr_mod = rep_data->ece.attr_mod; } static int cma_cm_event_handler(struct rdma_id_private *id_priv, struct rdma_cm_event *event) { int ret; lockdep_assert_held(&id_priv->handler_mutex); trace_cm_event_handler(id_priv, event); ret = id_priv->id.event_handler(&id_priv->id, event); trace_cm_event_done(id_priv, event, ret); return ret; } static int cma_ib_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; enum rdma_cm_state state; int ret; mutex_lock(&id_priv->handler_mutex); state = READ_ONCE(id_priv->state); if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_CONNECT) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_DISCONNECT)) goto out; switch (ib_event->event) { case IB_CM_REQ_ERROR: case IB_CM_REP_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: if (state == RDMA_CM_CONNECT && (id_priv->id.qp_type != IB_QPT_UD)) { trace_cm_send_mra(id_priv); ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); } if (id_priv->id.qp) { event.status = cma_rep_recv(id_priv); event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : RDMA_CM_EVENT_ESTABLISHED; } else { event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; } cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, ib_event->private_data); break; case IB_CM_RTU_RECEIVED: case IB_CM_USER_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: event.status = -ETIMEDOUT; fallthrough; case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_DISCONNECT)) goto out; event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IB_CM_TIMEWAIT_EXIT: event.event = RDMA_CM_EVENT_TIMEWAIT_EXIT; break; case IB_CM_MRA_RECEIVED: /* ignore event */ goto out; case IB_CM_REJ_RECEIVED: pr_debug_ratelimited("RDMA CM: REJECTED: %s\n", rdma_reject_msg(&id_priv->id, ib_event->param.rej_rcvd.reason)); cma_modify_qp_err(id_priv); event.status = ib_event->param.rej_rcvd.reason; event.event = RDMA_CM_EVENT_REJECTED; event.param.conn.private_data = ib_event->private_data; event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static struct rdma_id_private * cma_ib_new_conn_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; struct rdma_route *rt; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct sa_path_rec *path = ib_event->param.req_rcvd.primary_path; const __be64 service_id = ib_event->param.req_rcvd.primary_path->service_id; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(listen_id->route.addr.dev_addr.net, listen_id->event_handler, listen_id->context, listen_id->ps, ib_event->param.req_rcvd.qp_type, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, service_id)) goto err; rt = &id->route; rt->num_pri_alt_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1; rt->path_rec = kmalloc_array(rt->num_pri_alt_paths, sizeof(*rt->path_rec), GFP_KERNEL); if (!rt->path_rec) goto err; rt->path_rec[0] = *path; if (rt->num_pri_alt_paths == 2) rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path; if (net_dev) { rdma_copy_src_l2_addr(&rt->addr.dev_addr, net_dev); } else { if (!cma_protocol_roce(listen_id) && cma_any_addr(cma_src_addr(id_priv))) { rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); } else if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); if (ret) goto err; } } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static struct rdma_id_private * cma_ib_new_udp_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { const struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct net *net = listen_id->route.addr.dev_addr.net; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(net, listen_id->event_handler, listen_id->context, listen_id->ps, IB_QPT_UD, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, ib_event->param.sidr_req_rcvd.service_id)) goto err; if (net_dev) { rdma_copy_src_l2_addr(&id->route.addr.dev_addr, net_dev); } else { if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &id->route.addr.dev_addr); if (ret) goto err; } } id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static void cma_set_req_event_data(struct rdma_cm_event *event, const struct ib_cm_req_event_param *req_data, void *private_data, int offset) { event->param.conn.private_data = private_data + offset; event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset; event->param.conn.responder_resources = req_data->responder_resources; event->param.conn.initiator_depth = req_data->initiator_depth; event->param.conn.flow_control = req_data->flow_control; event->param.conn.retry_count = req_data->retry_count; event->param.conn.rnr_retry_count = req_data->rnr_retry_count; event->param.conn.srq = req_data->srq; event->param.conn.qp_num = req_data->remote_qpn; event->ece.vendor_id = req_data->ece.vendor_id; event->ece.attr_mod = req_data->ece.attr_mod; } static int cma_ib_check_req_qp_type(const struct rdma_cm_id *id, const struct ib_cm_event *ib_event) { return (((ib_event->event == IB_CM_REQ_RECEIVED) && (ib_event->param.req_rcvd.qp_type == id->qp_type)) || ((ib_event->event == IB_CM_SIDR_REQ_RECEIVED) && (id->qp_type == IB_QPT_UD)) || (!id->qp_type)); } static int cma_ib_req_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event = {}; struct cma_req_info req = {}; struct net_device *net_dev; u8 offset; int ret; listen_id = cma_ib_id_from_event(cm_id, ib_event, &req, &net_dev); if (IS_ERR(listen_id)) return PTR_ERR(listen_id); trace_cm_req_handler(listen_id, ib_event->event); if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) { ret = -EINVAL; goto net_dev_put; } mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) { ret = -ECONNABORTED; goto err_unlock; } offset = cma_user_data_offset(listen_id); event.event = RDMA_CM_EVENT_CONNECT_REQUEST; if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) { conn_id = cma_ib_new_udp_id(&listen_id->id, ib_event, net_dev); event.param.ud.private_data = ib_event->private_data + offset; event.param.ud.private_data_len = IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset; } else { conn_id = cma_ib_new_conn_id(&listen_id->id, ib_event, net_dev); cma_set_req_event_data(&event, &ib_event->param.req_rcvd, ib_event->private_data, offset); } if (!conn_id) { ret = -ENOMEM; goto err_unlock; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); ret = cma_ib_acquire_dev(conn_id, listen_id, &req); if (ret) { destroy_id_handler_unlock(conn_id); goto err_unlock; } conn_id->cm_id.ib = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ conn_id->cm_id.ib = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); goto net_dev_put; } if (READ_ONCE(conn_id->state) == RDMA_CM_CONNECT && conn_id->id.qp_type != IB_QPT_UD) { trace_cm_send_mra(cm_id->context); ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); } mutex_unlock(&conn_id->handler_mutex); err_unlock: mutex_unlock(&listen_id->handler_mutex); net_dev_put: dev_put(net_dev); return ret; } __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) { if (addr->sa_family == AF_IB) return ((struct sockaddr_ib *) addr)->sib_sid; return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr))); } EXPORT_SYMBOL(rdma_get_service_id); void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, union ib_gid *dgid) { struct rdma_addr *addr = &cm_id->route.addr; if (!cm_id->device) { if (sgid) memset(sgid, 0, sizeof(*sgid)); if (dgid) memset(dgid, 0, sizeof(*dgid)); return; } if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) { if (sgid) rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid); if (dgid) rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid); } else { if (sgid) rdma_addr_get_sgid(&addr->dev_addr, sgid); if (dgid) rdma_addr_get_dgid(&addr->dev_addr, dgid); } } EXPORT_SYMBOL(rdma_read_gids); static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; struct rdma_cm_event event = {}; int ret = 0; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (iw_event->event) { case IW_CM_EVENT_CLOSE: event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: memcpy(cma_src_addr(id_priv), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(id_priv), raddr, rdma_addr_size(raddr)); switch (iw_event->status) { case 0: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; case -ECONNRESET: case -ECONNREFUSED: event.event = RDMA_CM_EVENT_REJECTED; break; case -ETIMEDOUT: event.event = RDMA_CM_EVENT_UNREACHABLE; break; default: event.event = RDMA_CM_EVENT_CONNECT_ERROR; break; } break; case IW_CM_EVENT_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; default: goto out; } event.status = iw_event->status; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return ret; } static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct iw_cm_event *iw_event) { struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event = {}; int ret = -ECONNABORTED; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; event.event = RDMA_CM_EVENT_CONNECT_REQUEST; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; listen_id = cm_id->context; mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) goto out; /* Create a new RDMA id for the new IW CM ID */ conn_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net, listen_id->id.event_handler, listen_id->id.context, RDMA_PS_TCP, IB_QPT_RC, listen_id); if (IS_ERR(conn_id)) { ret = -ENOMEM; goto out; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); conn_id->state = RDMA_CM_CONNECT; ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } ret = cma_iw_acquire_dev(conn_id, listen_id); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; memcpy(cma_src_addr(conn_id), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(conn_id), raddr, rdma_addr_size(raddr)); ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } mutex_unlock(&conn_id->handler_mutex); out: mutex_unlock(&listen_id->handler_mutex); return ret; } static int cma_ib_listen(struct rdma_id_private *id_priv) { struct sockaddr *addr; struct ib_cm_id *id; __be64 svc_id; addr = cma_src_addr(id_priv); svc_id = rdma_get_service_id(&id_priv->id, addr); id = ib_cm_insert_listen(id_priv->id.device, cma_ib_req_handler, svc_id); if (IS_ERR(id)) return PTR_ERR(id); id_priv->cm_id.ib = id; return 0; } static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog) { int ret; struct iw_cm_id *id; id = iw_create_cm_id(id_priv->id.device, iw_conn_req_handler, id_priv); if (IS_ERR(id)) return PTR_ERR(id); mutex_lock(&id_priv->qp_mutex); id->tos = id_priv->tos; id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id->afonly = id_priv->afonly; id_priv->cm_id.iw = id; memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); ret = iw_cm_listen(id_priv->cm_id.iw, backlog); if (ret) { iw_destroy_cm_id(id_priv->cm_id.iw); id_priv->cm_id.iw = NULL; } return ret; } static int cma_listen_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct rdma_id_private *id_priv = id->context; /* Listening IDs are always destroyed on removal */ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) return -1; id->context = id_priv->id.context; id->event_handler = id_priv->id.event_handler; trace_cm_event_handler(id_priv, event); return id_priv->id.event_handler(id, event); } static int cma_listen_on_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev, struct rdma_id_private **to_destroy) { struct rdma_id_private *dev_id_priv; struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; lockdep_assert_held(&lock); *to_destroy = NULL; if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return 0; dev_id_priv = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps, id_priv->id.qp_type, id_priv); if (IS_ERR(dev_id_priv)) return PTR_ERR(dev_id_priv); dev_id_priv->state = RDMA_CM_ADDR_BOUND; memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); _cma_attach_to_dev(dev_id_priv, cma_dev); rdma_restrack_add(&dev_id_priv->res); cma_id_get(id_priv); dev_id_priv->internal_id = 1; dev_id_priv->afonly = id_priv->afonly; mutex_lock(&id_priv->qp_mutex); dev_id_priv->tos_set = id_priv->tos_set; dev_id_priv->tos = id_priv->tos; mutex_unlock(&id_priv->qp_mutex); ret = rdma_listen(&dev_id_priv->id, id_priv->backlog); if (ret) goto err_listen; list_add_tail(&dev_id_priv->listen_item, &id_priv->listen_list); return 0; err_listen: /* Caller must destroy this after releasing lock */ *to_destroy = dev_id_priv; dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret); return ret; } static int cma_listen_on_all(struct rdma_id_private *id_priv) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; int ret; mutex_lock(&lock); list_add_tail(&id_priv->listen_any_item, &listen_any_list); list_for_each_entry(cma_dev, &dev_list, list) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) { /* Prevent racing with cma_process_remove() */ if (to_destroy) list_del_init(&to_destroy->device_item); goto err_listen; } } mutex_unlock(&lock); return 0; err_listen: _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); return ret; } void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->tos = (u8) tos; id_priv->tos_set = true; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_set_service_type); /** * rdma_set_ack_timeout() - Set the ack timeout of QP associated * with a connection identifier. * @id: Communication identifier to associated with service type. * @timeout: Ack timeout to set a QP, expressed as 4.096 * 2^(timeout) usec. * * This function should be called before rdma_connect() on active side, * and on passive side before rdma_accept(). It is applicable to primary * path only. The timeout will affect the local side of the QP, it is not * negotiated with remote side and zero disables the timer. In case it is * set before rdma_resolve_route, the value will also be used to determine * PacketLifeTime for RoCE. * * Return: 0 for success */ int rdma_set_ack_timeout(struct rdma_cm_id *id, u8 timeout) { struct rdma_id_private *id_priv; if (id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_INI) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->timeout = timeout; id_priv->timeout_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_ack_timeout); /** * rdma_set_min_rnr_timer() - Set the minimum RNR Retry timer of the * QP associated with a connection identifier. * @id: Communication identifier to associated with service type. * @min_rnr_timer: 5-bit value encoded as Table 45: "Encoding for RNR NAK * Timer Field" in the IBTA specification. * * This function should be called before rdma_connect() on active * side, and on passive side before rdma_accept(). The timer value * will be associated with the local QP. When it receives a send it is * not read to handle, typically if the receive queue is empty, an RNR * Retry NAK is returned to the requester with the min_rnr_timer * encoded. The requester will then wait at least the time specified * in the NAK before retrying. The default is zero, which translates * to a minimum RNR Timer value of 655 ms. * * Return: 0 for success */ int rdma_set_min_rnr_timer(struct rdma_cm_id *id, u8 min_rnr_timer) { struct rdma_id_private *id_priv; /* It is a five-bit value */ if (min_rnr_timer & 0xe0) return -EINVAL; if (WARN_ON(id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_TGT)) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->min_rnr_timer = min_rnr_timer; id_priv->min_rnr_timer_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_min_rnr_timer); static int route_set_path_rec_inbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_inbound) { route->path_rec_inbound = kzalloc(sizeof(*route->path_rec_inbound), GFP_KERNEL); if (!route->path_rec_inbound) return -ENOMEM; } *route->path_rec_inbound = *path_rec; return 0; } static int route_set_path_rec_outbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_outbound) { route->path_rec_outbound = kzalloc(sizeof(*route->path_rec_outbound), GFP_KERNEL); if (!route->path_rec_outbound) return -ENOMEM; } *route->path_rec_outbound = *path_rec; return 0; } static void cma_query_handler(int status, struct sa_path_rec *path_rec, unsigned int num_prs, void *context) { struct cma_work *work = context; struct rdma_route *route; int i; route = &work->id->id.route; if (status) goto fail; for (i = 0; i < num_prs; i++) { if (!path_rec[i].flags || (path_rec[i].flags & IB_PATH_GMP)) *route->path_rec = path_rec[i]; else if (path_rec[i].flags & IB_PATH_INBOUND) status = route_set_path_rec_inbound(work, &path_rec[i]); else if (path_rec[i].flags & IB_PATH_OUTBOUND) status = route_set_path_rec_outbound(work, &path_rec[i]); else status = -EINVAL; if (status) goto fail; } route->num_pri_alt_paths = 1; queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_ERROR; work->event.status = status; pr_debug_ratelimited("RDMA CM: ROUTE_ERROR: failed to query path. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_query_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms, struct cma_work *work) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sa_path_rec path_rec; ib_sa_comp_mask comp_mask; struct sockaddr_in6 *sin6; struct sockaddr_ib *sib; memset(&path_rec, 0, sizeof path_rec); if (rdma_cap_opa_ah(id_priv->id.device, id_priv->id.port_num)) path_rec.rec_type = SA_PATH_REC_TYPE_OPA; else path_rec.rec_type = SA_PATH_REC_TYPE_IB; rdma_addr_get_sgid(dev_addr, &path_rec.sgid); rdma_addr_get_dgid(dev_addr, &path_rec.dgid); path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); path_rec.numb_path = 1; path_rec.reversible = 1; path_rec.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID; switch (cma_family(id_priv)) { case AF_INET: path_rec.qos_class = cpu_to_be16((u16) id_priv->tos); comp_mask |= IB_SA_PATH_REC_QOS_CLASS; break; case AF_INET6: sin6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; case AF_IB: sib = (struct sockaddr_ib *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sib->sib_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; } id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &path_rec, comp_mask, timeout_ms, GFP_KERNEL, cma_query_handler, work, &id_priv->query); return (id_priv->query_id < 0) ? id_priv->query_id : 0; } static void cma_iboe_join_work_handler(struct work_struct *work) { struct cma_multicast *mc = container_of(work, struct cma_multicast, iboe_join.work); struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_id_private *id_priv = mc->id_priv; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; ret = cma_cm_event_handler(id_priv, event); WARN_ON(ret); out_unlock: mutex_unlock(&id_priv->handler_mutex); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } static void cma_work_handler(struct work_struct *_work) { struct cma_work *work = container_of(_work, struct cma_work, work); struct rdma_id_private *id_priv = work->id; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; if (work->old_state != 0 || work->new_state != 0) { if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) goto out_unlock; } if (cma_cm_event_handler(id_priv, &work->event)) { cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); goto out_free; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); out_free: if (work->event.event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&work->event.param.ud.ah_attr); kfree(work); } static void cma_init_resolve_route_work(struct cma_work *work, struct rdma_id_private *id_priv) { work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; } static void enqueue_resolve_addr_work(struct cma_work *work, struct rdma_id_private *id_priv) { /* Balances with cma_id_put() in cma_work_handler */ cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDR_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; queue_work(cma_wq, &work->work); } static int cma_resolve_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms) { struct rdma_route *route = &id_priv->id.route; struct cma_work *work; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); if (!route->path_rec) route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; goto err1; } ret = cma_query_ib_route(id_priv, timeout_ms, work); if (ret) goto err2; return 0; err2: kfree(route->path_rec); route->path_rec = NULL; err1: kfree(work); return ret; } static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, unsigned long supported_gids, enum ib_gid_type default_gid) { if ((network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) && test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) return IB_GID_TYPE_ROCE_UDP_ENCAP; return default_gid; } /* * cma_iboe_set_path_rec_l2_fields() is helper function which sets * path record type based on GID type. * It also sets up other L2 fields which includes destination mac address * netdev ifindex, of the path record. * It returns the netdev of the bound interface for this path record entry. */ static struct net_device * cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; enum ib_gid_type gid_type = IB_GID_TYPE_ROCE; struct rdma_addr *addr = &route->addr; unsigned long supported_gids; struct net_device *ndev; if (!addr->dev_addr.bound_dev_if) return NULL; ndev = dev_get_by_index(addr->dev_addr.net, addr->dev_addr.bound_dev_if); if (!ndev) return NULL; supported_gids = roce_gid_type_mask_support(id_priv->id.device, id_priv->id.port_num); gid_type = cma_route_gid_type(addr->dev_addr.network, supported_gids, id_priv->gid_type); /* Use the hint from IP Stack to select GID Type */ if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) gid_type = ib_network_to_gid_type(addr->dev_addr.network); route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); route->path_rec->roce.route_resolved = true; sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); return ndev; } int rdma_set_ib_path(struct rdma_cm_id *id, struct sa_path_rec *path_rec) { struct rdma_id_private *id_priv; struct net_device *ndev; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec), GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } if (rdma_protocol_roce(id->device, id->port_num)) { ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err_free; } dev_put(ndev); } id->route.num_pri_alt_paths = 1; return 0; err_free: kfree(id->route.path_rec); id->route.path_rec = NULL; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_set_ib_path); static int cma_resolve_iw_route(struct rdma_id_private *id_priv) { struct cma_work *work; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; } static int get_vlan_ndev_tc(struct net_device *vlan_ndev, int prio) { struct net_device *dev; dev = vlan_dev_real_dev(vlan_ndev); if (dev->num_tc) return netdev_get_prio_tc_map(dev, prio); return (vlan_dev_get_egress_qos_mask(vlan_ndev, prio) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } struct iboe_prio_tc_map { int input_prio; int output_tc; bool found; }; static int get_lower_vlan_dev_tc(struct net_device *dev, struct netdev_nested_priv *priv) { struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); else if (dev->num_tc) map->output_tc = netdev_get_prio_tc_map(dev, map->input_prio); else map->output_tc = 0; /* We are interested only in first level VLAN device, so always * return 1 to stop iterating over next level devices. */ map->found = true; return 1; } static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. */ if (prio_tc_map.found) return prio_tc_map.output_tc; else if (ndev->num_tc) return netdev_get_prio_tc_map(ndev, prio); else return 0; } static __be32 cma_get_roce_udp_flow_label(struct rdma_id_private *id_priv) { struct sockaddr_in6 *addr6; u16 dport, sport; u32 hash, fl; addr6 = (struct sockaddr_in6 *)cma_src_addr(id_priv); fl = be32_to_cpu(addr6->sin6_flowinfo) & IB_GRH_FLOWLABEL_MASK; if ((cma_family(id_priv) != AF_INET6) || !fl) { dport = be16_to_cpu(cma_port(cma_dst_addr(id_priv))); sport = be16_to_cpu(cma_port(cma_src_addr(id_priv))); hash = (u32)sport * 31 + dport; fl = hash & IB_GRH_FLOWLABEL_MASK; } return cpu_to_be32(fl); } static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; struct rdma_addr *addr = &route->addr; struct cma_work *work; int ret; struct net_device *ndev; u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; u8 tos; mutex_lock(&id_priv->qp_mutex); tos = id_priv->tos_set ? id_priv->tos : default_roce_tos; mutex_unlock(&id_priv->qp_mutex); work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; goto err1; } route->num_pri_alt_paths = 1; ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err2; } rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &route->path_rec->sgid); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, &route->path_rec->dgid); if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB) /* TODO: get the hoplimit from the inet/inet6 device */ route->path_rec->hop_limit = addr->dev_addr.hoplimit; else route->path_rec->hop_limit = 1; route->path_rec->reversible = 1; route->path_rec->pkey = cpu_to_be16(0xffff); route->path_rec->mtu_selector = IB_SA_EQ; route->path_rec->sl = iboe_tos_to_sl(ndev, tos); route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate * PacketLifeTime. As per IBTA 12.7.34, * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). * Assuming a negligible local ACK delay, we can use * PacketLifeTime = local ACK timeout/2 * as a reasonable approximation for RoCE networks. */ mutex_lock(&id_priv->qp_mutex); if (id_priv->timeout_set && id_priv->timeout) route->path_rec->packet_life_time = id_priv->timeout - 1; else route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; mutex_unlock(&id_priv->qp_mutex); if (!route->path_rec->mtu) { ret = -EINVAL; goto err2; } if (rdma_protocol_roce_udp_encap(id_priv->id.device, id_priv->id.port_num)) route->path_rec->flow_label = cma_get_roce_udp_flow_label(id_priv); cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err2: kfree(route->path_rec); route->path_rec = NULL; route->num_pri_alt_paths = 0; err1: kfree(work); return ret; } int rdma_resolve_route(struct rdma_cm_id *id, unsigned long timeout_ms) { struct rdma_id_private *id_priv; int ret; if (!timeout_ms) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY)) return -EINVAL; cma_id_get(id_priv); if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_route(id_priv, timeout_ms); else if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_resolve_iboe_route(id_priv); if (!ret) cma_add_id_to_tree(id_priv); } else if (rdma_protocol_iwarp(id->device, id->port_num)) ret = cma_resolve_iw_route(id_priv); else ret = -ENOSYS; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_QUERY, RDMA_CM_ADDR_RESOLVED); cma_id_put(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_route); static void cma_set_loopback(struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); break; case AF_INET6: ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr, 0, 0, 0, htonl(1)); break; default: ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr, 0, 0, 0, htonl(1)); break; } } static int cma_bind_loopback(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; union ib_gid gid; enum ib_port_state port_state; unsigned int p; u16 pkey; int ret; cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cur_dev->device, 1)) continue; if (!cma_dev) cma_dev = cur_dev; rdma_for_each_port (cur_dev->device, p) { if (!ib_get_cached_port_state(cur_dev->device, p, &port_state) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; goto port_found; } } } if (!cma_dev) { ret = -ENODEV; goto out; } p = 1; port_found: ret = rdma_query_gid(cma_dev->device, p, 0, &gid); if (ret) goto out; ret = ib_get_cached_pkey(cma_dev->device, p, 0, &pkey); if (ret) goto out; id_priv->id.route.addr.dev_addr.dev_type = (rdma_protocol_ib(cma_dev->device, p)) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey); id_priv->id.port_num = p; cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); cma_set_loopback(cma_src_addr(id_priv)); out: mutex_unlock(&lock); return ret; } static void addr_handler(int status, struct sockaddr *src_addr, struct rdma_dev_addr *dev_addr, void *context) { struct rdma_id_private *id_priv = context; struct rdma_cm_event event = {}; struct sockaddr *addr; struct sockaddr_storage old_addr; mutex_lock(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_RESOLVED)) goto out; /* * Store the previous src address, so that if we fail to acquire * matching rdma device, old address can be restored back, which helps * to cancel the cma listen operation correctly. */ addr = cma_src_addr(id_priv); memcpy(&old_addr, addr, rdma_addr_size(addr)); memcpy(addr, src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) { status = cma_acquire_dev_by_src_ip(id_priv); if (status) pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n", status); rdma_restrack_add(&id_priv->res); } else if (status) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status); } if (status) { memcpy(addr, &old_addr, rdma_addr_size((struct sockaddr *)&old_addr)); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ADDR_BOUND)) goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; if (cma_cm_event_handler(id_priv, &event)) { destroy_id_handler_unlock(id_priv); return; } out: mutex_unlock(&id_priv->handler_mutex); } static int cma_resolve_loopback(struct rdma_id_private *id_priv) { struct cma_work *work; union ib_gid gid; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_bind_loopback(id_priv); if (ret) goto err; } rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) { struct cma_work *work; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_resolve_ib_dev(id_priv); if (ret) goto err; } rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if ((reuse && id_priv->state != RDMA_CM_LISTEN) || id_priv->state == RDMA_CM_IDLE) { id_priv->reuseaddr = reuse; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_reuseaddr); int rdma_set_afonly(struct rdma_cm_id *id, int afonly) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if (id_priv->state == RDMA_CM_IDLE || id_priv->state == RDMA_CM_ADDR_BOUND) { id_priv->options |= (1 << CMA_OPTION_AFONLY); id_priv->afonly = afonly; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_afonly); static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct sockaddr *addr; struct sockaddr_ib *sib; u64 sid, mask; __be16 port; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); port = htons(bind_list->port); switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_port = port; break; case AF_INET6: ((struct sockaddr_in6 *) addr)->sin6_port = port; break; case AF_IB: sib = (struct sockaddr_ib *) addr; sid = be64_to_cpu(sib->sib_sid); mask = be64_to_cpu(sib->sib_sid_mask); sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port)); sib->sib_sid_mask = cpu_to_be64(~0ULL); break; } id_priv->bind_list = bind_list; hlist_add_head(&id_priv->node, &bind_list->owners); } static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; int ret; lockdep_assert_held(&lock); bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; ret = cma_ps_alloc(id_priv->id.route.addr.dev_addr.net, ps, bind_list, snum); if (ret < 0) goto err; bind_list->ps = ps; bind_list->port = snum; cma_bind_port(bind_list, id_priv); return 0; err: kfree(bind_list); return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct rdma_id_private *cur_id; struct sockaddr *daddr = cma_dst_addr(id_priv); struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); lockdep_assert_held(&lock); hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); __be16 cur_dport = cma_port(cur_daddr); if (id_priv == cur_id) continue; /* different dest port -> unique */ if (!cma_any_port(daddr) && !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; /* different src address -> unique */ if (!cma_any_addr(saddr) && !cma_any_addr(cur_saddr) && cma_addr_cmp(saddr, cur_saddr)) continue; /* different dst address -> unique */ if (!cma_any_addr(daddr) && !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; return -EADDRNOTAVAIL; } return 0; } static int cma_alloc_any_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { static unsigned int last_used_port; int low, high, remaining; unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; lockdep_assert_held(&lock); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_inclusive(low, remaining + low - 1); retry: if (last_used_port != rover) { struct rdma_bind_list *bind_list; int ret; bind_list = cma_ps_find(net, ps, (unsigned short)rover); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, rover); } else { ret = cma_port_is_unique(bind_list, id_priv); if (!ret) cma_bind_port(bind_list, id_priv); } /* * Remember previously used port number in order to avoid * re-using same port immediately after it is closed. */ if (!ret) last_used_port = rover; if (ret != -EADDRNOTAVAIL) return ret; } if (--remaining) { rover++; if ((rover < low) || (rover > high)) rover = low; goto retry; } return -EADDRNOTAVAIL; } /* * Check that the requested port is available. This is called when trying to * bind to a specific port, or when trying to listen on a bound port. In * the latter case, the provided id_priv may already be on the bind_list, but * we still need to check that it's okay to start listening. */ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv, uint8_t reuseaddr) { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) continue; if (reuseaddr && cur_id->reuseaddr) continue; cur_addr = cma_src_addr(cur_id); if (id_priv->afonly && cur_id->afonly && (addr->sa_family != cur_addr->sa_family)) continue; if (cma_any_addr(addr) || cma_any_addr(cur_addr)) return -EADDRNOTAVAIL; if (!cma_addr_cmp(addr, cur_addr)) return -EADDRINUSE; } return 0; } static int cma_use_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list; unsigned short snum; int ret; lockdep_assert_held(&lock); snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; bind_list = cma_ps_find(id_priv->id.route.addr.dev_addr.net, ps, snum); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, snum); } else { ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); if (!ret) cma_bind_port(bind_list, id_priv); } return ret; } static enum rdma_ucm_port_space cma_select_inet_ps(struct rdma_id_private *id_priv) { switch (id_priv->id.ps) { case RDMA_PS_TCP: case RDMA_PS_UDP: case RDMA_PS_IPOIB: case RDMA_PS_IB: return id_priv->id.ps; default: return 0; } } static enum rdma_ucm_port_space cma_select_ib_ps(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps = 0; struct sockaddr_ib *sib; u64 sid_ps, mask, sid; sib = (struct sockaddr_ib *) cma_src_addr(id_priv); mask = be64_to_cpu(sib->sib_sid_mask) & RDMA_IB_IP_PS_MASK; sid = be64_to_cpu(sib->sib_sid) & mask; if ((id_priv->id.ps == RDMA_PS_IB) && (sid == (RDMA_IB_IP_PS_IB & mask))) { sid_ps = RDMA_IB_IP_PS_IB; ps = RDMA_PS_IB; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_TCP)) && (sid == (RDMA_IB_IP_PS_TCP & mask))) { sid_ps = RDMA_IB_IP_PS_TCP; ps = RDMA_PS_TCP; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_UDP)) && (sid == (RDMA_IB_IP_PS_UDP & mask))) { sid_ps = RDMA_IB_IP_PS_UDP; ps = RDMA_PS_UDP; } if (ps) { sib->sib_sid = cpu_to_be64(sid_ps | ntohs(cma_port((struct sockaddr *) sib))); sib->sib_sid_mask = cpu_to_be64(RDMA_IB_IP_PS_MASK | be64_to_cpu(sib->sib_sid_mask)); } return ps; } static int cma_get_port(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps; int ret; if (cma_family(id_priv) != AF_IB) ps = cma_select_inet_ps(id_priv); else ps = cma_select_ib_ps(id_priv); if (!ps) return -EPROTONOSUPPORT; mutex_lock(&lock); if (cma_any_port(cma_src_addr(id_priv))) ret = cma_alloc_any_port(ps, id_priv); else ret = cma_use_port(ps, id_priv); mutex_unlock(&lock); return ret; } static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, struct sockaddr *addr) { #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 *sin6; if (addr->sa_family != AF_INET6) return 0; sin6 = (struct sockaddr_in6 *) addr; if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) return 0; if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; #endif return 0; } int rdma_listen(struct rdma_cm_id *id, int backlog) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { struct sockaddr_in any_in = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN))) return -EINVAL; } /* * Once the ID reaches RDMA_CM_LISTEN it is not allowed to be reusable * any more, and has to be unique in the bind list. */ if (id_priv->reuseaddr) { mutex_lock(&lock); ret = cma_check_port(id_priv->bind_list, id_priv, 0); if (!ret) id_priv->reuseaddr = 0; mutex_unlock(&lock); if (ret) goto err; } id_priv->backlog = backlog; if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id->device, 1)) { ret = cma_ib_listen(id_priv); if (ret) goto err; } else if (rdma_cap_iw_cm(id->device, 1)) { ret = cma_iw_listen(id_priv, backlog); if (ret) goto err; } else { ret = -ENOSYS; goto err; } } else { ret = cma_listen_on_all(id_priv); if (ret) goto err; } return 0; err: id_priv->backlog = 0; /* * All the failure paths that lead here will not allow the req_handler's * to have run. */ cma_comp_exch(id_priv, RDMA_CM_LISTEN, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_listen); static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, struct sockaddr *addr, const struct sockaddr *daddr) { struct sockaddr *id_daddr; int ret; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT; if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1; memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1; ret = cma_acquire_dev_by_src_ip(id_priv); if (ret) goto err1; } if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { if (addr->sa_family == AF_INET) id_priv->afonly = 1; #if IS_ENABLED(CONFIG_IPV6) else if (addr->sa_family == AF_INET6) { struct net *net = id_priv->id.route.addr.dev_addr.net; id_priv->afonly = net->ipv6.sysctl.bindv6only; } #endif } id_daddr = cma_dst_addr(id_priv); if (daddr != id_daddr) memcpy(id_daddr, daddr, rdma_addr_size(addr)); id_daddr->sa_family = addr->sa_family; ret = cma_get_port(id_priv); if (ret) goto err2; if (!cma_any_addr(addr)) rdma_restrack_add(&id_priv->res); return 0; err2: if (id_priv->cma_dev) cma_release_dev(id_priv); err1: cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct sockaddr_storage zero_sock = {}; if (src_addr && src_addr->sa_family) return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); /* * When the src_addr is not specified, automatically supply an any addr */ zero_sock.ss_family = dst_addr->sa_family; if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)&zero_sock; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; } else if (dst_addr->sa_family == AF_IB) { ((struct sockaddr_ib *)&zero_sock)->sib_pkey = ((struct sockaddr_ib *)dst_addr)->sib_pkey; } return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); } /* * If required, resolve the source address for bind and leave the id_priv in * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior * calls made by ULP, a previously bound ID will not be re-bound and src_addr is * ignored. */ static int resolve_prepare_src(struct rdma_id_private *id_priv, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))) return -EINVAL; } else { memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); } if (cma_family(id_priv) != dst_addr->sa_family) { ret = -EINVAL; goto err_state; } return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr, unsigned long timeout_ms) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; ret = resolve_prepare_src(id_priv, src_addr, dst_addr); if (ret) return ret; if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); } else { if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { /* * The FSM can return back to RDMA_CM_ADDR_BOUND after * rdma_resolve_ip() is called, eg through the error * path in addr_handler(). If this happens the existing * request must be canceled before issuing a new one. * Since canceling a request is a bit slow and this * oddball path is rare, keep track once a request has * been issued. The track turns out to be a permanent * state since this is the only cancel as it is * immediately before rdma_resolve_ip(). */ if (id_priv->used_resolve_ip) rdma_addr_cancel(&id->route.addr.dev_addr); else id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, false, id_priv); } } if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_addr); int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); } EXPORT_SYMBOL(rdma_bind_addr); static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) { struct cma_hdr *cma_hdr; cma_hdr = hdr; cma_hdr->cma_version = CMA_VERSION; if (cma_family(id_priv) == AF_INET) { struct sockaddr_in *src4, *dst4; src4 = (struct sockaddr_in *) cma_src_addr(id_priv); dst4 = (struct sockaddr_in *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 4); cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; cma_hdr->port = src4->sin_port; } else if (cma_family(id_priv) == AF_INET6) { struct sockaddr_in6 *src6, *dst6; src6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); dst6 = (struct sockaddr_in6 *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 6); cma_hdr->src_addr.ip6 = src6->sin6_addr; cma_hdr->dst_addr.ip6 = dst6->sin6_addr; cma_hdr->port = src6->sin6_port; } return 0; } static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; const struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (ib_event->event) { case IB_CM_SIDR_REQ_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_SIDR_REP_RECEIVED: event.param.ud.private_data = ib_event->private_data; event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE; if (rep->status != IB_SIDR_SUCCESS) { event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = ib_event->param.sidr_rep_rcvd.status; pr_debug_ratelimited("RDMA CM: UNREACHABLE: bad SIDR reply. status %d\n", event.status); break; } ret = cma_set_qkey(id_priv, rep->qkey); if (ret) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to set qkey. status %d\n", ret); event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = ret; break; } ib_init_ah_attr_from_path(id_priv->id.device, id_priv->id.port_num, id_priv->id.route.path_rec, &event.param.ud.ah_attr, rep->sgid_attr); event.param.ud.qp_num = rep->qpn; event.param.ud.qkey = rep->qkey; event.event = RDMA_CM_EVENT_ESTABLISHED; event.status = 0; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); rdma_destroy_ah_attr(&event.param.ud.ah_attr); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; req.path = id_priv->id.route.path_rec; req.sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); req.max_cm_retries = CMA_MAX_CM_RETRIES; trace_cm_send_sidr_req(id_priv); ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req); if (ret) { ib_destroy_cm_id(id_priv->cm_id.ib); id_priv->cm_id.ib = NULL; } out: kfree(private_data); return ret; } static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_req_param req; struct rdma_route *route; void *private_data; struct ib_cm_id *id; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; route = &id_priv->id.route; if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } req.primary_path = &route->path_rec[0]; req.primary_path_inbound = route->path_rec_inbound; req.primary_path_outbound = route->path_rec_outbound; if (route->num_pri_alt_paths == 2) req.alternate_path = &route->path_rec[1]; req.ppath_sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; /* Alternate path SGID attribute currently unsupported */ req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.qp_num = id_priv->qp_num; req.qp_type = id_priv->id.qp_type; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; req.flow_control = conn_param->flow_control; req.retry_count = min_t(u8, 7, conn_param->retry_count); req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.max_cm_retries = CMA_MAX_CM_RETRIES; req.srq = id_priv->srq ? 1 : 0; req.ece.vendor_id = id_priv->ece.vendor_id; req.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_req(id_priv); ret = ib_send_cm_req(id_priv->cm_id.ib, &req); out: if (ret && !IS_ERR(id)) { ib_destroy_cm_id(id); id_priv->cm_id.ib = NULL; } kfree(private_data); return ret; } static int cma_connect_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_id *cm_id; int ret; struct iw_cm_conn_param iw_param; cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); mutex_lock(&id_priv->qp_mutex); cm_id->tos = id_priv->tos; cm_id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id_priv->cm_id.iw = cm_id; memcpy(&cm_id->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); memcpy(&cm_id->remote_addr, cma_dst_addr(id_priv), rdma_addr_size(cma_dst_addr(id_priv))); ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; if (conn_param) { iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; iw_param.qpn = id_priv->id.qp ? id_priv->qp_num : conn_param->qp_num; } else { memset(&iw_param, 0, sizeof iw_param); iw_param.qpn = id_priv->qp_num; } ret = iw_cm_connect(cm_id, &iw_param); out: if (ret) { iw_destroy_cm_id(cm_id); id_priv->cm_id.iw = NULL; } return ret; } /** * rdma_connect_locked - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Same as rdma_connect() but can only be called from the * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback. */ int rdma_connect_locked(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_connect_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto err_state; return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_connect_locked); /** * rdma_connect - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Users must have resolved a route for the rdma_cm_id to connect with by having * called rdma_resolve_route before calling this routine. * * This call will either connect to a remote QP or obtain remote QP information * for unconnected rdma_cm_id's. The actual operation is based on the * rdma_cm_id's port space. */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; mutex_lock(&id_priv->handler_mutex); ret = rdma_connect_locked(id, conn_param); mutex_unlock(&id_priv->handler_mutex); return ret; } EXPORT_SYMBOL(rdma_connect); /** * rdma_connect_ece - Initiate an active connection request with ECE data. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * @ece: ECE parameters * * See rdma_connect() explanation. */ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_connect(id, conn_param); } EXPORT_SYMBOL(rdma_connect_ece); static int cma_accept_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_rep_param rep; int ret; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; ret = cma_modify_qp_rts(id_priv, conn_param); if (ret) goto out; memset(&rep, 0, sizeof rep); rep.qp_num = id_priv->qp_num; rep.starting_psn = id_priv->seq_num; rep.private_data = conn_param->private_data; rep.private_data_len = conn_param->private_data_len; rep.responder_resources = conn_param->responder_resources; rep.initiator_depth = conn_param->initiator_depth; rep.failover_accepted = 0; rep.flow_control = conn_param->flow_control; rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); rep.srq = id_priv->srq ? 1 : 0; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_rep(id_priv); ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); out: return ret; } static int cma_accept_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_conn_param iw_param; int ret; if (!conn_param) return -EINVAL; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) return ret; iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; if (id_priv->id.qp) iw_param.qpn = id_priv->qp_num; else iw_param.qpn = conn_param->qp_num; return iw_cm_accept(id_priv->cm_id.iw, &iw_param); } static int cma_send_sidr_rep(struct rdma_id_private *id_priv, enum ib_cm_sidr_status status, u32 qkey, const void *private_data, int private_data_len) { struct ib_cm_sidr_rep_param rep; int ret; memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { if (qkey) ret = cma_set_qkey(id_priv, qkey); else ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; rep.qkey = id_priv->qkey; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; } rep.private_data = private_data; rep.private_data_len = private_data_len; trace_cm_send_sidr_rep(id_priv); return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep); } /** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request. * @conn_param: Information needed to establish the connection. This must be * provided if accepting a connection request. If accepting a connection * response, this parameter must be NULL. * * Typically, this routine is only called by the listener to accept a connection * request. It must also be called on the active side of a connection if the * user is performing their own QP transitions. * * In the case of error, a reject message is sent to the remote side and the * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. * * This function is for use by kernel ULPs and must be called from under the * handler callback. */ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) return -EINVAL; if (!id->qp && conn_param) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { if (conn_param) ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, conn_param->qkey, conn_param->private_data, conn_param->private_data_len); else ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, 0, NULL, 0); } else { if (conn_param) ret = cma_accept_ib(id_priv, conn_param); else ret = cma_rep_recv(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_accept_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto reject; return 0; reject: cma_modify_qp_err(id_priv); rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED); return ret; } EXPORT_SYMBOL(rdma_accept); int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_accept(id, conn_param); } EXPORT_SYMBOL(rdma_accept_ece); void rdma_lock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_lock_handler); void rdma_unlock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_unlock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_unlock_handler); int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; switch (id->device->node_type) { case RDMA_NODE_IB_CA: ret = ib_cm_notify(id_priv->cm_id.ib, event); break; default: ret = 0; break; } return ret; } EXPORT_SYMBOL(rdma_notify); int rdma_reject(struct rdma_cm_id *id, const void *private_data, u8 private_data_len, u8 reason) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); } else { trace_cm_send_rej(id_priv); ret = ib_send_cm_rej(id_priv->cm_id.ib, reason, NULL, 0, private_data, private_data_len); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw, private_data, private_data_len); } else { ret = -ENOSYS; } return ret; } EXPORT_SYMBOL(rdma_reject); int rdma_disconnect(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { ret = cma_modify_qp_err(id_priv); if (ret) goto out; /* Initiate or respond to a disconnect. */ trace_cm_disconnect(id_priv); if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) { if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0)) trace_cm_sent_drep(id_priv); } else { trace_cm_sent_dreq(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_disconnect(id_priv->cm_id.iw, 0); } else ret = -EINVAL; out: return ret; } EXPORT_SYMBOL(rdma_disconnect); static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, struct ib_sa_multicast *multicast, struct rdma_cm_event *event, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr; enum ib_gid_type gid_type; struct net_device *ndev; if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); event->status = status; event->param.ud.private_data = mc->context; if (status) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; return; } dev_addr = &id_priv->id.route.addr.dev_addr; ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); gid_type = id_priv->cma_dev ->default_gid_type[id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; event->event = RDMA_CM_EVENT_MULTICAST_JOIN; if (ib_init_ah_from_mcmember(id_priv->id.device, id_priv->id.port_num, &multicast->rec, ndev, gid_type, &event->param.ud.ah_attr)) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; goto out; } event->param.ud.qp_num = 0xFFFFFF; event->param.ud.qkey = id_priv->qkey; out: dev_put(ndev); } static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) { struct cma_multicast *mc = multicast->context; struct rdma_id_private *id_priv = mc->id_priv; struct rdma_cm_event event = {}; int ret = 0; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL || READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); if (!ret) { cma_make_mc_event(status, id_priv, multicast, &event, mc); ret = cma_cm_event_handler(id_priv, &event); } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); out: mutex_unlock(&id_priv->handler_mutex); return 0; } static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, union ib_gid *mgid) { unsigned char mc_map[MAX_ADDR_LEN]; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sockaddr_in *sin = (struct sockaddr_in *) addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if ((addr->sa_family == AF_INET6) && ((be32_to_cpu(sin6->sin6_addr.s6_addr32[0]) & 0xFFF0FFFF) == 0xFF10A01B)) { /* IPv6 address is an SA assigned MGID. */ memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else if (addr->sa_family == AF_IB) { memcpy(mgid, &((struct sockaddr_ib *) addr)->sib_addr, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { ipv6_ib_mc_map(&sin6->sin6_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } else { ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } } static int cma_join_ib_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct ib_sa_mcmember_rec rec; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; ib_sa_comp_mask comp_mask; int ret; ib_addr_get_mgid(dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (ret) return ret; if (!id_priv->qkey) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); rdma_addr_get_sgid(dev_addr, &rec.port_gid); rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = mc->join_state; comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE | IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL | IB_SA_MCMEMBER_REC_FLOW_LABEL | IB_SA_MCMEMBER_REC_TRAFFIC_CLASS; if (id_priv->id.ps == RDMA_PS_IPOIB) comp_mask |= IB_SA_MCMEMBER_REC_RATE | IB_SA_MCMEMBER_REC_RATE_SELECTOR | IB_SA_MCMEMBER_REC_MTU_SELECTOR | IB_SA_MCMEMBER_REC_MTU | IB_SA_MCMEMBER_REC_HOP_LIMIT; mc->sa_mc = ib_sa_join_multicast(&sa_client, id_priv->id.device, id_priv->id.port_num, &rec, comp_mask, GFP_KERNEL, cma_ib_mc_handler, mc); return PTR_ERR_OR_ZERO(mc->sa_mc); } static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type) { struct sockaddr_in *sin = (struct sockaddr_in *)addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else { mgid->raw[0] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0xff; mgid->raw[1] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0x0e; mgid->raw[2] = 0; mgid->raw[3] = 0; mgid->raw[4] = 0; mgid->raw[5] = 0; mgid->raw[6] = 0; mgid->raw[7] = 0; mgid->raw[8] = 0; mgid->raw[9] = 0; mgid->raw[10] = 0xff; mgid->raw[11] = 0xff; *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; } } static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (cma_zero_addr(addr)) return -EINVAL; gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) return -ENODEV; ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } } else { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) err = -ENOTSUPP; } dev_put(ndev); if (err || !ib.rec.mtu) return err ?: -EINVAL; if (!id_priv->qkey) cma_set_default_qkey(id_priv); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); cma_make_mc_event(0, id_priv, &ib, &mc->iboe_join.event, mc); queue_work(cma_wq, &mc->iboe_join.work); return 0; } int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, u8 join_state, void *context) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct cma_multicast *mc; int ret; /* Not supported for kernel QPs */ if (WARN_ON(id->qp)) return -EINVAL; /* ULP is calling this wrong. */ if (!id->device || (READ_ONCE(id_priv->state) != RDMA_CM_ADDR_BOUND && READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; if (id_priv->id.qp_type != IB_QPT_UD) return -EINVAL; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; memcpy(&mc->addr, addr, rdma_addr_size(addr)); mc->context = context; mc->id_priv = id_priv; mc->join_state = join_state; if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_iboe_join_multicast(id_priv, mc); if (ret) goto out_err; } else if (rdma_cap_ib_mcast(id->device, id->port_num)) { ret = cma_join_ib_multicast(id_priv, mc); if (ret) goto out_err; } else { ret = -ENOSYS; goto out_err; } spin_lock(&id_priv->lock); list_add(&mc->list, &id_priv->mc_list); spin_unlock(&id_priv->lock); return 0; out_err: kfree(mc); return ret; } EXPORT_SYMBOL(rdma_join_multicast); void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; struct cma_multicast *mc; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) continue; list_del(&mc->list); spin_unlock_irq(&id_priv->lock); WARN_ON(id_priv->cma_dev->device != id->device); destroy_mc(id_priv, mc); return; } spin_unlock_irq(&id_priv->lock); } EXPORT_SYMBOL(rdma_leave_multicast); static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr; struct cma_work *work; dev_addr = &id_priv->id.route.addr.dev_addr; if ((dev_addr->bound_dev_if == ndev->ifindex) && (net_eq(dev_net(ndev), dev_addr->net)) && memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) { pr_info("RDMA CM addr change for ndev %s used by id %p\n", ndev->name, &id_priv->id); work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; INIT_WORK(&work->work, cma_work_handler); work->id = id_priv; work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; cma_id_get(id_priv); queue_work(cma_wq, &work->work); } return 0; } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; if (event != NETDEV_BONDING_FAILOVER) return NOTIFY_DONE; if (!netif_is_bond_master(ndev)) return NOTIFY_DONE; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) list_for_each_entry(id_priv, &cma_dev->id_list, device_item) { ret = cma_netdev_change(ndev, id_priv); if (ret) goto out; } out: mutex_unlock(&lock); return ret; } static void cma_netevent_work_handler(struct work_struct *_work) { struct rdma_id_private *id_priv = container_of(_work, struct rdma_id_private, id.net_work); struct rdma_cm_event event = {}; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; if (cma_cm_event_handler(id_priv, &event)) { __acquire(&id_priv->handler_mutex); id_priv->cm_id.ib = NULL; cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); return; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); } static int cma_netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { struct id_table_entry *ips_node = NULL; struct rdma_id_private *current_id; struct neighbour *neigh = ctx; unsigned long flags; if (event != NETEVENT_NEIGH_UPDATE) return NOTIFY_DONE; spin_lock_irqsave(&id_table_lock, flags); if (neigh->tbl->family == AF_INET6) { struct sockaddr_in6 neigh_sock_6; neigh_sock_6.sin6_family = AF_INET6; neigh_sock_6.sin6_addr = *(struct in6_addr *)neigh->primary_key; ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_6); } else if (neigh->tbl->family == AF_INET) { struct sockaddr_in neigh_sock_4; neigh_sock_4.sin_family = AF_INET; neigh_sock_4.sin_addr.s_addr = *(__be32 *)(neigh->primary_key); ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_4); } else goto out; if (!ips_node) goto out; list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) { if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr, neigh->ha, ETH_ALEN)) continue; INIT_WORK(¤t_id->id.net_work, cma_netevent_work_handler); cma_id_get(current_id); queue_work(cma_wq, ¤t_id->id.net_work); } out: spin_unlock_irqrestore(&id_table_lock, flags); return NOTIFY_DONE; } static struct notifier_block cma_nb = { .notifier_call = cma_netdev_callback }; static struct notifier_block cma_netevent_cb = { .notifier_call = cma_netevent_callback }; static void cma_send_device_removal_put(struct rdma_id_private *id_priv) { struct rdma_cm_event event = { .event = RDMA_CM_EVENT_DEVICE_REMOVAL }; enum rdma_cm_state state; unsigned long flags; mutex_lock(&id_priv->handler_mutex); /* Record that we want to remove the device */ spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; if (state == RDMA_CM_DESTROYING || state == RDMA_CM_DEVICE_REMOVAL) { spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); return; } id_priv->state = RDMA_CM_DEVICE_REMOVAL; spin_unlock_irqrestore(&id_priv->lock, flags); if (cma_cm_event_handler(id_priv, &event)) { /* * At this point the ULP promises it won't call * rdma_destroy_id() concurrently */ cma_id_put(id_priv); mutex_unlock(&id_priv->handler_mutex); trace_cm_id_destroy(id_priv); _destroy_id(id_priv, state); return; } mutex_unlock(&id_priv->handler_mutex); /* * If this races with destroy then the thread that first assigns state * to a destroying does the cancel. */ cma_cancel_operation(id_priv, state); cma_id_put(id_priv); } static void cma_process_remove(struct cma_device *cma_dev) { mutex_lock(&lock); while (!list_empty(&cma_dev->id_list)) { struct rdma_id_private *id_priv = list_first_entry( &cma_dev->id_list, struct rdma_id_private, device_item); list_del_init(&id_priv->listen_item); list_del_init(&id_priv->device_item); cma_id_get(id_priv); mutex_unlock(&lock); cma_send_device_removal_put(id_priv); mutex_lock(&lock); } mutex_unlock(&lock); cma_dev_put(cma_dev); wait_for_completion(&cma_dev->comp); } static bool cma_supported(struct ib_device *device) { u32 i; rdma_for_each_port(device, i) { if (rdma_cap_ib_cm(device, i) || rdma_cap_iw_cm(device, i)) return true; } return false; } static int cma_add_one(struct ib_device *device) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; struct rdma_id_private *id_priv; unsigned long supported_gids = 0; int ret; u32 i; if (!cma_supported(device)) return -EOPNOTSUPP; cma_dev = kmalloc(sizeof(*cma_dev), GFP_KERNEL); if (!cma_dev) return -ENOMEM; cma_dev->device = device; cma_dev->default_gid_type = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_gid_type), GFP_KERNEL); if (!cma_dev->default_gid_type) { ret = -ENOMEM; goto free_cma_dev; } cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_roce_tos), GFP_KERNEL); if (!cma_dev->default_roce_tos) { ret = -ENOMEM; goto free_gid_type; } rdma_for_each_port (device, i) { supported_gids = roce_gid_type_mask_support(device, i); WARN_ON(!supported_gids); if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE)) cma_dev->default_gid_type[i - rdma_start_port(device)] = CMA_PREFERRED_ROCE_GID_TYPE; else cma_dev->default_gid_type[i - rdma_start_port(device)] = find_first_bit(&supported_gids, BITS_PER_LONG); cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0; } init_completion(&cma_dev->comp); refcount_set(&cma_dev->refcount, 1); INIT_LIST_HEAD(&cma_dev->id_list); ib_set_client_data(device, &cma_client, cma_dev); mutex_lock(&lock); list_add_tail(&cma_dev->list, &dev_list); list_for_each_entry(id_priv, &listen_any_list, listen_any_item) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) goto free_listen; } mutex_unlock(&lock); trace_cm_add_one(device); return 0; free_listen: list_del(&cma_dev->list); mutex_unlock(&lock); /* cma_process_remove() will delete to_destroy */ cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); free_gid_type: kfree(cma_dev->default_gid_type); free_cma_dev: kfree(cma_dev); return ret; } static void cma_remove_one(struct ib_device *device, void *client_data) { struct cma_device *cma_dev = client_data; trace_cm_remove_one(device); mutex_lock(&lock); list_del(&cma_dev->list); mutex_unlock(&lock); cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); kfree(cma_dev->default_gid_type); kfree(cma_dev); } static int cma_init_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); xa_init(&pernet->tcp_ps); xa_init(&pernet->udp_ps); xa_init(&pernet->ipoib_ps); xa_init(&pernet->ib_ps); return 0; } static void cma_exit_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); WARN_ON(!xa_empty(&pernet->tcp_ps)); WARN_ON(!xa_empty(&pernet->udp_ps)); WARN_ON(!xa_empty(&pernet->ipoib_ps)); WARN_ON(!xa_empty(&pernet->ib_ps)); } static struct pernet_operations cma_pernet_operations = { .init = cma_init_net, .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), }; static int __init cma_init(void) { int ret; /* * There is a rare lock ordering dependency in cma_netdev_callback() * that only happens when bonding is enabled. Teach lockdep that rtnl * must never be nested under lock so it can find these without having * to test with bonding. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { rtnl_lock(); mutex_lock(&lock); mutex_unlock(&lock); rtnl_unlock(); } cma_wq = alloc_ordered_workqueue("rdma_cm", WQ_MEM_RECLAIM); if (!cma_wq) return -ENOMEM; ret = register_pernet_subsys(&cma_pernet_operations); if (ret) goto err_wq; ib_sa_register_client(&sa_client); register_netdevice_notifier(&cma_nb); register_netevent_notifier(&cma_netevent_cb); ret = ib_register_client(&cma_client); if (ret) goto err; ret = cma_configfs_init(); if (ret) goto err_ib; return 0; err_ib: ib_unregister_client(&cma_client); err: unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret; } static void __exit cma_cleanup(void) { cma_configfs_exit(); ib_unregister_client(&cma_client); unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); destroy_workqueue(cma_wq); } module_init(cma_init); module_exit(cma_cleanup); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/rtnetlink.h> #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/ip_fib.h> int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { ASSERT_RTNL(); info->family = AF_INET; net->ipv4.fib_seq++; return call_fib_notifiers(net, event_type, info); } static unsigned int fib4_seq_read(struct net *net) { ASSERT_RTNL(); return net->ipv4.fib_seq + fib4_rules_seq_read(net); } static int fib4_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; err = fib4_rules_dump(net, nb, extack); if (err) return err; return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { .family = AF_INET, .fib_seq_read = fib4_seq_read, .fib_dump = fib4_dump, .owner = THIS_MODULE, }; int __net_init fib4_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.fib_seq = 0; ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.notifier_ops = ops; return 0; } void __net_exit fib4_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.notifier_ops); } |
| 3348 3348 3338 3327 3339 3338 3338 3295 3345 1896 3339 3341 118 98 3334 1831 1829 1825 1831 3334 3334 1832 1825 247 247 3322 3293 247 2 3326 3326 3338 10 3329 3338 3328 3 3329 3338 10 117 117 117 26 107 107 107 3330 3327 3321 3331 10 10 3315 3315 3320 3318 9 9 3316 11 117 118 118 118 11 117 117 116 117 117 117 3317 5 3316 3330 3325 91 3322 3337 3326 3338 3325 3328 3292 247 3337 3330 3329 3327 3331 3338 148 149 3320 3308 3342 3328 3336 3347 3318 3326 3320 3321 3338 3342 3340 3348 3340 3333 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" #include "internal.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 3 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, &seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) * * desc_update_last_finalized:A / desc_last_finalized_seq:A * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos) { struct prb_data_ring *data_ring = &rb->text_data_ring; unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* * Data blocks are not created for empty lines. Instead, the * reader will recognize these special lpos values and handle * it appropriately. */ blk_lpos->begin = EMPTY_LINE_LPOS; blk_lpos->next = EMPTY_LINE_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { /* Failed to allocate, specify a data-less block. */ blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* If the data block does not increase, there is nothing to do. */ if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) return NULL; /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { /* * Records that are just empty lines are also valid, even * though they do not have a data block. For such records * explicitly return empty string data to signify success. */ if (blk_lpos->begin == EMPTY_LINE_LPOS && blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; } /* Data lost, invalid, or otherwise unavailable. */ return NULL; } /* Regular data block: @begin less than @next and in same wrap. */ if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && blk_lpos->begin < blk_lpos->next) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == DATA_WRAPS(data_ring, blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* A valid data block will always have at least an ID. */ if (WARN_ON_ONCE(*data_size < sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB If desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * @last_finalized_seq value guarantees that all records up to and including * this sequence number are finalized and can be read. The only exception are * too old records which have already been overwritten. * * It is also guaranteed that @last_finalized_seq only increases. * * Be aware that finalized records following non-finalized records are not * reported because they are not yet available to the reader. For example, * a new record stored via printk() will not be available to a printer if * it follows a record that has not been finalized yet. However, once that * non-finalized record becomes finalized, @last_finalized_seq will be * appropriately updated and the full set of finalized records will be * available to the printer. And since each printk() caller will either * directly print or trigger deferred printing of all available unprinted * records, all printk() messages will get printed. */ static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long ulseq; /* * Guarantee the sequence number is loaded before loading the * associated record in order to guarantee that the record can be * seen by this CPU. This pairs with desc_update_last_finalized:A. */ ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq ); /* LMM(desc_last_finalized_seq:A) */ return __ulseq_to_u64seq(rb, ulseq); } static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count); /* * Check if there are records directly following @last_finalized_seq that are * finalized. If so, update @last_finalized_seq to the latest of these * records. It is not allowed to skip over records that are not yet finalized. */ static void desc_update_last_finalized(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; u64 old_seq = desc_last_finalized_seq(rb); unsigned long oldval; unsigned long newval; u64 finalized_seq; u64 try_seq; try_again: finalized_seq = old_seq; try_seq = finalized_seq + 1; /* Try to find later finalized records. */ while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { finalized_seq = try_seq; try_seq++; } /* No update needed if no later finalized record was found. */ if (finalized_seq == old_seq) return; oldval = __u64seq_to_ulseq(old_seq); newval = __u64seq_to_ulseq(finalized_seq); /* * Set the sequence number of a later finalized record that has been * seen. * * Guarantee the record data is visible to other CPUs before storing * its sequence number. This pairs with desc_last_finalized_seq:A. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then desc_read:A reads from * _prb_commit:B. * * Relies on: * * RELEASE from _prb_commit:B to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to desc_read:A * * Note: _prb_commit:B and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A * CPU (which performs the release) must have previously seen * _prb_commit:B. */ if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ old_seq = __ulseq_to_u64seq(rb, oldval); goto try_again; } } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ desc_update_last_finalized(rb); } } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB _prb_commit:B to prb_commit:A * matching * MB desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(e->rb, e->id); } /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { _prb_commit(e, desc_finalized); desc_update_last_finalized(e->rb); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /** * prb_next_reserve_seq() - Get the sequence number after the most recently * reserved record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what sequence * number will be assigned to the next reserved record. * * Note that depending on the situation, this value can be equal to or * higher than the sequence number returned by prb_next_seq(). * * Context: Any context. * Return: The sequence number that will be assigned to the next record * reserved. */ u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long last_finalized_id; atomic_long_t *state_var; u64 last_finalized_seq; unsigned long head_id; struct prb_desc desc; unsigned long diff; struct prb_desc *d; int err; /* * It may not be possible to read a sequence number for @head_id. * So the ID of @last_finailzed_seq is used to calculate what the * sequence number of @head_id will be. */ try_again: last_finalized_seq = desc_last_finalized_seq(rb); /* * @head_id is loaded after @last_finalized_seq to ensure that * it points to the record with @last_finalized_seq or newer. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then * prb_next_reserve_seq:A reads from desc_reserve:D. * * Relies on: * * RELEASE from desc_reserve:D to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A * * Note: desc_reserve:D and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A CPU * (which performs the release) must have previously seen * desc_read:C, which implies desc_reserve:D can be seen. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ d = to_desc(desc_ring, last_finalized_seq); state_var = &d->state_var; /* Extract the ID, used to specify the descriptor to read. */ last_finalized_id = DESC_ID(atomic_long_read(state_var)); /* Ensure @last_finalized_id is correct. */ err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); if (err == -EINVAL) { if (last_finalized_seq == 0) { /* * No record has been finalized or even reserved yet. * * The @head_id is initialized such that the first * increment will yield the first record (seq=0). * Handle it separately to avoid a negative @diff * below. */ if (head_id == DESC0_ID(desc_ring->count_bits)) return 0; /* * One or more descriptors are already reserved. Use * the descriptor ID of the first one (@seq=0) for * the @diff below. */ last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; } else { /* Record must have been overwritten. Try again. */ goto try_again; } } /* Diff of known descriptor IDs to compute related sequence numbers. */ diff = head_id - last_finalized_id; /* * @head_id points to the most recently reserved record, but this * function returns the sequence number that will be assigned to the * next (not yet reserved) record. Thus +1 is needed. */ return (last_finalized_seq + diff + 1); } /* * Non-blocking read of a record. * * On success @seq is updated to the record that was read and (if provided) * @r and @line_count will contain the read/calculated data. * * On failure @seq is updated to a record that is not yet available to the * reader, but it will be the next record available to the reader. * * Note: When the current CPU is in panic, this function will skip over any * non-existent/non-finalized records in order to allow the panic CPU * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { /* * Non-existent/non-finalized record. Must stop. * * For panic situations it cannot be expected that * non-finalized records will become finalized. But * there may be other finalized records beyond that * need to be printed for a panic situation. If this * is the panic CPU, skip this * non-existent/non-finalized record unless it is * at or beyond the head, in which case it is not * possible to continue. * * Note that new messages printed on panic CPU are * finalized when we are here. The only exception * might be the last message without trailing newline. * But it would have the sequence number returned * by "prb_next_reserve_seq() - 1". */ if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb))) (*seq)++; else return false; } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. It is guaranteed that all records * previous to the returned value have been finalized and are (or were) * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { u64 seq; seq = desc_last_finalized_seq(rb); /* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++; /* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 441 6 6 6 444 445 445 443 445 445 445 422 456 457 456 1 1 1 1 456 201 44 447 187 3 455 10 275 8 5 8 43 43 43 43 3 3 436 6 435 3 1 2 113 25 25 1 113 10 83 110 110 111 111 106 25 10 113 132 3 1 3 3 3 7 7 2 2 7 24 19 19 20 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 503 503 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 4 3 3 2 1 133 131 88 2 126 126 2 132 116 17 104 100 6 140 15 131 101 129 128 130 130 129 2 128 130 101 127 128 103 2 84 83 83 83 83 83 83 83 140 140 19 140 17 137 137 137 137 137 27 23 138 136 137 436 436 437 400 114 434 33 33 26 7 1 1 1 9 4 4 4 9 9 3 4 3 1 2 1 4 4 5 5 5 5 5 1 1 5 5 7 7 7 436 437 435 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/sizes.h> #include <linux/list_sort.h> #include "misc.h" #include "ctree.h" #include "block-group.h" #include "space-info.h" #include "disk-io.h" #include "free-space-cache.h" #include "free-space-tree.h" #include "volumes.h" #include "transaction.h" #include "ref-verify.h" #include "sysfs.h" #include "tree-log.h" #include "delalloc-space.h" #include "discard.h" #include "raid56.h" #include "zoned.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #ifdef CONFIG_BTRFS_DEBUG int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) && block_group->flags & BTRFS_BLOCK_GROUP_METADATA) || (btrfs_test_opt(fs_info, FRAGMENT_DATA) && block_group->flags & BTRFS_BLOCK_GROUP_DATA); } #endif /* * Return target flags in extended format or 0 if restripe for this chunk_type * is not in progress * * Should be called with balance_lock held */ static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags) { struct btrfs_balance_control *bctl = fs_info->balance_ctl; u64 target = 0; if (!bctl) return 0; if (flags & BTRFS_BLOCK_GROUP_DATA && bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) { target = BTRFS_BLOCK_GROUP_DATA | bctl->data.target; } else if (flags & BTRFS_BLOCK_GROUP_SYSTEM && bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) { target = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target; } else if (flags & BTRFS_BLOCK_GROUP_METADATA && bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) { target = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target; } return target; } /* * @flags: available profiles in extended format (see ctree.h) * * Return reduced profile in chunk format. If profile changing is in progress * (either running or paused) picks the target profile (if it's already * available), otherwise falls back to plain reducing. */ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags) { u64 num_devices = fs_info->fs_devices->rw_devices; u64 target; u64 raid_type; u64 allowed = 0; /* * See if restripe for this chunk_type is in progress, if so try to * reduce to the target profile */ spin_lock(&fs_info->balance_lock); target = get_restripe_target(fs_info, flags); if (target) { spin_unlock(&fs_info->balance_lock); return extended_to_chunk(target); } spin_unlock(&fs_info->balance_lock); /* First, mask out the RAID levels which aren't possible */ for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { if (num_devices >= btrfs_raid_array[raid_type].devs_min) allowed |= btrfs_raid_array[raid_type].bg_flag; } allowed &= flags; /* Select the highest-redundancy RAID level. */ if (allowed & BTRFS_BLOCK_GROUP_RAID1C4) allowed = BTRFS_BLOCK_GROUP_RAID1C4; else if (allowed & BTRFS_BLOCK_GROUP_RAID6) allowed = BTRFS_BLOCK_GROUP_RAID6; else if (allowed & BTRFS_BLOCK_GROUP_RAID1C3) allowed = BTRFS_BLOCK_GROUP_RAID1C3; else if (allowed & BTRFS_BLOCK_GROUP_RAID5) allowed = BTRFS_BLOCK_GROUP_RAID5; else if (allowed & BTRFS_BLOCK_GROUP_RAID10) allowed = BTRFS_BLOCK_GROUP_RAID10; else if (allowed & BTRFS_BLOCK_GROUP_RAID1) allowed = BTRFS_BLOCK_GROUP_RAID1; else if (allowed & BTRFS_BLOCK_GROUP_DUP) allowed = BTRFS_BLOCK_GROUP_DUP; else if (allowed & BTRFS_BLOCK_GROUP_RAID0) allowed = BTRFS_BLOCK_GROUP_RAID0; flags &= ~BTRFS_BLOCK_GROUP_PROFILE_MASK; return extended_to_chunk(flags | allowed); } u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags) { unsigned seq; u64 flags; do { flags = orig_flags; seq = read_seqbegin(&fs_info->profiles_lock); if (flags & BTRFS_BLOCK_GROUP_DATA) flags |= fs_info->avail_data_alloc_bits; else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) flags |= fs_info->avail_system_alloc_bits; else if (flags & BTRFS_BLOCK_GROUP_METADATA) flags |= fs_info->avail_metadata_alloc_bits; } while (read_seqretry(&fs_info->profiles_lock, seq)); return btrfs_reduce_alloc_profile(fs_info, flags); } void btrfs_get_block_group(struct btrfs_block_group *cache) { refcount_inc(&cache->refs); } void btrfs_put_block_group(struct btrfs_block_group *cache) { if (refcount_dec_and_test(&cache->refs)) { WARN_ON(cache->pinned > 0); /* * If there was a failure to cleanup a log tree, very likely due * to an IO failure on a writeback attempt of one or more of its * extent buffers, we could not do proper (and cheap) unaccounting * of their reserved space, so don't warn on reserved > 0 in that * case. */ if (!(cache->flags & BTRFS_BLOCK_GROUP_METADATA) || !BTRFS_FS_LOG_CLEANUP_ERROR(cache->fs_info)) WARN_ON(cache->reserved > 0); /* * A block_group shouldn't be on the discard_list anymore. * Remove the block_group from the discard_list to prevent us * from causing a panic due to NULL pointer dereference. */ if (WARN_ON(!list_empty(&cache->discard_list))) btrfs_discard_cancel_work(&cache->fs_info->discard_ctl, cache); kfree(cache->free_space_ctl); btrfs_free_chunk_map(cache->physical_map); kfree(cache); } } /* * This adds the block group to the fs_info rb tree for the block group cache */ static int btrfs_add_block_group_cache(struct btrfs_fs_info *info, struct btrfs_block_group *block_group) { struct rb_node **p; struct rb_node *parent = NULL; struct btrfs_block_group *cache; bool leftmost = true; ASSERT(block_group->length != 0); write_lock(&info->block_group_cache_lock); p = &info->block_group_cache_tree.rb_root.rb_node; while (*p) { parent = *p; cache = rb_entry(parent, struct btrfs_block_group, cache_node); if (block_group->start < cache->start) { p = &(*p)->rb_left; } else if (block_group->start > cache->start) { p = &(*p)->rb_right; leftmost = false; } else { write_unlock(&info->block_group_cache_lock); return -EEXIST; } } rb_link_node(&block_group->cache_node, parent, p); rb_insert_color_cached(&block_group->cache_node, &info->block_group_cache_tree, leftmost); write_unlock(&info->block_group_cache_lock); return 0; } /* * This will return the block group at or after bytenr if contains is 0, else * it will return the block group that contains the bytenr */ static struct btrfs_block_group *block_group_cache_tree_search( struct btrfs_fs_info *info, u64 bytenr, int contains) { struct btrfs_block_group *cache, *ret = NULL; struct rb_node *n; u64 end, start; read_lock(&info->block_group_cache_lock); n = info->block_group_cache_tree.rb_root.rb_node; while (n) { cache = rb_entry(n, struct btrfs_block_group, cache_node); end = cache->start + cache->length - 1; start = cache->start; if (bytenr < start) { if (!contains && (!ret || start < ret->start)) ret = cache; n = n->rb_left; } else if (bytenr > start) { if (contains && bytenr <= end) { ret = cache; break; } n = n->rb_right; } else { ret = cache; break; } } if (ret) btrfs_get_block_group(ret); read_unlock(&info->block_group_cache_lock); return ret; } /* * Return the block group that starts at or after bytenr */ struct btrfs_block_group *btrfs_lookup_first_block_group( struct btrfs_fs_info *info, u64 bytenr) { return block_group_cache_tree_search(info, bytenr, 0); } /* * Return the block group that contains the given bytenr */ struct btrfs_block_group *btrfs_lookup_block_group( struct btrfs_fs_info *info, u64 bytenr) { return block_group_cache_tree_search(info, bytenr, 1); } struct btrfs_block_group *btrfs_next_block_group( struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; struct rb_node *node; read_lock(&fs_info->block_group_cache_lock); /* If our block group was removed, we need a full search. */ if (RB_EMPTY_NODE(&cache->cache_node)) { const u64 next_bytenr = cache->start + cache->length; read_unlock(&fs_info->block_group_cache_lock); btrfs_put_block_group(cache); return btrfs_lookup_first_block_group(fs_info, next_bytenr); } node = rb_next(&cache->cache_node); btrfs_put_block_group(cache); if (node) { cache = rb_entry(node, struct btrfs_block_group, cache_node); btrfs_get_block_group(cache); } else cache = NULL; read_unlock(&fs_info->block_group_cache_lock); return cache; } /* * Check if we can do a NOCOW write for a given extent. * * @fs_info: The filesystem information object. * @bytenr: Logical start address of the extent. * * Check if we can do a NOCOW write for the given extent, and increments the * number of NOCOW writers in the block group that contains the extent, as long * as the block group exists and it's currently not in read-only mode. * * Returns: A non-NULL block group pointer if we can do a NOCOW write, the caller * is responsible for calling btrfs_dec_nocow_writers() later. * * Or NULL if we can not do a NOCOW write */ struct btrfs_block_group *btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) { struct btrfs_block_group *bg; bool can_nocow = true; bg = btrfs_lookup_block_group(fs_info, bytenr); if (!bg) return NULL; spin_lock(&bg->lock); if (bg->ro) can_nocow = false; else atomic_inc(&bg->nocow_writers); spin_unlock(&bg->lock); if (!can_nocow) { btrfs_put_block_group(bg); return NULL; } /* No put on block group, done by btrfs_dec_nocow_writers(). */ return bg; } /* * Decrement the number of NOCOW writers in a block group. * * This is meant to be called after a previous call to btrfs_inc_nocow_writers(), * and on the block group returned by that call. Typically this is called after * creating an ordered extent for a NOCOW write, to prevent races with scrub and * relocation. * * After this call, the caller should not use the block group anymore. It it wants * to use it, then it should get a reference on it before calling this function. */ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg) { if (atomic_dec_and_test(&bg->nocow_writers)) wake_up_var(&bg->nocow_writers); /* For the lookup done by a previous call to btrfs_inc_nocow_writers(). */ btrfs_put_block_group(bg); } void btrfs_wait_nocow_writers(struct btrfs_block_group *bg) { wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers)); } void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, const u64 start) { struct btrfs_block_group *bg; bg = btrfs_lookup_block_group(fs_info, start); ASSERT(bg); if (atomic_dec_and_test(&bg->reservations)) wake_up_var(&bg->reservations); btrfs_put_block_group(bg); } void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg) { struct btrfs_space_info *space_info = bg->space_info; ASSERT(bg->ro); if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA)) return; /* * Our block group is read only but before we set it to read only, * some task might have had allocated an extent from it already, but it * has not yet created a respective ordered extent (and added it to a * root's list of ordered extents). * Therefore wait for any task currently allocating extents, since the * block group's reservations counter is incremented while a read lock * on the groups' semaphore is held and decremented after releasing * the read access on that semaphore and creating the ordered extent. */ down_write(&space_info->groups_sem); up_write(&space_info->groups_sem); wait_var_event(&bg->reservations, !atomic_read(&bg->reservations)); } struct btrfs_caching_control *btrfs_get_caching_control( struct btrfs_block_group *cache) { struct btrfs_caching_control *ctl; spin_lock(&cache->lock); if (!cache->caching_ctl) { spin_unlock(&cache->lock); return NULL; } ctl = cache->caching_ctl; refcount_inc(&ctl->count); spin_unlock(&cache->lock); return ctl; } static void btrfs_put_caching_control(struct btrfs_caching_control *ctl) { if (refcount_dec_and_test(&ctl->count)) kfree(ctl); } /* * When we wait for progress in the block group caching, its because our * allocation attempt failed at least once. So, we must sleep and let some * progress happen before we try again. * * This function will sleep at least once waiting for new free space to show * up, and then it will check the block group free space numbers for our min * num_bytes. Another option is to have it go ahead and look in the rbtree for * a free extent of a given size, but this is a good start. * * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using * any of the information in this block group. */ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes) { struct btrfs_caching_control *caching_ctl; int progress; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return; /* * We've already failed to allocate from this block group, so even if * there's enough space in the block group it isn't contiguous enough to * allow for an allocation, so wait for at least the next wakeup tick, * or for the thing to be done. */ progress = atomic_read(&caching_ctl->progress); wait_event(caching_ctl->wait, btrfs_block_group_done(cache) || (progress != atomic_read(&caching_ctl->progress) && (cache->free_space_ctl->free_space >= num_bytes))); btrfs_put_caching_control(caching_ctl); } static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache, struct btrfs_caching_control *caching_ctl) { wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0; } static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) { struct btrfs_caching_control *caching_ctl; int ret; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0; ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); btrfs_put_caching_control(caching_ctl); return ret; } #ifdef CONFIG_BTRFS_DEBUG static void fragment_free_space(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; u64 start = block_group->start; u64 len = block_group->length; u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ? fs_info->nodesize : fs_info->sectorsize; u64 step = chunk << 1; while (len > chunk) { btrfs_remove_free_space(block_group, start, chunk); start += step; if (len < step) len = 0; else len -= step; } } #endif /* * Add a free space range to the in memory free space cache of a block group. * This checks if the range contains super block locations and any such * locations are not added to the free space cache. * * @block_group: The target block group. * @start: Start offset of the range. * @end: End offset of the range (exclusive). * @total_added_ret: Optional pointer to return the total amount of space * added to the block group's free space cache. * * Returns 0 on success or < 0 on error. */ int btrfs_add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end, u64 *total_added_ret) { struct btrfs_fs_info *info = block_group->fs_info; u64 extent_start, extent_end, size; int ret; if (total_added_ret) *total_added_ret = 0; while (start < end) { if (!find_first_extent_bit(&info->excluded_extents, start, &extent_start, &extent_end, EXTENT_DIRTY | EXTENT_UPTODATE, NULL)) break; if (extent_start <= start) { start = extent_end + 1; } else if (extent_start > start && extent_start < end) { size = extent_start - start; ret = btrfs_add_free_space_async_trimmed(block_group, start, size); if (ret) return ret; if (total_added_ret) *total_added_ret += size; start = extent_end + 1; } else { break; } } if (start < end) { size = end - start; ret = btrfs_add_free_space_async_trimmed(block_group, start, size); if (ret) return ret; if (total_added_ret) *total_added_ret += size; } return 0; } /* * Get an arbitrary extent item index / max_index through the block group * * @block_group the block group to sample from * @index: the integral step through the block group to grab from * @max_index: the granularity of the sampling * @key: return value parameter for the item we find * * Pre-conditions on indices: * 0 <= index <= max_index * 0 < max_index * * Returns: 0 on success, 1 if the search didn't yield a useful item, negative * error code on error. */ static int sample_block_group_extent_item(struct btrfs_caching_control *caching_ctl, struct btrfs_block_group *block_group, int index, int max_index, struct btrfs_key *found_key) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *extent_root; u64 search_offset; u64 search_end = block_group->start + block_group->length; struct btrfs_path *path; struct btrfs_key search_key; int ret = 0; ASSERT(index >= 0); ASSERT(index <= max_index); ASSERT(max_index > 0); lockdep_assert_held(&caching_ctl->mutex); lockdep_assert_held_read(&fs_info->commit_root_sem); path = btrfs_alloc_path(); if (!path) return -ENOMEM; extent_root = btrfs_extent_root(fs_info, max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET)); path->skip_locking = 1; path->search_commit_root = 1; path->reada = READA_FORWARD; search_offset = index * div_u64(block_group->length, max_index); search_key.objectid = block_group->start + search_offset; search_key.type = BTRFS_EXTENT_ITEM_KEY; search_key.offset = 0; btrfs_for_each_slot(extent_root, &search_key, found_key, path, ret) { /* Success; sampled an extent item in the block group */ if (found_key->type == BTRFS_EXTENT_ITEM_KEY && found_key->objectid >= block_group->start && found_key->objectid + found_key->offset <= search_end) break; /* We can't possibly find a valid extent item anymore */ if (found_key->objectid >= search_end) { ret = 1; break; } } lockdep_assert_held(&caching_ctl->mutex); lockdep_assert_held_read(&fs_info->commit_root_sem); btrfs_free_path(path); return ret; } /* * Best effort attempt to compute a block group's size class while caching it. * * @block_group: the block group we are caching * * We cannot infer the size class while adding free space extents, because that * logic doesn't care about contiguous file extents (it doesn't differentiate * between a 100M extent and 100 contiguous 1M extents). So we need to read the * file extent items. Reading all of them is quite wasteful, because usually * only a handful are enough to give a good answer. Therefore, we just grab 5 of * them at even steps through the block group and pick the smallest size class * we see. Since size class is best effort, and not guaranteed in general, * inaccuracy is acceptable. * * To be more explicit about why this algorithm makes sense: * * If we are caching in a block group from disk, then there are three major cases * to consider: * 1. the block group is well behaved and all extents in it are the same size * class. * 2. the block group is mostly one size class with rare exceptions for last * ditch allocations * 3. the block group was populated before size classes and can have a totally * arbitrary mix of size classes. * * In case 1, looking at any extent in the block group will yield the correct * result. For the mixed cases, taking the minimum size class seems like a good * approximation, since gaps from frees will be usable to the size class. For * 2., a small handful of file extents is likely to yield the right answer. For * 3, we can either read every file extent, or admit that this is best effort * anyway and try to stay fast. * * Returns: 0 on success, negative error code on error. */ static int load_block_group_size_class(struct btrfs_caching_control *caching_ctl, struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_key key; int i; u64 min_size = block_group->length; enum btrfs_block_group_size_class size_class = BTRFS_BG_SZ_NONE; int ret; if (!btrfs_block_group_should_use_size_class(block_group)) return 0; lockdep_assert_held(&caching_ctl->mutex); lockdep_assert_held_read(&fs_info->commit_root_sem); for (i = 0; i < 5; ++i) { ret = sample_block_group_extent_item(caching_ctl, block_group, i, 5, &key); if (ret < 0) goto out; if (ret > 0) continue; min_size = min_t(u64, min_size, key.offset); size_class = btrfs_calc_block_group_size_class(min_size); } if (size_class != BTRFS_BG_SZ_NONE) { spin_lock(&block_group->lock); block_group->size_class = size_class; spin_unlock(&block_group->lock); } out: return ret; } static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl) { struct btrfs_block_group *block_group = caching_ctl->block_group; struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *extent_root; struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_key key; u64 total_found = 0; u64 last = 0; u32 nritems; int ret; bool wakeup = true; path = btrfs_alloc_path(); if (!path) return -ENOMEM; last = max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET); extent_root = btrfs_extent_root(fs_info, last); #ifdef CONFIG_BTRFS_DEBUG /* * If we're fragmenting we don't want to make anybody think we can * allocate from this block group until we've had a chance to fragment * the free space. */ if (btrfs_should_fragment_free_space(block_group)) wakeup = false; #endif /* * We don't want to deadlock with somebody trying to allocate a new * extent for the extent root while also trying to search the extent * root to add free space. So we skip locking and search the commit * root, since its read-only */ path->skip_locking = 1; path->search_commit_root = 1; path->reada = READA_FORWARD; key.objectid = last; key.offset = 0; key.type = BTRFS_EXTENT_ITEM_KEY; next: ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) goto out; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); while (1) { if (btrfs_fs_closing(fs_info) > 1) { last = (u64)-1; break; } if (path->slots[0] < nritems) { btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); } else { ret = btrfs_find_next_key(extent_root, path, &key, 0, 0); if (ret) break; if (need_resched() || rwsem_is_contended(&fs_info->commit_root_sem)) { btrfs_release_path(path); up_read(&fs_info->commit_root_sem); mutex_unlock(&caching_ctl->mutex); cond_resched(); mutex_lock(&caching_ctl->mutex); down_read(&fs_info->commit_root_sem); goto next; } ret = btrfs_next_leaf(extent_root, path); if (ret < 0) goto out; if (ret) break; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); continue; } if (key.objectid < last) { key.objectid = last; key.offset = 0; key.type = BTRFS_EXTENT_ITEM_KEY; btrfs_release_path(path); goto next; } if (key.objectid < block_group->start) { path->slots[0]++; continue; } if (key.objectid >= block_group->start + block_group->length) break; if (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY) { u64 space_added; ret = btrfs_add_new_free_space(block_group, last, key.objectid, &space_added); if (ret) goto out; total_found += space_added; if (key.type == BTRFS_METADATA_ITEM_KEY) last = key.objectid + fs_info->nodesize; else last = key.objectid + key.offset; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; if (wakeup) { atomic_inc(&caching_ctl->progress); wake_up(&caching_ctl->wait); } } } path->slots[0]++; } ret = btrfs_add_new_free_space(block_group, last, block_group->start + block_group->length, NULL); out: btrfs_free_path(path); return ret; } static inline void btrfs_free_excluded_extents(const struct btrfs_block_group *bg) { clear_extent_bits(&bg->fs_info->excluded_extents, bg->start, bg->start + bg->length - 1, EXTENT_UPTODATE); } static noinline void caching_thread(struct btrfs_work *work) { struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_caching_control *caching_ctl; int ret; caching_ctl = container_of(work, struct btrfs_caching_control, work); block_group = caching_ctl->block_group; fs_info = block_group->fs_info; mutex_lock(&caching_ctl->mutex); down_read(&fs_info->commit_root_sem); load_block_group_size_class(caching_ctl, block_group); if (btrfs_test_opt(fs_info, SPACE_CACHE)) { ret = load_free_space_cache(block_group); if (ret == 1) { ret = 0; goto done; } /* * We failed to load the space cache, set ourselves to * CACHE_STARTED and carry on. */ spin_lock(&block_group->lock); block_group->cached = BTRFS_CACHE_STARTED; spin_unlock(&block_group->lock); wake_up(&caching_ctl->wait); } /* * If we are in the transaction that populated the free space tree we * can't actually cache from the free space tree as our commit root and * real root are the same, so we could change the contents of the blocks * while caching. Instead do the slow caching in this case, and after * the transaction has committed we will be safe. */ if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); done: spin_lock(&block_group->lock); block_group->caching_ctl = NULL; block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED; spin_unlock(&block_group->lock); #ifdef CONFIG_BTRFS_DEBUG if (btrfs_should_fragment_free_space(block_group)) { u64 bytes_used; spin_lock(&block_group->space_info->lock); spin_lock(&block_group->lock); bytes_used = block_group->length - block_group->used; block_group->space_info->bytes_used += bytes_used >> 1; spin_unlock(&block_group->lock); spin_unlock(&block_group->space_info->lock); fragment_free_space(block_group); } #endif up_read(&fs_info->commit_root_sem); btrfs_free_excluded_extents(block_group); mutex_unlock(&caching_ctl->mutex); wake_up(&caching_ctl->wait); btrfs_put_caching_control(caching_ctl); btrfs_put_block_group(block_group); } int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; /* Allocator for zoned filesystems does not use the cache at all */ if (btrfs_is_zoned(fs_info)) return 0; caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS); if (!caching_ctl) return -ENOMEM; INIT_LIST_HEAD(&caching_ctl->list); mutex_init(&caching_ctl->mutex); init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; refcount_set(&caching_ctl->count, 2); atomic_set(&caching_ctl->progress, 0); btrfs_init_work(&caching_ctl->work, caching_thread, NULL); spin_lock(&cache->lock); if (cache->cached != BTRFS_CACHE_NO) { kfree(caching_ctl); caching_ctl = cache->caching_ctl; if (caching_ctl) refcount_inc(&caching_ctl->count); spin_unlock(&cache->lock); goto out; } WARN_ON(cache->caching_ctl); cache->caching_ctl = caching_ctl; cache->cached = BTRFS_CACHE_STARTED; spin_unlock(&cache->lock); write_lock(&fs_info->block_group_cache_lock); refcount_inc(&caching_ctl->count); list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups); write_unlock(&fs_info->block_group_cache_lock); btrfs_get_block_group(cache); btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); out: if (wait && caching_ctl) ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); if (caching_ctl) btrfs_put_caching_control(caching_ctl); return ret; } static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) { u64 extra_flags = chunk_to_extended(flags) & BTRFS_EXTENDED_PROFILE_MASK; write_seqlock(&fs_info->profiles_lock); if (flags & BTRFS_BLOCK_GROUP_DATA) fs_info->avail_data_alloc_bits &= ~extra_flags; if (flags & BTRFS_BLOCK_GROUP_METADATA) fs_info->avail_metadata_alloc_bits &= ~extra_flags; if (flags & BTRFS_BLOCK_GROUP_SYSTEM) fs_info->avail_system_alloc_bits &= ~extra_flags; write_sequnlock(&fs_info->profiles_lock); } /* * Clear incompat bits for the following feature(s): * * - RAID56 - in case there's neither RAID5 nor RAID6 profile block group * in the whole filesystem * * - RAID1C34 - same as above for RAID1C3 and RAID1C4 block groups */ static void clear_incompat_bg_bits(struct btrfs_fs_info *fs_info, u64 flags) { bool found_raid56 = false; bool found_raid1c34 = false; if ((flags & BTRFS_BLOCK_GROUP_RAID56_MASK) || (flags & BTRFS_BLOCK_GROUP_RAID1C3) || (flags & BTRFS_BLOCK_GROUP_RAID1C4)) { struct list_head *head = &fs_info->space_info; struct btrfs_space_info *sinfo; list_for_each_entry_rcu(sinfo, head, list) { down_read(&sinfo->groups_sem); if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID5])) found_raid56 = true; if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID6])) found_raid56 = true; if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C3])) found_raid1c34 = true; if (!list_empty(&sinfo->block_groups[BTRFS_RAID_RAID1C4])) found_raid1c34 = true; up_read(&sinfo->groups_sem); } if (!found_raid56) btrfs_clear_fs_incompat(fs_info, RAID56); if (!found_raid1c34) btrfs_clear_fs_incompat(fs_info, RAID1C34); } } static struct btrfs_root *btrfs_block_group_root(struct btrfs_fs_info *fs_info) { if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) return fs_info->block_group_root; return btrfs_extent_root(fs_info, 0); } static int remove_block_group_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root; struct btrfs_key key; int ret; root = btrfs_block_group_root(fs_info); key.objectid = block_group->start; key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; key.offset = block_group->length; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) ret = -ENOENT; if (ret < 0) return ret; ret = btrfs_del_item(trans, root, path); return ret; } int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_chunk_map *map) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path; struct btrfs_block_group *block_group; struct btrfs_free_cluster *cluster; struct inode *inode; struct kobject *kobj = NULL; int ret; int index; int factor; struct btrfs_caching_control *caching_ctl = NULL; bool remove_map; bool remove_rsv = false; block_group = btrfs_lookup_block_group(fs_info, map->start); if (!block_group) return -ENOENT; BUG_ON(!block_group->ro); trace_btrfs_remove_block_group(block_group); /* * Free the reserved super bytes from this block group before * remove it. */ btrfs_free_excluded_extents(block_group); btrfs_free_ref_tree_range(fs_info, block_group->start, block_group->length); index = btrfs_bg_flags_to_raid_index(block_group->flags); factor = btrfs_bg_type_to_factor(block_group->flags); /* make sure this block group isn't part of an allocation cluster */ cluster = &fs_info->data_alloc_cluster; spin_lock(&cluster->refill_lock); btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&cluster->refill_lock); /* * make sure this block group isn't part of a metadata * allocation cluster */ cluster = &fs_info->meta_alloc_cluster; spin_lock(&cluster->refill_lock); btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&cluster->refill_lock); btrfs_clear_treelog_bg(block_group); btrfs_clear_data_reloc_bg(block_group); path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } /* * get the inode first so any iput calls done for the io_list * aren't the final iput (no unlinks allowed now) */ inode = lookup_free_space_inode(block_group, path); mutex_lock(&trans->transaction->cache_write_mutex); /* * Make sure our free space cache IO is done before removing the * free space inode */ spin_lock(&trans->transaction->dirty_bgs_lock); if (!list_empty(&block_group->io_list)) { list_del_init(&block_group->io_list); WARN_ON(!IS_ERR(inode) && inode != block_group->io_ctl.inode); spin_unlock(&trans->transaction->dirty_bgs_lock); btrfs_wait_cache_io(trans, block_group, path); btrfs_put_block_group(block_group); spin_lock(&trans->transaction->dirty_bgs_lock); } if (!list_empty(&block_group->dirty_list)) { list_del_init(&block_group->dirty_list); remove_rsv = true; btrfs_put_block_group(block_group); } spin_unlock(&trans->transaction->dirty_bgs_lock); mutex_unlock(&trans->transaction->cache_write_mutex); ret = btrfs_remove_free_space_inode(trans, inode, block_group); if (ret) goto out; write_lock(&fs_info->block_group_cache_lock); rb_erase_cached(&block_group->cache_node, &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); /* Once for the block groups rbtree */ btrfs_put_block_group(block_group); write_unlock(&fs_info->block_group_cache_lock); down_write(&block_group->space_info->groups_sem); /* * we must use list_del_init so people can check to see if they * are still on the list after taking the semaphore */ list_del_init(&block_group->list); if (list_empty(&block_group->space_info->block_groups[index])) { kobj = block_group->space_info->block_group_kobjs[index]; block_group->space_info->block_group_kobjs[index] = NULL; clear_avail_alloc_bits(fs_info, block_group->flags); } up_write(&block_group->space_info->groups_sem); clear_incompat_bg_bits(fs_info, block_group->flags); if (kobj) { kobject_del(kobj); kobject_put(kobj); } if (block_group->cached == BTRFS_CACHE_STARTED) btrfs_wait_block_group_cache_done(block_group); write_lock(&fs_info->block_group_cache_lock); caching_ctl = btrfs_get_caching_control(block_group); if (!caching_ctl) { struct btrfs_caching_control *ctl; list_for_each_entry(ctl, &fs_info->caching_block_groups, list) { if (ctl->block_group == block_group) { caching_ctl = ctl; refcount_inc(&caching_ctl->count); break; } } } if (caching_ctl) list_del_init(&caching_ctl->list); write_unlock(&fs_info->block_group_cache_lock); if (caching_ctl) { /* Once for the caching bgs list and once for us. */ btrfs_put_caching_control(caching_ctl); btrfs_put_caching_control(caching_ctl); } spin_lock(&trans->transaction->dirty_bgs_lock); WARN_ON(!list_empty(&block_group->dirty_list)); WARN_ON(!list_empty(&block_group->io_list)); spin_unlock(&trans->transaction->dirty_bgs_lock); btrfs_remove_free_space_cache(block_group); spin_lock(&block_group->space_info->lock); list_del_init(&block_group->ro_list); if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) { WARN_ON(block_group->space_info->total_bytes < block_group->length); WARN_ON(block_group->space_info->bytes_readonly < block_group->length - block_group->zone_unusable); WARN_ON(block_group->space_info->bytes_zone_unusable < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); } block_group->space_info->total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info, -block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); /* * Remove the free space for the block group from the free space tree * and the block group's item from the extent tree before marking the * block group as removed. This is to prevent races with tasks that * freeze and unfreeze a block group, this task and another task * allocating a new block group - the unfreeze task ends up removing * the block group's extent map before the task calling this function * deletes the block group item from the extent tree, allowing for * another task to attempt to create another block group with the same * item key (and failing with -EEXIST and a transaction abort). */ ret = remove_block_group_free_space(trans, block_group); if (ret) goto out; ret = remove_block_group_item(trans, path, block_group); if (ret < 0) goto out; spin_lock(&block_group->lock); set_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags); /* * At this point trimming or scrub can't start on this block group, * because we removed the block group from the rbtree * fs_info->block_group_cache_tree so no one can't find it anymore and * even if someone already got this block group before we removed it * from the rbtree, they have already incremented block_group->frozen - * if they didn't, for the trimming case they won't find any free space * entries because we already removed them all when we called * btrfs_remove_free_space_cache(). * * And we must not remove the chunk map from the fs_info->mapping_tree * to prevent the same logical address range and physical device space * ranges from being reused for a new block group. This is needed to * avoid races with trimming and scrub. * * An fs trim operation (btrfs_trim_fs() / btrfs_ioctl_fitrim()) is * completely transactionless, so while it is trimming a range the * currently running transaction might finish and a new one start, * allowing for new block groups to be created that can reuse the same * physical device locations unless we take this special care. * * There may also be an implicit trim operation if the file system * is mounted with -odiscard. The same protections must remain * in place until the extents have been discarded completely when * the transaction commit has completed. */ remove_map = (atomic_read(&block_group->frozen) == 0); spin_unlock(&block_group->lock); if (remove_map) btrfs_remove_chunk_map(fs_info, map); out: /* Once for the lookup reference */ btrfs_put_block_group(block_group); if (remove_rsv) btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); btrfs_free_path(path); return ret; } struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, const u64 chunk_offset) { struct btrfs_root *root = btrfs_block_group_root(fs_info); struct btrfs_chunk_map *map; unsigned int num_items; map = btrfs_find_chunk_map(fs_info, chunk_offset, 1); ASSERT(map != NULL); ASSERT(map->start == chunk_offset); /* * We need to reserve 3 + N units from the metadata space info in order * to remove a block group (done at btrfs_remove_chunk() and at * btrfs_remove_block_group()), which are used for: * * 1 unit for adding the free space inode's orphan (located in the tree * of tree roots). * 1 unit for deleting the block group item (located in the extent * tree). * 1 unit for deleting the free space item (located in tree of tree * roots). * N units for deleting N device extent items corresponding to each * stripe (located in the device tree). * * In order to remove a block group we also need to reserve units in the * system space info in order to update the chunk tree (update one or * more device items and remove one chunk item), but this is done at * btrfs_remove_chunk() through a call to check_system_chunk(). */ num_items = 3 + map->num_stripes; btrfs_free_chunk_map(map); return btrfs_start_transaction_fallback_global_rsv(root, num_items); } /* * Mark block group @cache read-only, so later write won't happen to block * group @cache. * * If @force is not set, this function will only mark the block group readonly * if we have enough free space (1M) in other metadata/system block groups. * If @force is not set, this function will mark the block group readonly * without checking free space. * * NOTE: This function doesn't care if other block groups can contain all the * data in this block group. That check should be done by relocation routine, * not this function. */ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) { struct btrfs_space_info *sinfo = cache->space_info; u64 num_bytes; int ret = -ENOSPC; spin_lock(&sinfo->lock); spin_lock(&cache->lock); if (cache->swap_extents) { ret = -ETXTBSY; goto out; } if (cache->ro) { cache->ro++; ret = 0; goto out; } num_bytes = cache->length - cache->reserved - cache->pinned - cache->bytes_super - cache->zone_unusable - cache->used; /* * Data never overcommits, even in mixed mode, so do just the straight * check of left over space in how much we have allocated. */ if (force) { ret = 0; } else if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) { u64 sinfo_used = btrfs_space_info_used(sinfo, true); /* * Here we make sure if we mark this bg RO, we still have enough * free space as buffer. */ if (sinfo_used + num_bytes <= sinfo->total_bytes) ret = 0; } else { /* * We overcommit metadata, so we need to do the * btrfs_can_overcommit check here, and we need to pass in * BTRFS_RESERVE_NO_FLUSH to give ourselves the most amount of * leeway to allow us to mark this block group as read only. */ if (btrfs_can_overcommit(cache->fs_info, sinfo, num_bytes, BTRFS_RESERVE_NO_FLUSH)) ret = 0; } if (!ret) { sinfo->bytes_readonly += num_bytes; if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes to readonly */ sinfo->bytes_readonly += cache->zone_unusable; btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, -cache->zone_unusable); cache->zone_unusable = 0; } cache->ro++; list_add_tail(&cache->ro_list, &sinfo->ro_bgs); } out: spin_unlock(&cache->lock); spin_unlock(&sinfo->lock); if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) { btrfs_info(cache->fs_info, "unable to make block group %llu ro", cache->start); btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0); } return ret; } static bool clean_pinned_extents(struct btrfs_trans_handle *trans, struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; struct btrfs_transaction *prev_trans = NULL; const u64 start = bg->start; const u64 end = start + bg->length - 1; int ret; spin_lock(&fs_info->trans_lock); if (trans->transaction->list.prev != &fs_info->trans_list) { prev_trans = list_last_entry(&trans->transaction->list, struct btrfs_transaction, list); refcount_inc(&prev_trans->use_count); } spin_unlock(&fs_info->trans_lock); /* * Hold the unused_bg_unpin_mutex lock to avoid racing with * btrfs_finish_extent_commit(). If we are at transaction N, another * task might be running finish_extent_commit() for the previous * transaction N - 1, and have seen a range belonging to the block * group in pinned_extents before we were able to clear the whole block * group range from pinned_extents. This means that task can lookup for * the block group after we unpinned it from pinned_extents and removed * it, leading to an error at unpin_extent_range(). */ mutex_lock(&fs_info->unused_bg_unpin_mutex); if (prev_trans) { ret = clear_extent_bits(&prev_trans->pinned_extents, start, end, EXTENT_DIRTY); if (ret) goto out; } ret = clear_extent_bits(&trans->transaction->pinned_extents, start, end, EXTENT_DIRTY); out: mutex_unlock(&fs_info->unused_bg_unpin_mutex); if (prev_trans) btrfs_put_transaction(prev_trans); return ret == 0; } /* * Process the unused_bgs list and remove any that don't have any allocated * space inside of them. */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { LIST_HEAD(retry_list); struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; const bool async_trim_enabled = btrfs_test_opt(fs_info, DISCARD_ASYNC); int ret = 0; if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; if (btrfs_fs_closing(fs_info)) return; /* * Long running balances can keep us blocked here for eternity, so * simply skip deletion if we're unable to get the mutex. */ if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) return; spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { u64 used; int trimming; block_group = list_first_entry(&fs_info->unused_bgs, struct btrfs_block_group, bg_list); list_del_init(&block_group->bg_list); space_info = block_group->space_info; if (ret || btrfs_mixed_space_info(space_info)) { btrfs_put_block_group(block_group); continue; } spin_unlock(&fs_info->unused_bgs_lock); btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group); /* Don't want to race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); /* * Async discard moves the final block group discard to be prior * to the unused_bgs code path. Therefore, if it's not fully * trimmed, punt it back to the async discard lists. */ if (btrfs_test_opt(fs_info, DISCARD_ASYNC) && !btrfs_is_free_space_trimmed(block_group)) { trace_btrfs_skip_unused_block_group(block_group); up_write(&space_info->groups_sem); /* Requeue if we failed because of async discard */ btrfs_discard_queue_work(&fs_info->discard_ctl, block_group); goto next; } spin_lock(&space_info->lock); spin_lock(&block_group->lock); if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have * outstanding allocations in this block group. We do * the ro check in case balance is currently acting on * this block group. * * Also bail out if this is the only block group for its * type, because otherwise we would lose profile * information from fs_info->avail_*_alloc_bits and the * next block group of this type would be created with a * "single" profile (even if we're in a raid fs) because * fs_info->avail_*_alloc_bits would be 0. */ trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } /* * The block group may be unused but there may be space reserved * accounting with the existence of that block group, that is, * space_info->bytes_may_use was incremented by a task but no * space was yet allocated from the block group by the task. * That space may or may not be allocated, as we are generally * pessimistic about space reservation for metadata as well as * for data when using compression (as we reserve space based on * the worst case, when data can't be compressed, and before * actually attempting compression, before starting writeback). * * So check if the total space of the space_info minus the size * of this block group is less than the used space of the * space_info - if that's the case, then it means we have tasks * that might be relying on the block group in order to allocate * extents, and add back the block group to the unused list when * we finish, so that we retry later in case no tasks ended up * needing to allocate extents from the block group. */ used = btrfs_space_info_used(space_info, true); if (space_info->total_bytes - block_group->length < used && block_group->zone_unusable < block_group->length) { /* * Add a reference for the list, compensate for the ref * drop under the "next" label for the * fs_info->unused_bgs list. */ btrfs_get_block_group(block_group); list_add_tail(&block_group->bg_list, &retry_list); trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); /* We don't want to force the issue, only flip if it's ok. */ ret = inc_block_group_ro(block_group, 0); up_write(&space_info->groups_sem); if (ret < 0) { ret = 0; goto next; } ret = btrfs_zone_finish(block_group); if (ret < 0) { btrfs_dec_block_group_ro(block_group); if (ret == -EAGAIN) ret = 0; goto next; } /* * Want to do this before we do anything else so we can recover * properly if we fail to join the transaction. */ trans = btrfs_start_trans_remove_block_group(fs_info, block_group->start); if (IS_ERR(trans)) { btrfs_dec_block_group_ro(block_group); ret = PTR_ERR(trans); goto next; } /* * We could have pending pinned extents for this block group, * just delete them, we don't care about them anymore. */ if (!clean_pinned_extents(trans, block_group)) { btrfs_dec_block_group_ro(block_group); goto end_trans; } /* * At this point, the block_group is read only and should fail * new allocations. However, btrfs_finish_extent_commit() can * cause this block_group to be placed back on the discard * lists because now the block_group isn't fully discarded. * Bail here and try again later after discarding everything. */ spin_lock(&fs_info->discard_ctl.lock); if (!list_empty(&block_group->discard_list)) { spin_unlock(&fs_info->discard_ctl.lock); btrfs_dec_block_group_ro(block_group); btrfs_discard_queue_work(&fs_info->discard_ctl, block_group); goto end_trans; } spin_unlock(&fs_info->discard_ctl.lock); /* Reset pinned so btrfs_put_block_group doesn't complain */ spin_lock(&space_info->lock); spin_lock(&block_group->lock); btrfs_space_info_update_bytes_pinned(fs_info, space_info, -block_group->pinned); space_info->bytes_readonly += block_group->pinned; block_group->pinned = 0; spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); /* * The normal path here is an unused block group is passed here, * then trimming is handled in the transaction commit path. * Async discard interposes before this to do the trimming * before coming down the unused block group path as trimming * will no longer be done later in the transaction commit path. */ if (!async_trim_enabled && btrfs_test_opt(fs_info, DISCARD_ASYNC)) goto flip_async; /* * DISCARD can flip during remount. On zoned filesystems, we * need to reset sequential-required zones. */ trimming = btrfs_test_opt(fs_info, DISCARD_SYNC) || btrfs_is_zoned(fs_info); /* Implicit trim during transaction commit. */ if (trimming) btrfs_freeze_block_group(block_group); /* * Btrfs_remove_chunk will abort the transaction if things go * horribly wrong. */ ret = btrfs_remove_chunk(trans, block_group->start); if (ret) { if (trimming) btrfs_unfreeze_block_group(block_group); goto end_trans; } /* * If we're not mounted with -odiscard, we can just forget * about this block group. Otherwise we'll need to wait * until transaction commit to do the actual discard. */ if (trimming) { spin_lock(&fs_info->unused_bgs_lock); /* * A concurrent scrub might have added us to the list * fs_info->unused_bgs, so use a list_move operation * to add the block group to the deleted_bgs list. */ list_move(&block_group->bg_list, &trans->transaction->deleted_bgs); spin_unlock(&fs_info->unused_bgs_lock); btrfs_get_block_group(block_group); } end_trans: btrfs_end_transaction(trans); next: btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); return; flip_async: btrfs_end_transaction(trans); spin_lock(&fs_info->unused_bgs_lock); list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_put_block_group(block_group); btrfs_discard_punt_unused_bgs_list(fs_info); } void btrfs_mark_bg_unused(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; spin_lock(&fs_info->unused_bgs_lock); if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); trace_btrfs_add_unused_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->unused_bgs); } else if (!test_bit(BLOCK_GROUP_FLAG_NEW, &bg->runtime_flags)) { /* Pull out the block group from the reclaim_bgs list. */ trace_btrfs_add_unused_block_group(bg); list_move_tail(&bg->bg_list, &fs_info->unused_bgs); } spin_unlock(&fs_info->unused_bgs_lock); } /* * We want block groups with a low number of used bytes to be in the beginning * of the list, so they will get reclaimed first. */ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, const struct list_head *b) { const struct btrfs_block_group *bg1, *bg2; bg1 = list_entry(a, struct btrfs_block_group, bg_list); bg2 = list_entry(b, struct btrfs_block_group, bg_list); return bg1->used > bg2->used; } static inline bool btrfs_should_reclaim(struct btrfs_fs_info *fs_info) { if (btrfs_is_zoned(fs_info)) return btrfs_zoned_should_reclaim(fs_info); return true; } static bool should_reclaim_block_group(struct btrfs_block_group *bg, u64 bytes_freed) { const int thresh_pct = btrfs_calc_reclaim_threshold(bg->space_info); u64 thresh_bytes = mult_perc(bg->length, thresh_pct); const u64 new_val = bg->used; const u64 old_val = new_val + bytes_freed; if (thresh_bytes == 0) return false; /* * If we were below the threshold before don't reclaim, we are likely a * brand new block group and we don't want to relocate new block groups. */ if (old_val < thresh_bytes) return false; if (new_val >= thresh_bytes) return false; return true; } void btrfs_reclaim_bgs_work(struct work_struct *work) { struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, reclaim_bgs_work); struct btrfs_block_group *bg; struct btrfs_space_info *space_info; LIST_HEAD(retry_list); if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; if (btrfs_fs_closing(fs_info)) return; if (!btrfs_should_reclaim(fs_info)) return; sb_start_write(fs_info->sb); if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { sb_end_write(fs_info->sb); return; } /* * Long running balances can keep us blocked here for eternity, so * simply skip reclaim if we're unable to get the mutex. */ if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) { btrfs_exclop_finish(fs_info); sb_end_write(fs_info->sb); return; } spin_lock(&fs_info->unused_bgs_lock); /* * Sort happens under lock because we can't simply splice it and sort. * The block groups might still be in use and reachable via bg_list, * and their presence in the reclaim_bgs list must be preserved. */ list_sort(NULL, &fs_info->reclaim_bgs, reclaim_bgs_cmp); while (!list_empty(&fs_info->reclaim_bgs)) { u64 zone_unusable; u64 reclaimed; int ret = 0; bg = list_first_entry(&fs_info->reclaim_bgs, struct btrfs_block_group, bg_list); list_del_init(&bg->bg_list); space_info = bg->space_info; spin_unlock(&fs_info->unused_bgs_lock); /* Don't race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); spin_lock(&space_info->lock); spin_lock(&bg->lock); if (bg->reserved || bg->pinned || bg->ro) { /* * We want to bail if we made new allocations or have * outstanding allocations in this block group. We do * the ro check in case balance is currently acting on * this block group. */ spin_unlock(&bg->lock); spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } if (bg->used == 0) { /* * It is possible that we trigger relocation on a block * group as its extents are deleted and it first goes * below the threshold, then shortly after goes empty. * * In this case, relocating it does delete it, but has * some overhead in relocation specific metadata, looking * for the non-existent extents and running some extra * transactions, which we can avoid by using one of the * other mechanisms for dealing with empty block groups. */ if (!btrfs_test_opt(fs_info, DISCARD_ASYNC)) btrfs_mark_bg_unused(bg); spin_unlock(&bg->lock); spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } /* * The block group might no longer meet the reclaim condition by * the time we get around to reclaiming it, so to avoid * reclaiming overly full block_groups, skip reclaiming them. * * Since the decision making process also depends on the amount * being freed, pass in a fake giant value to skip that extra * check, which is more meaningful when adding to the list in * the first place. */ if (!should_reclaim_block_group(bg, bg->length)) { spin_unlock(&bg->lock); spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } spin_unlock(&bg->lock); spin_unlock(&space_info->lock); /* * Get out fast, in case we're read-only or unmounting the * filesystem. It is OK to drop block groups from the list even * for the read-only case. As we did sb_start_write(), * "mount -o remount,ro" won't happen and read-only filesystem * means it is forced read-only due to a fatal error. So, it * never gets back to read-write to let us reclaim again. */ if (btrfs_need_cleaner_sleep(fs_info)) { up_write(&space_info->groups_sem); goto next; } /* * Cache the zone_unusable value before turning the block group * to read only. As soon as the blog group is read only it's * zone_unusable value gets moved to the block group's read-only * bytes and isn't available for calculations anymore. */ zone_unusable = bg->zone_unusable; ret = inc_block_group_ro(bg, 0); up_write(&space_info->groups_sem); if (ret < 0) goto next; btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used %llu%% unusable", bg->start, div64_u64(bg->used * 100, bg->length), div64_u64(zone_unusable * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); reclaimed = bg->used; ret = btrfs_relocate_chunk(fs_info, bg->start); if (ret) { btrfs_dec_block_group_ro(bg); btrfs_err(fs_info, "error relocating chunk %llu", bg->start); reclaimed = 0; spin_lock(&space_info->lock); space_info->reclaim_errors++; if (READ_ONCE(space_info->periodic_reclaim)) space_info->periodic_reclaim_ready = false; spin_unlock(&space_info->lock); } spin_lock(&space_info->lock); space_info->reclaim_count++; space_info->reclaim_bytes += reclaimed; spin_unlock(&space_info->lock); next: if (ret && !READ_ONCE(space_info->periodic_reclaim)) { /* Refcount held by the reclaim_bgs list after splice. */ spin_lock(&fs_info->unused_bgs_lock); /* * This block group might be added to the unused list * during the above process. Move it back to the * reclaim list otherwise. */ if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); list_add_tail(&bg->bg_list, &retry_list); } spin_unlock(&fs_info->unused_bgs_lock); } btrfs_put_block_group(bg); mutex_unlock(&fs_info->reclaim_bgs_lock); /* * Reclaiming all the block groups in the list can take really * long. Prioritize cleaning up unused block groups. */ btrfs_delete_unused_bgs(fs_info); /* * If we are interrupted by a balance, we can just bail out. The * cleaner thread restart again if necessary. */ if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) goto end; spin_lock(&fs_info->unused_bgs_lock); } spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); end: spin_lock(&fs_info->unused_bgs_lock); list_splice_tail(&retry_list, &fs_info->reclaim_bgs); spin_unlock(&fs_info->unused_bgs_lock); btrfs_exclop_finish(fs_info); sb_end_write(fs_info->sb); } void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info) { btrfs_reclaim_sweep(fs_info); spin_lock(&fs_info->unused_bgs_lock); if (!list_empty(&fs_info->reclaim_bgs)) queue_work(system_unbound_wq, &fs_info->reclaim_bgs_work); spin_unlock(&fs_info->unused_bgs_lock); } void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; spin_lock(&fs_info->unused_bgs_lock); if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); trace_btrfs_add_reclaim_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->reclaim_bgs); } spin_unlock(&fs_info->unused_bgs_lock); } static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key, struct btrfs_path *path) { struct btrfs_chunk_map *map; struct btrfs_block_group_item bg; struct extent_buffer *leaf; int slot; u64 flags; int ret = 0; slot = path->slots[0]; leaf = path->nodes[0]; map = btrfs_find_chunk_map(fs_info, key->objectid, key->offset); if (!map) { btrfs_err(fs_info, "logical %llu len %llu found bg but no related chunk", key->objectid, key->offset); return -ENOENT; } if (map->start != key->objectid || map->chunk_len != key->offset) { btrfs_err(fs_info, "block group %llu len %llu mismatch with chunk %llu len %llu", key->objectid, key->offset, map->start, map->chunk_len); ret = -EUCLEAN; goto out_free_map; } read_extent_buffer(leaf, &bg, btrfs_item_ptr_offset(leaf, slot), sizeof(bg)); flags = btrfs_stack_block_group_flags(&bg) & BTRFS_BLOCK_GROUP_TYPE_MASK; if (flags != (map->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) { btrfs_err(fs_info, "block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx", key->objectid, key->offset, flags, (BTRFS_BLOCK_GROUP_TYPE_MASK & map->type)); ret = -EUCLEAN; } out_free_map: btrfs_free_chunk_map(map); return ret; } static int find_first_block_group(struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_key *key) { struct btrfs_root *root = btrfs_block_group_root(fs_info); int ret; struct btrfs_key found_key; btrfs_for_each_slot(root, key, &found_key, path, ret) { if (found_key.objectid >= key->objectid && found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) { return read_bg_from_eb(fs_info, &found_key, path); } } return ret; } static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) { u64 extra_flags = chunk_to_extended(flags) & BTRFS_EXTENDED_PROFILE_MASK; write_seqlock(&fs_info->profiles_lock); if (flags & BTRFS_BLOCK_GROUP_DATA) fs_info->avail_data_alloc_bits |= extra_flags; if (flags & BTRFS_BLOCK_GROUP_METADATA) fs_info->avail_metadata_alloc_bits |= extra_flags; if (flags & BTRFS_BLOCK_GROUP_SYSTEM) fs_info->avail_system_alloc_bits |= extra_flags; write_sequnlock(&fs_info->profiles_lock); } /* * Map a physical disk address to a list of logical addresses. * * @fs_info: the filesystem * @chunk_start: logical address of block group * @physical: physical address to map to logical addresses * @logical: return array of logical addresses which map to @physical * @naddrs: length of @logical * @stripe_len: size of IO stripe for the given block group * * Maps a particular @physical disk address to a list of @logical addresses. * Used primarily to exclude those portions of a block group that contain super * block copies. */ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, u64 physical, u64 **logical, int *naddrs, int *stripe_len) { struct btrfs_chunk_map *map; u64 *buf; u64 bytenr; u64 data_stripe_length; u64 io_stripe_size; int i, nr = 0; int ret = 0; map = btrfs_get_chunk_map(fs_info, chunk_start, 1); if (IS_ERR(map)) return -EIO; data_stripe_length = map->stripe_size; io_stripe_size = BTRFS_STRIPE_LEN; chunk_start = map->start; /* For RAID5/6 adjust to a full IO stripe length */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) io_stripe_size = btrfs_stripe_nr_to_offset(nr_data_stripes(map)); buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS); if (!buf) { ret = -ENOMEM; goto out; } for (i = 0; i < map->num_stripes; i++) { bool already_inserted = false; u32 stripe_nr; u32 offset; int j; if (!in_range(physical, map->stripes[i].physical, data_stripe_length)) continue; stripe_nr = (physical - map->stripes[i].physical) >> BTRFS_STRIPE_LEN_SHIFT; offset = (physical - map->stripes[i].physical) & BTRFS_STRIPE_LEN_MASK; if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) stripe_nr = div_u64(stripe_nr * map->num_stripes + i, map->sub_stripes); /* * The remaining case would be for RAID56, multiply by * nr_data_stripes(). Alternatively, just use rmap_len below * instead of map->stripe_len */ bytenr = chunk_start + stripe_nr * io_stripe_size + offset; /* Ensure we don't add duplicate addresses */ for (j = 0; j < nr; j++) { if (buf[j] == bytenr) { already_inserted = true; break; } } if (!already_inserted) buf[nr++] = bytenr; } *logical = buf; *naddrs = nr; *stripe_len = io_stripe_size; out: btrfs_free_chunk_map(map); return ret; } static int exclude_super_stripes(struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; const bool zoned = btrfs_is_zoned(fs_info); u64 bytenr; u64 *logical; int stripe_len; int i, nr, ret; if (cache->start < BTRFS_SUPER_INFO_OFFSET) { stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->start; cache->bytes_super += stripe_len; ret = set_extent_bit(&fs_info->excluded_extents, cache->start, cache->start + stripe_len - 1, EXTENT_UPTODATE, NULL); if (ret) return ret; } for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { bytenr = btrfs_sb_offset(i); ret = btrfs_rmap_block(fs_info, cache->start, bytenr, &logical, &nr, &stripe_len); if (ret) return ret; /* Shouldn't have super stripes in sequential zones */ if (zoned && nr) { kfree(logical); btrfs_err(fs_info, "zoned: block group %llu must not contain super block", cache->start); return -EUCLEAN; } while (nr--) { u64 len = min_t(u64, stripe_len, cache->start + cache->length - logical[nr]); cache->bytes_super += len; ret = set_extent_bit(&fs_info->excluded_extents, logical[nr], logical[nr] + len - 1, EXTENT_UPTODATE, NULL); if (ret) { kfree(logical); return ret; } } kfree(logical); } return 0; } static struct btrfs_block_group *btrfs_create_block_group_cache( struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = kzalloc(sizeof(*cache), GFP_NOFS); if (!cache) return NULL; cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl), GFP_NOFS); if (!cache->free_space_ctl) { kfree(cache); return NULL; } cache->start = start; cache->fs_info = fs_info; cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start); cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED; refcount_set(&cache->refs, 1); spin_lock_init(&cache->lock); init_rwsem(&cache->data_rwsem); INIT_LIST_HEAD(&cache->list); INIT_LIST_HEAD(&cache->cluster_list); INIT_LIST_HEAD(&cache->bg_list); INIT_LIST_HEAD(&cache->ro_list); INIT_LIST_HEAD(&cache->discard_list); INIT_LIST_HEAD(&cache->dirty_list); INIT_LIST_HEAD(&cache->io_list); INIT_LIST_HEAD(&cache->active_bg_list); btrfs_init_free_space_ctl(cache, cache->free_space_ctl); atomic_set(&cache->frozen, 0); mutex_init(&cache->free_space_lock); return cache; } /* * Iterate all chunks and verify that each of them has the corresponding block * group */ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) { u64 start = 0; int ret = 0; while (1) { struct btrfs_chunk_map *map; struct btrfs_block_group *bg; /* * btrfs_find_chunk_map() will return the first chunk map * intersecting the range, so setting @length to 1 is enough to * get the first chunk. */ map = btrfs_find_chunk_map(fs_info, start, 1); if (!map) break; bg = btrfs_lookup_block_group(fs_info, map->start); if (!bg) { btrfs_err(fs_info, "chunk start=%llu len=%llu doesn't have corresponding block group", map->start, map->chunk_len); ret = -EUCLEAN; btrfs_free_chunk_map(map); break; } if (bg->start != map->start || bg->length != map->chunk_len || (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) != (map->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) { btrfs_err(fs_info, "chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx", map->start, map->chunk_len, map->type & BTRFS_BLOCK_GROUP_TYPE_MASK, bg->start, bg->length, bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK); ret = -EUCLEAN; btrfs_free_chunk_map(map); btrfs_put_block_group(bg); break; } start = map->start + map->chunk_len; btrfs_free_chunk_map(map); btrfs_put_block_group(bg); } return ret; } static int read_one_block_group(struct btrfs_fs_info *info, struct btrfs_block_group_item *bgi, const struct btrfs_key *key, int need_clear) { struct btrfs_block_group *cache; const bool mixed = btrfs_fs_incompat(info, MIXED_GROUPS); int ret; ASSERT(key->type == BTRFS_BLOCK_GROUP_ITEM_KEY); cache = btrfs_create_block_group_cache(info, key->objectid); if (!cache) return -ENOMEM; cache->length = key->offset; cache->used = btrfs_stack_block_group_used(bgi); cache->commit_used = cache->used; cache->flags = btrfs_stack_block_group_flags(bgi); cache->global_root_id = btrfs_stack_block_group_chunk_objectid(bgi); set_free_space_tree_thresholds(cache); if (need_clear) { /* * When we mount with old space cache, we need to * set BTRFS_DC_CLEAR and set dirty flag. * * a) Setting 'BTRFS_DC_CLEAR' makes sure that we * truncate the old free space cache inode and * setup a new one. * b) Setting 'dirty flag' makes sure that we flush * the new space cache info onto disk. */ if (btrfs_test_opt(info, SPACE_CACHE)) cache->disk_cache_state = BTRFS_DC_CLEAR; } if (!mixed && ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) && (cache->flags & BTRFS_BLOCK_GROUP_DATA))) { btrfs_err(info, "bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", cache->start); ret = -EINVAL; goto error; } ret = btrfs_load_block_group_zone_info(cache, false); if (ret) { btrfs_err(info, "zoned: failed to load zone info of bg %llu", cache->start); goto error; } /* * We need to exclude the super stripes now so that the space info has * super bytes accounted for, otherwise we'll think we have more space * than we actually do. */ ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case. */ btrfs_free_excluded_extents(cache); goto error; } /* * For zoned filesystem, space after the allocation offset is the only * free space for a block group. So, we don't need any caching work. * btrfs_calc_zone_unusable() will set the amount of free space and * zone_unusable space. * * For regular filesystem, check for two cases, either we are full, and * therefore don't need to bother with the caching work since we won't * find any space, or we are empty, and we can just add all the space * in and be done with it. This saves us _a_lot_ of time, particularly * in the full case. */ if (btrfs_is_zoned(info)) { btrfs_calc_zone_unusable(cache); /* Should not have any excluded extents. Just in case, though. */ btrfs_free_excluded_extents(cache); } else if (cache->length == cache->used) { cache->cached = BTRFS_CACHE_FINISHED; btrfs_free_excluded_extents(cache); } else if (cache->used == 0) { cache->cached = BTRFS_CACHE_FINISHED; ret = btrfs_add_new_free_space(cache, cache->start, cache->start + cache->length, NULL); btrfs_free_excluded_extents(cache); if (ret) goto error; } ret = btrfs_add_block_group_cache(info, cache); if (ret) { btrfs_remove_free_space_cache(cache); goto error; } trace_btrfs_add_block_group(info, cache, 0); btrfs_add_bg_to_space_info(info, cache); set_avail_alloc_bits(info, cache->flags); if (btrfs_chunk_writeable(info, cache->start)) { if (cache->used == 0) { ASSERT(list_empty(&cache->bg_list)); if (btrfs_test_opt(info, DISCARD_ASYNC)) btrfs_discard_queue_work(&info->discard_ctl, cache); else btrfs_mark_bg_unused(cache); } } else { inc_block_group_ro(cache, 1); } return 0; error: btrfs_put_block_group(cache); return ret; } static int fill_dummy_bgs(struct btrfs_fs_info *fs_info) { struct rb_node *node; int ret = 0; for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) { struct btrfs_chunk_map *map; struct btrfs_block_group *bg; map = rb_entry(node, struct btrfs_chunk_map, rb_node); bg = btrfs_create_block_group_cache(fs_info, map->start); if (!bg) { ret = -ENOMEM; break; } /* Fill dummy cache as FULL */ bg->length = map->chunk_len; bg->flags = map->type; bg->cached = BTRFS_CACHE_FINISHED; bg->used = map->chunk_len; bg->flags = map->type; ret = btrfs_add_block_group_cache(fs_info, bg); /* * We may have some valid block group cache added already, in * that case we skip to the next one. */ if (ret == -EEXIST) { ret = 0; btrfs_put_block_group(bg); continue; } if (ret) { btrfs_remove_free_space_cache(bg); btrfs_put_block_group(bg); break; } btrfs_add_bg_to_space_info(fs_info, bg); set_avail_alloc_bits(fs_info, bg->flags); } if (!ret) btrfs_init_global_block_rsv(fs_info); return ret; } int btrfs_read_block_groups(struct btrfs_fs_info *info) { struct btrfs_root *root = btrfs_block_group_root(info); struct btrfs_path *path; int ret; struct btrfs_block_group *cache; struct btrfs_space_info *space_info; struct btrfs_key key; int need_clear = 0; u64 cache_gen; /* * Either no extent root (with ibadroots rescue option) or we have * unsupported RO options. The fs can never be mounted read-write, so no * need to waste time searching block group items. * * This also allows new extent tree related changes to be RO compat, * no need for a full incompat flag. */ if (!root || (btrfs_super_compat_ro_flags(info->super_copy) & ~BTRFS_FEATURE_COMPAT_RO_SUPP)) return fill_dummy_bgs(info); key.objectid = 0; key.offset = 0; key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; path = btrfs_alloc_path(); if (!path) return -ENOMEM; cache_gen = btrfs_super_cache_generation(info->super_copy); if (btrfs_test_opt(info, SPACE_CACHE) && btrfs_super_generation(info->super_copy) != cache_gen) need_clear = 1; if (btrfs_test_opt(info, CLEAR_CACHE)) need_clear = 1; while (1) { struct btrfs_block_group_item bgi; struct extent_buffer *leaf; int slot; ret = find_first_block_group(info, path, &key); if (ret > 0) break; if (ret != 0) goto error; leaf = path->nodes[0]; slot = path->slots[0]; read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), sizeof(bgi)); btrfs_item_key_to_cpu(leaf, &key, slot); btrfs_release_path(path); ret = read_one_block_group(info, &bgi, &key, need_clear); if (ret < 0) goto error; key.objectid += key.offset; key.offset = 0; } btrfs_release_path(path); list_for_each_entry(space_info, &info->space_info, list) { int i; for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { if (list_empty(&space_info->block_groups[i])) continue; cache = list_first_entry(&space_info->block_groups[i], struct btrfs_block_group, list); btrfs_sysfs_add_block_group_type(cache); } if (!(btrfs_get_alloc_profile(info, space_info->flags) & (BTRFS_BLOCK_GROUP_RAID10 | BTRFS_BLOCK_GROUP_RAID1_MASK | BTRFS_BLOCK_GROUP_RAID56_MASK | BTRFS_BLOCK_GROUP_DUP))) continue; /* * Avoid allocating from un-mirrored block group if there are * mirrored block groups. */ list_for_each_entry(cache, &space_info->block_groups[BTRFS_RAID_RAID0], list) inc_block_group_ro(cache, 1); list_for_each_entry(cache, &space_info->block_groups[BTRFS_RAID_SINGLE], list) inc_block_group_ro(cache, 1); } btrfs_init_global_block_rsv(info); ret = check_chunk_block_group_mappings(info); error: btrfs_free_path(path); /* * We've hit some error while reading the extent tree, and have * rescue=ibadroots mount option. * Try to fill the tree using dummy block groups so that the user can * continue to mount and grab their data. */ if (ret && btrfs_test_opt(info, IGNOREBADROOTS)) ret = fill_dummy_bgs(info); return ret; } /* * This function, insert_block_group_item(), belongs to the phase 2 of chunk * allocation. * * See the comment at btrfs_chunk_alloc() for details about the chunk allocation * phases. */ static int insert_block_group_item(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group_item bgi; struct btrfs_root *root = btrfs_block_group_root(fs_info); struct btrfs_key key; u64 old_commit_used; int ret; spin_lock(&block_group->lock); btrfs_set_stack_block_group_used(&bgi, block_group->used); btrfs_set_stack_block_group_chunk_objectid(&bgi, block_group->global_root_id); btrfs_set_stack_block_group_flags(&bgi, block_group->flags); old_commit_used = block_group->commit_used; block_group->commit_used = block_group->used; key.objectid = block_group->start; key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; key.offset = block_group->length; spin_unlock(&block_group->lock); ret = btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi)); if (ret < 0) { spin_lock(&block_group->lock); block_group->commit_used = old_commit_used; spin_unlock(&block_group->lock); } return ret; } static int insert_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 chunk_offset, u64 start, u64 num_bytes) { struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_root *root = fs_info->dev_root; struct btrfs_path *path; struct btrfs_dev_extent *extent; struct extent_buffer *leaf; struct btrfs_key key; int ret; WARN_ON(!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state)); WARN_ON(test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)); path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = device->devid; key.type = BTRFS_DEV_EXTENT_KEY; key.offset = start; ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*extent)); if (ret) goto out; leaf = path->nodes[0]; extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); btrfs_set_dev_extent_chunk_tree(leaf, extent, BTRFS_CHUNK_TREE_OBJECTID); btrfs_set_dev_extent_chunk_objectid(leaf, extent, BTRFS_FIRST_CHUNK_TREE_OBJECTID); btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset); btrfs_set_dev_extent_length(leaf, extent, num_bytes); btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; } /* * This function belongs to phase 2. * * See the comment at btrfs_chunk_alloc() for details about the chunk allocation * phases. */ static int insert_dev_extents(struct btrfs_trans_handle *trans, u64 chunk_offset, u64 chunk_size) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_device *device; struct btrfs_chunk_map *map; u64 dev_offset; int i; int ret = 0; map = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size); if (IS_ERR(map)) return PTR_ERR(map); /* * Take the device list mutex to prevent races with the final phase of * a device replace operation that replaces the device object associated * with the map's stripes, because the device object's id can change * at any time during that final phase of the device replace operation * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID, * resulting in persisting a device extent item with such ID. */ mutex_lock(&fs_info->fs_devices->device_list_mutex); for (i = 0; i < map->num_stripes; i++) { device = map->stripes[i].dev; dev_offset = map->stripes[i].physical; ret = insert_dev_extent(trans, device, chunk_offset, dev_offset, map->stripe_size); if (ret) break; } mutex_unlock(&fs_info->fs_devices->device_list_mutex); btrfs_free_chunk_map(map); return ret; } /* * This function, btrfs_create_pending_block_groups(), belongs to the phase 2 of * chunk allocation. * * See the comment at btrfs_chunk_alloc() for details about the chunk allocation * phases. */ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *block_group; int ret = 0; while (!list_empty(&trans->new_bgs)) { int index; block_group = list_first_entry(&trans->new_bgs, struct btrfs_block_group, bg_list); if (ret) goto next; index = btrfs_bg_flags_to_raid_index(block_group->flags); ret = insert_block_group_item(trans, block_group); if (ret) btrfs_abort_transaction(trans, ret); if (!test_bit(BLOCK_GROUP_FLAG_CHUNK_ITEM_INSERTED, &block_group->runtime_flags)) { mutex_lock(&fs_info->chunk_mutex); ret = btrfs_chunk_alloc_add_chunk_item(trans, block_group); mutex_unlock(&fs_info->chunk_mutex); if (ret) btrfs_abort_transaction(trans, ret); } ret = insert_dev_extents(trans, block_group->start, block_group->length); if (ret) btrfs_abort_transaction(trans, ret); add_block_group_free_space(trans, block_group); /* * If we restriped during balance, we may have added a new raid * type, so now add the sysfs entries when it is safe to do so. * We don't have to worry about locking here as it's handled in * btrfs_sysfs_add_block_group_type. */ if (block_group->space_info->block_group_kobjs[index] == NULL) btrfs_sysfs_add_block_group_type(block_group); /* Already aborted the transaction if it failed. */ next: btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info); list_del_init(&block_group->bg_list); clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags); /* * If the block group is still unused, add it to the list of * unused block groups. The block group may have been created in * order to satisfy a space reservation, in which case the * extent allocation only happens later. But often we don't * actually need to allocate space that we previously reserved, * so the block group may become unused for a long time. For * example for metadata we generally reserve space for a worst * possible scenario, but then don't end up allocating all that * space or none at all (due to no need to COW, extent buffers * were already COWed in the current transaction and still * unwritten, tree heights lower than the maximum possible * height, etc). For data we generally reserve the axact amount * of space we are going to allocate later, the exception is * when using compression, as we must reserve space based on the * uncompressed data size, because the compression is only done * when writeback triggered and we don't know how much space we * are actually going to need, so we reserve the uncompressed * size because the data may be uncompressible in the worst case. */ if (ret == 0) { bool used; spin_lock(&block_group->lock); used = btrfs_is_block_group_used(block_group); spin_unlock(&block_group->lock); if (!used) btrfs_mark_bg_unused(block_group); } } btrfs_trans_release_chunk_metadata(trans); } /* * For extent tree v2 we use the block_group_item->chunk_offset to point at our * global root id. For v1 it's always set to BTRFS_FIRST_CHUNK_TREE_OBJECTID. */ static u64 calculate_global_root_id(struct btrfs_fs_info *fs_info, u64 offset) { u64 div = SZ_1G; u64 index; if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) return BTRFS_FIRST_CHUNK_TREE_OBJECTID; /* If we have a smaller fs index based on 128MiB. */ if (btrfs_super_total_bytes(fs_info->super_copy) <= (SZ_1G * 10ULL)) div = SZ_128M; offset = div64_u64(offset, div); div64_u64_rem(offset, fs_info->nr_global_roots, &index); return index; } struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 type, u64 chunk_offset, u64 size) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *cache; int ret; btrfs_set_log_full_commit(trans); cache = btrfs_create_block_group_cache(fs_info, chunk_offset); if (!cache) return ERR_PTR(-ENOMEM); /* * Mark it as new before adding it to the rbtree of block groups or any * list, so that no other task finds it and calls btrfs_mark_bg_unused() * before the new flag is set. */ set_bit(BLOCK_GROUP_FLAG_NEW, &cache->runtime_flags); cache->length = size; set_free_space_tree_thresholds(cache); cache->flags = type; cache->cached = BTRFS_CACHE_FINISHED; cache->global_root_id = calculate_global_root_id(fs_info, cache->start); if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) set_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &cache->runtime_flags); ret = btrfs_load_block_group_zone_info(cache, true); if (ret) { btrfs_put_block_group(cache); return ERR_PTR(ret); } ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ btrfs_free_excluded_extents(cache); btrfs_put_block_group(cache); return ERR_PTR(ret); } ret = btrfs_add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL); btrfs_free_excluded_extents(cache); if (ret) { btrfs_put_block_group(cache); return ERR_PTR(ret); } /* * Ensure the corresponding space_info object is created and * assigned to our block group. We want our bg to be added to the rbtree * with its ->space_info set. */ cache->space_info = btrfs_find_space_info(fs_info, cache->flags); ASSERT(cache->space_info); ret = btrfs_add_block_group_cache(fs_info, cache); if (ret) { btrfs_remove_free_space_cache(cache); btrfs_put_block_group(cache); return ERR_PTR(ret); } /* * Now that our block group has its ->space_info set and is inserted in * the rbtree, update the space info's counters. */ trace_btrfs_add_block_group(fs_info, cache, 1); btrfs_add_bg_to_space_info(fs_info, cache); btrfs_update_global_block_rsv(fs_info); #ifdef CONFIG_BTRFS_DEBUG if (btrfs_should_fragment_free_space(cache)) { cache->space_info->bytes_used += size >> 1; fragment_free_space(cache); } #endif list_add_tail(&cache->bg_list, &trans->new_bgs); btrfs_inc_delayed_refs_rsv_bg_inserts(fs_info); set_avail_alloc_bits(fs_info, type); return cache; } /* * Mark one block group RO, can be called several times for the same block * group. * * @cache: the destination block group * @do_chunk_alloc: whether need to do chunk pre-allocation, this is to * ensure we still have some free space after marking this * block group RO. */ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, bool do_chunk_alloc) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_trans_handle *trans; struct btrfs_root *root = btrfs_block_group_root(fs_info); u64 alloc_flags; int ret; bool dirty_bg_running; /* * This can only happen when we are doing read-only scrub on read-only * mount. * In that case we should not start a new transaction on read-only fs. * Thus here we skip all chunk allocations. */ if (sb_rdonly(fs_info->sb)) { mutex_lock(&fs_info->ro_block_group_mutex); ret = inc_block_group_ro(cache, 0); mutex_unlock(&fs_info->ro_block_group_mutex); return ret; } do { trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); dirty_bg_running = false; /* * We're not allowed to set block groups readonly after the dirty * block group cache has started writing. If it already started, * back off and let this transaction commit. */ mutex_lock(&fs_info->ro_block_group_mutex); if (test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &trans->transaction->flags)) { u64 transid = trans->transid; mutex_unlock(&fs_info->ro_block_group_mutex); btrfs_end_transaction(trans); ret = btrfs_wait_for_commit(fs_info, transid); if (ret) return ret; dirty_bg_running = true; } } while (dirty_bg_running); if (do_chunk_alloc) { /* * If we are changing raid levels, try to allocate a * corresponding block group with the new raid level. */ alloc_flags = btrfs_get_alloc_profile(fs_info, cache->flags); if (alloc_flags != cache->flags) { ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); /* * ENOSPC is allowed here, we may have enough space * already allocated at the new raid level to carry on */ if (ret == -ENOSPC) ret = 0; if (ret < 0) goto out; } } ret = inc_block_group_ro(cache, 0); if (!ret) goto out; if (ret == -ETXTBSY) goto unlock_out; /* * Skip chunk allocation if the bg is SYSTEM, this is to avoid system * chunk allocation storm to exhaust the system chunk array. Otherwise * we still want to try our best to mark the block group read-only. */ if (!do_chunk_alloc && ret == -ENOSPC && (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM)) goto unlock_out; alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); if (ret < 0) goto out; /* * We have allocated a new chunk. We also need to activate that chunk to * grant metadata tickets for zoned filesystem. */ ret = btrfs_zoned_activate_one_bg(fs_info, cache->space_info, true); if (ret < 0) goto out; ret = inc_block_group_ro(cache, 0); if (ret == -ETXTBSY) goto unlock_out; out: if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) { alloc_flags = btrfs_get_alloc_profile(fs_info, cache->flags); mutex_lock(&fs_info->chunk_mutex); check_system_chunk(trans, alloc_flags); mutex_unlock(&fs_info->chunk_mutex); } unlock_out: mutex_unlock(&fs_info->ro_block_group_mutex); btrfs_end_transaction(trans); return ret; } void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) { struct btrfs_space_info *sinfo = cache->space_info; u64 num_bytes; BUG_ON(!cache->ro); spin_lock(&sinfo->lock); spin_lock(&cache->lock); if (!--cache->ro) { if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = (cache->alloc_offset - cache->used - cache->pinned - cache->reserved) + (cache->length - cache->zone_capacity); btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, cache->zone_unusable); sinfo->bytes_readonly -= cache->zone_unusable; } num_bytes = cache->length - cache->reserved - cache->pinned - cache->bytes_super - cache->zone_unusable - cache->used; sinfo->bytes_readonly -= num_bytes; list_del_init(&cache->ro_list); } spin_unlock(&cache->lock); spin_unlock(&sinfo->lock); } static int update_block_group_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; struct btrfs_root *root = btrfs_block_group_root(fs_info); unsigned long bi; struct extent_buffer *leaf; struct btrfs_block_group_item bgi; struct btrfs_key key; u64 old_commit_used; u64 used; /* * Block group items update can be triggered out of commit transaction * critical section, thus we need a consistent view of used bytes. * We cannot use cache->used directly outside of the spin lock, as it * may be changed. */ spin_lock(&cache->lock); old_commit_used = cache->commit_used; used = cache->used; /* No change in used bytes, can safely skip it. */ if (cache->commit_used == used) { spin_unlock(&cache->lock); return 0; } cache->commit_used = used; spin_unlock(&cache->lock); key.objectid = cache->start; key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; key.offset = cache->length; ret = btrfs_search_slot(trans, root, &key, path, 0, 1); if (ret) { if (ret > 0) ret = -ENOENT; goto fail; } leaf = path->nodes[0]; bi = btrfs_item_ptr_offset(leaf, path->slots[0]); btrfs_set_stack_block_group_used(&bgi, used); btrfs_set_stack_block_group_chunk_objectid(&bgi, cache->global_root_id); btrfs_set_stack_block_group_flags(&bgi, cache->flags); write_extent_buffer(leaf, &bgi, bi, sizeof(bgi)); btrfs_mark_buffer_dirty(trans, leaf); fail: btrfs_release_path(path); /* * We didn't update the block group item, need to revert commit_used * unless the block group item didn't exist yet - this is to prevent a * race with a concurrent insertion of the block group item, with * insert_block_group_item(), that happened just after we attempted to * update. In that case we would reset commit_used to 0 just after the * insertion set it to a value greater than 0 - if the block group later * becomes with 0 used bytes, we would incorrectly skip its update. */ if (ret < 0 && ret != -ENOENT) { spin_lock(&cache->lock); cache->commit_used = old_commit_used; spin_unlock(&cache->lock); } return ret; } static int cache_save_setup(struct btrfs_block_group *block_group, struct btrfs_trans_handle *trans, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct inode *inode = NULL; struct extent_changeset *data_reserved = NULL; u64 alloc_hint = 0; int dcs = BTRFS_DC_ERROR; u64 cache_size = 0; int retries = 0; int ret = 0; if (!btrfs_test_opt(fs_info, SPACE_CACHE)) return 0; /* * If this block group is smaller than 100 megs don't bother caching the * block group. */ if (block_group->length < (100 * SZ_1M)) { spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_WRITTEN; spin_unlock(&block_group->lock); return 0; } if (TRANS_ABORTED(trans)) return 0; again: inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) { ret = PTR_ERR(inode); btrfs_release_path(path); goto out; } if (IS_ERR(inode)) { BUG_ON(retries); retries++; if (block_group->ro) goto out_free; ret = create_free_space_inode(trans, block_group, path); if (ret) goto out_free; goto again; } /* * We want to set the generation to 0, that way if anything goes wrong * from here on out we know not to trust this cache when we load up next * time. */ BTRFS_I(inode)->generation = 0; ret = btrfs_update_inode(trans, BTRFS_I(inode)); if (ret) { /* * So theoretically we could recover from this, simply set the * super cache generation to 0 so we know to invalidate the * cache, but then we'd have to keep track of the block groups * that fail this way so we know we _have_ to reset this cache * before the next commit or risk reading stale cache. So to * limit our exposure to horrible edge cases lets just abort the * transaction, this only happens in really bad situations * anyway. */ btrfs_abort_transaction(trans, ret); goto out_put; } WARN_ON(ret); /* We've already setup this transaction, go ahead and exit */ if (block_group->cache_generation == trans->transid && i_size_read(inode)) { dcs = BTRFS_DC_SETUP; goto out_put; } if (i_size_read(inode) > 0) { ret = btrfs_check_trunc_cache_free_space(fs_info, &fs_info->global_block_rsv); if (ret) goto out_put; ret = btrfs_truncate_free_space_cache(trans, NULL, inode); if (ret) goto out_put; } spin_lock(&block_group->lock); if (block_group->cached != BTRFS_CACHE_FINISHED || !btrfs_test_opt(fs_info, SPACE_CACHE)) { /* * don't bother trying to write stuff out _if_ * a) we're not cached, * b) we're with nospace_cache mount option, * c) we're with v2 space_cache (FREE_SPACE_TREE). */ dcs = BTRFS_DC_WRITTEN; spin_unlock(&block_group->lock); goto out_put; } spin_unlock(&block_group->lock); /* * We hit an ENOSPC when setting up the cache in this transaction, just * skip doing the setup, we've already cleared the cache so we're safe. */ if (test_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags)) { ret = -ENOSPC; goto out_put; } /* * Try to preallocate enough space based on how big the block group is. * Keep in mind this has to include any pinned space which could end up * taking up quite a bit since it's not folded into the other space * cache. */ cache_size = div_u64(block_group->length, SZ_256M); if (!cache_size) cache_size = 1; cache_size *= 16; cache_size *= fs_info->sectorsize; ret = btrfs_check_data_free_space(BTRFS_I(inode), &data_reserved, 0, cache_size, false); if (ret) goto out_put; ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, cache_size, cache_size, cache_size, &alloc_hint); /* * Our cache requires contiguous chunks so that we don't modify a bunch * of metadata or split extents when writing the cache out, which means * we can enospc if we are heavily fragmented in addition to just normal * out of space conditions. So if we hit this just skip setting up any * other block groups for this transaction, maybe we'll unpin enough * space the next time around. */ if (!ret) dcs = BTRFS_DC_SETUP; else if (ret == -ENOSPC) set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags); out_put: iput(inode); out_free: btrfs_release_path(path); out: spin_lock(&block_group->lock); if (!ret && dcs == BTRFS_DC_SETUP) block_group->cache_generation = trans->transid; block_group->disk_cache_state = dcs; spin_unlock(&block_group->lock); extent_changeset_free(data_reserved); return ret; } int btrfs_setup_space_cache(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *cache, *tmp; struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_path *path; if (list_empty(&cur_trans->dirty_bgs) || !btrfs_test_opt(fs_info, SPACE_CACHE)) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* Could add new block groups, use _safe just in case */ list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs, dirty_list) { if (cache->disk_cache_state == BTRFS_DC_CLEAR) cache_save_setup(cache, trans, path); } btrfs_free_path(path); return 0; } /* * Transaction commit does final block group cache writeback during a critical * section where nothing is allowed to change the FS. This is required in * order for the cache to actually match the block group, but can introduce a * lot of latency into the commit. * * So, btrfs_start_dirty_block_groups is here to kick off block group cache IO. * There's a chance we'll have to redo some of it if the block group changes * again during the commit, but it greatly reduces the commit latency by * getting rid of the easy block groups while we're still allowing others to * join the commit. */ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *cache; struct btrfs_transaction *cur_trans = trans->transaction; int ret = 0; int should_put; struct btrfs_path *path = NULL; LIST_HEAD(dirty); struct list_head *io = &cur_trans->io_bgs; int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); if (list_empty(&cur_trans->dirty_bgs)) { spin_unlock(&cur_trans->dirty_bgs_lock); return 0; } list_splice_init(&cur_trans->dirty_bgs, &dirty); spin_unlock(&cur_trans->dirty_bgs_lock); again: /* Make sure all the block groups on our dirty list actually exist */ btrfs_create_pending_block_groups(trans); if (!path) { path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } } /* * cache_write_mutex is here only to save us from balance or automatic * removal of empty block groups deleting this block group while we are * writing out the cache */ mutex_lock(&trans->transaction->cache_write_mutex); while (!list_empty(&dirty)) { bool drop_reserve = true; cache = list_first_entry(&dirty, struct btrfs_block_group, dirty_list); /* * This can happen if something re-dirties a block group that * is already under IO. Just wait for it to finish and then do * it all again */ if (!list_empty(&cache->io_list)) { list_del_init(&cache->io_list); btrfs_wait_cache_io(trans, cache, path); btrfs_put_block_group(cache); } /* * btrfs_wait_cache_io uses the cache->dirty_list to decide if * it should update the cache_state. Don't delete until after * we wait. * * Since we're not running in the commit critical section * we need the dirty_bgs_lock to protect from update_block_group */ spin_lock(&cur_trans->dirty_bgs_lock); list_del_init(&cache->dirty_list); spin_unlock(&cur_trans->dirty_bgs_lock); should_put = 1; cache_save_setup(cache, trans, path); if (cache->disk_cache_state == BTRFS_DC_SETUP) { cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { should_put = 0; /* * The cache_write_mutex is protecting the * io_list, also refer to the definition of * btrfs_transaction::io_bgs for more details */ list_add_tail(&cache->io_list, io); } else { /* * If we failed to write the cache, the * generation will be bad and life goes on */ ret = 0; } } if (!ret) { ret = update_block_group_item(trans, path, cache); /* * Our block group might still be attached to the list * of new block groups in the transaction handle of some * other task (struct btrfs_trans_handle->new_bgs). This * means its block group item isn't yet in the extent * tree. If this happens ignore the error, as we will * try again later in the critical section of the * transaction commit. */ if (ret == -ENOENT) { ret = 0; spin_lock(&cur_trans->dirty_bgs_lock); if (list_empty(&cache->dirty_list)) { list_add_tail(&cache->dirty_list, &cur_trans->dirty_bgs); btrfs_get_block_group(cache); drop_reserve = false; } spin_unlock(&cur_trans->dirty_bgs_lock); } else if (ret) { btrfs_abort_transaction(trans, ret); } } /* If it's not on the io list, we need to put the block group */ if (should_put) btrfs_put_block_group(cache); if (drop_reserve) btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); /* * Avoid blocking other tasks for too long. It might even save * us from writing caches for block groups that are going to be * removed. */ mutex_unlock(&trans->transaction->cache_write_mutex); if (ret) goto out; mutex_lock(&trans->transaction->cache_write_mutex); } mutex_unlock(&trans->transaction->cache_write_mutex); /* * Go through delayed refs for all the stuff we've just kicked off * and then loop back (just once) */ if (!ret) ret = btrfs_run_delayed_refs(trans, 0); if (!ret && loops == 0) { loops++; spin_lock(&cur_trans->dirty_bgs_lock); list_splice_init(&cur_trans->dirty_bgs, &dirty); /* * dirty_bgs_lock protects us from concurrent block group * deletes too (not just cache_write_mutex). */ if (!list_empty(&dirty)) { spin_unlock(&cur_trans->dirty_bgs_lock); goto again; } spin_unlock(&cur_trans->dirty_bgs_lock); } out: if (ret < 0) { spin_lock(&cur_trans->dirty_bgs_lock); list_splice_init(&dirty, &cur_trans->dirty_bgs); spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_cleanup_dirty_bgs(cur_trans, fs_info); } btrfs_free_path(path); return ret; } int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *cache; struct btrfs_transaction *cur_trans = trans->transaction; int ret = 0; int should_put; struct btrfs_path *path; struct list_head *io = &cur_trans->io_bgs; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* * Even though we are in the critical section of the transaction commit, * we can still have concurrent tasks adding elements to this * transaction's list of dirty block groups. These tasks correspond to * endio free space workers started when writeback finishes for a * space cache, which run inode.c:btrfs_finish_ordered_io(), and can * allocate new block groups as a result of COWing nodes of the root * tree when updating the free space inode. The writeback for the space * caches is triggered by an earlier call to * btrfs_start_dirty_block_groups() and iterations of the following * loop. * Also we want to do the cache_save_setup first and then run the * delayed refs to make sure we have the best chance at doing this all * in one shot. */ spin_lock(&cur_trans->dirty_bgs_lock); while (!list_empty(&cur_trans->dirty_bgs)) { cache = list_first_entry(&cur_trans->dirty_bgs, struct btrfs_block_group, dirty_list); /* * This can happen if cache_save_setup re-dirties a block group * that is already under IO. Just wait for it to finish and * then do it all again */ if (!list_empty(&cache->io_list)) { spin_unlock(&cur_trans->dirty_bgs_lock); list_del_init(&cache->io_list); btrfs_wait_cache_io(trans, cache, path); btrfs_put_block_group(cache); spin_lock(&cur_trans->dirty_bgs_lock); } /* * Don't remove from the dirty list until after we've waited on * any pending IO */ list_del_init(&cache->dirty_list); spin_unlock(&cur_trans->dirty_bgs_lock); should_put = 1; cache_save_setup(cache, trans, path); if (!ret) ret = btrfs_run_delayed_refs(trans, U64_MAX); if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP) { cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { should_put = 0; list_add_tail(&cache->io_list, io); } else { /* * If we failed to write the cache, the * generation will be bad and life goes on */ ret = 0; } } if (!ret) { ret = update_block_group_item(trans, path, cache); /* * One of the free space endio workers might have * created a new block group while updating a free space * cache's inode (at inode.c:btrfs_finish_ordered_io()) * and hasn't released its transaction handle yet, in * which case the new block group is still attached to * its transaction handle and its creation has not * finished yet (no block group item in the extent tree * yet, etc). If this is the case, wait for all free * space endio workers to finish and retry. This is a * very rare case so no need for a more efficient and * complex approach. */ if (ret == -ENOENT) { wait_event(cur_trans->writer_wait, atomic_read(&cur_trans->num_writers) == 1); ret = update_block_group_item(trans, path, cache); } if (ret) btrfs_abort_transaction(trans, ret); } /* If its not on the io list, we need to put the block group */ if (should_put) btrfs_put_block_group(cache); btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); spin_lock(&cur_trans->dirty_bgs_lock); } spin_unlock(&cur_trans->dirty_bgs_lock); /* * Refer to the definition of io_bgs member for details why it's safe * to use it without any locking */ while (!list_empty(io)) { cache = list_first_entry(io, struct btrfs_block_group, io_list); list_del_init(&cache->io_list); btrfs_wait_cache_io(trans, cache, path); btrfs_put_block_group(cache); } btrfs_free_path(path); return ret; } int btrfs_update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, bool alloc) { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_space_info *space_info; struct btrfs_block_group *cache; u64 old_val; bool reclaim = false; bool bg_already_dirty = true; int factor; /* Block accounting for super block */ spin_lock(&info->delalloc_root_lock); old_val = btrfs_super_bytes_used(info->super_copy); if (alloc) old_val += num_bytes; else old_val -= num_bytes; btrfs_set_super_bytes_used(info->super_copy, old_val); spin_unlock(&info->delalloc_root_lock); cache = btrfs_lookup_block_group(info, bytenr); if (!cache) return -ENOENT; /* An extent can not span multiple block groups. */ ASSERT(bytenr + num_bytes <= cache->start + cache->length); space_info = cache->space_info; factor = btrfs_bg_type_to_factor(cache->flags); /* * If this block group has free space cache written out, we need to make * sure to load it if we are removing space. This is because we need * the unpinning stage to actually add the space back to the block group, * otherwise we will leak space. */ if (!alloc && !btrfs_block_group_done(cache)) btrfs_cache_block_group(cache, true); spin_lock(&space_info->lock); spin_lock(&cache->lock); if (btrfs_test_opt(info, SPACE_CACHE) && cache->disk_cache_state < BTRFS_DC_CLEAR) cache->disk_cache_state = BTRFS_DC_CLEAR; old_val = cache->used; if (alloc) { old_val += num_bytes; cache->used = old_val; cache->reserved -= num_bytes; cache->reclaim_mark = 0; space_info->bytes_reserved -= num_bytes; space_info->bytes_used += num_bytes; space_info->disk_used += num_bytes * factor; if (READ_ONCE(space_info->periodic_reclaim)) btrfs_space_info_update_reclaimable(space_info, -num_bytes); spin_unlock(&cache->lock); spin_unlock(&space_info->lock); } else { old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; btrfs_space_info_update_bytes_pinned(info, space_info, num_bytes); space_info->bytes_used -= num_bytes; space_info->disk_used -= num_bytes * factor; if (READ_ONCE(space_info->periodic_reclaim)) btrfs_space_info_update_reclaimable(space_info, num_bytes); else reclaim = should_reclaim_block_group(cache, num_bytes); spin_unlock(&cache->lock); spin_unlock(&space_info->lock); set_extent_bit(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, EXTENT_DIRTY, NULL); } spin_lock(&trans->transaction->dirty_bgs_lock); if (list_empty(&cache->dirty_list)) { list_add_tail(&cache->dirty_list, &trans->transaction->dirty_bgs); bg_already_dirty = false; btrfs_get_block_group(cache); } spin_unlock(&trans->transaction->dirty_bgs_lock); /* * No longer have used bytes in this block group, queue it for deletion. * We do this after adding the block group to the dirty list to avoid * races between cleaner kthread and space cache writeout. */ if (!alloc && old_val == 0) { if (!btrfs_test_opt(info, DISCARD_ASYNC)) btrfs_mark_bg_unused(cache); } else if (!alloc && reclaim) { btrfs_mark_bg_to_reclaim(cache); } btrfs_put_block_group(cache); /* Modified block groups are accounted for in the delayed_refs_rsv. */ if (!bg_already_dirty) btrfs_inc_delayed_refs_rsv_bg_updates(info); return 0; } /* * Update the block_group and space info counters. * * @cache: The cache we are manipulating * @ram_bytes: The number of bytes of file content, and will be same to * @num_bytes except for the compress path. * @num_bytes: The number of bytes in question * @delalloc: The blocks are allocated for the delalloc write * * This is called by the allocator when it reserves space. If this is a * reservation and the block group has become read only we cannot make the * reservation and return -EAGAIN, otherwise this function always succeeds. */ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache, u64 ram_bytes, u64 num_bytes, int delalloc, bool force_wrong_size_class) { struct btrfs_space_info *space_info = cache->space_info; enum btrfs_block_group_size_class size_class; int ret = 0; spin_lock(&space_info->lock); spin_lock(&cache->lock); if (cache->ro) { ret = -EAGAIN; goto out; } if (btrfs_block_group_should_use_size_class(cache)) { size_class = btrfs_calc_block_group_size_class(num_bytes); ret = btrfs_use_block_group_size_class(cache, size_class, force_wrong_size_class); if (ret) goto out; } cache->reserved += num_bytes; space_info->bytes_reserved += num_bytes; trace_btrfs_space_reservation(cache->fs_info, "space_info", space_info->flags, num_bytes, 1); btrfs_space_info_update_bytes_may_use(cache->fs_info, space_info, -ram_bytes); if (delalloc) cache->delalloc_bytes += num_bytes; /* * Compression can use less space than we reserved, so wake tickets if * that happens. */ if (num_bytes < ram_bytes) btrfs_try_granting_tickets(cache->fs_info, space_info); out: spin_unlock(&cache->lock); spin_unlock(&space_info->lock); return ret; } /* * Update the block_group and space info counters. * * @cache: The cache we are manipulating * @num_bytes: The number of bytes in question * @delalloc: The blocks are allocated for the delalloc write * * This is called by somebody who is freeing space that was never actually used * on disk. For example if you reserve some space for a new leaf in transaction * A and before transaction A commits you free that leaf, you call this with * reserve set to 0 in order to clear the reservation. */ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; spin_lock(&space_info->lock); spin_lock(&cache->lock); if (cache->ro) space_info->bytes_readonly += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; space_info->max_extent_size = 0; if (delalloc) cache->delalloc_bytes -= num_bytes; spin_unlock(&cache->lock); btrfs_try_granting_tickets(cache->fs_info, space_info); spin_unlock(&space_info->lock); } static void force_metadata_allocation(struct btrfs_fs_info *info) { struct list_head *head = &info->space_info; struct btrfs_space_info *found; list_for_each_entry(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_METADATA) found->force_alloc = CHUNK_ALLOC_FORCE; } } static int should_alloc_chunk(struct btrfs_fs_info *fs_info, struct btrfs_space_info *sinfo, int force) { u64 bytes_used = btrfs_space_info_used(sinfo, false); u64 thresh; if (force == CHUNK_ALLOC_FORCE) return 1; /* * in limited mode, we want to have some free space up to * about 1% of the FS size. */ if (force == CHUNK_ALLOC_LIMITED) { thresh = btrfs_super_total_bytes(fs_info->super_copy); thresh = max_t(u64, SZ_64M, mult_perc(thresh, 1)); if (sinfo->total_bytes - bytes_used < thresh) return 1; } if (bytes_used + SZ_2M < mult_perc(sinfo->total_bytes, 80)) return 0; return 1; } int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) { u64 alloc_flags = btrfs_get_alloc_profile(trans->fs_info, type); return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) { struct btrfs_block_group *bg; int ret; /* * Check if we have enough space in the system space info because we * will need to update device items in the chunk btree and insert a new * chunk item in the chunk btree as well. This will allocate a new * system block group if needed. */ check_system_chunk(trans, flags); bg = btrfs_create_chunk(trans, flags); if (IS_ERR(bg)) { ret = PTR_ERR(bg); goto out; } ret = btrfs_chunk_alloc_add_chunk_item(trans, bg); /* * Normally we are not expected to fail with -ENOSPC here, since we have * previously reserved space in the system space_info and allocated one * new system chunk if necessary. However there are three exceptions: * * 1) We may have enough free space in the system space_info but all the * existing system block groups have a profile which can not be used * for extent allocation. * * This happens when mounting in degraded mode. For example we have a * RAID1 filesystem with 2 devices, lose one device and mount the fs * using the other device in degraded mode. If we then allocate a chunk, * we may have enough free space in the existing system space_info, but * none of the block groups can be used for extent allocation since they * have a RAID1 profile, and because we are in degraded mode with a * single device, we are forced to allocate a new system chunk with a * SINGLE profile. Making check_system_chunk() iterate over all system * block groups and check if they have a usable profile and enough space * can be slow on very large filesystems, so we tolerate the -ENOSPC and * try again after forcing allocation of a new system chunk. Like this * we avoid paying the cost of that search in normal circumstances, when * we were not mounted in degraded mode; * * 2) We had enough free space info the system space_info, and one suitable * block group to allocate from when we called check_system_chunk() * above. However right after we called it, the only system block group * with enough free space got turned into RO mode by a running scrub, * and in this case we have to allocate a new one and retry. We only * need do this allocate and retry once, since we have a transaction * handle and scrub uses the commit root to search for block groups; * * 3) We had one system block group with enough free space when we called * check_system_chunk(), but after that, right before we tried to * allocate the last extent buffer we needed, a discard operation came * in and it temporarily removed the last free space entry from the * block group (discard removes a free space entry, discards it, and * then adds back the entry to the block group cache). */ if (ret == -ENOSPC) { const u64 sys_flags = btrfs_system_alloc_profile(trans->fs_info); struct btrfs_block_group *sys_bg; sys_bg = btrfs_create_chunk(trans, sys_flags); if (IS_ERR(sys_bg)) { ret = PTR_ERR(sys_bg); btrfs_abort_transaction(trans, ret); goto out; } ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg); if (ret) { btrfs_abort_transaction(trans, ret); goto out; } ret = btrfs_chunk_alloc_add_chunk_item(trans, bg); if (ret) { btrfs_abort_transaction(trans, ret); goto out; } } else if (ret) { btrfs_abort_transaction(trans, ret); goto out; } out: btrfs_trans_release_chunk_metadata(trans); if (ret) return ERR_PTR(ret); btrfs_get_block_group(bg); return bg; } /* * Chunk allocation is done in 2 phases: * * 1) Phase 1 - through btrfs_chunk_alloc() we allocate device extents for * the chunk, the chunk mapping, create its block group and add the items * that belong in the chunk btree to it - more specifically, we need to * update device items in the chunk btree and add a new chunk item to it. * * 2) Phase 2 - through btrfs_create_pending_block_groups(), we add the block * group item to the extent btree and the device extent items to the devices * btree. * * This is done to prevent deadlocks. For example when COWing a node from the * extent btree we are holding a write lock on the node's parent and if we * trigger chunk allocation and attempted to insert the new block group item * in the extent btree right way, we could deadlock because the path for the * insertion can include that parent node. At first glance it seems impossible * to trigger chunk allocation after starting a transaction since tasks should * reserve enough transaction units (metadata space), however while that is true * most of the time, chunk allocation may still be triggered for several reasons: * * 1) When reserving metadata, we check if there is enough free space in the * metadata space_info and therefore don't trigger allocation of a new chunk. * However later when the task actually tries to COW an extent buffer from * the extent btree or from the device btree for example, it is forced to * allocate a new block group (chunk) because the only one that had enough * free space was just turned to RO mode by a running scrub for example (or * device replace, block group reclaim thread, etc), so we can not use it * for allocating an extent and end up being forced to allocate a new one; * * 2) Because we only check that the metadata space_info has enough free bytes, * we end up not allocating a new metadata chunk in that case. However if * the filesystem was mounted in degraded mode, none of the existing block * groups might be suitable for extent allocation due to their incompatible * profile (for e.g. mounting a 2 devices filesystem, where all block groups * use a RAID1 profile, in degraded mode using a single device). In this case * when the task attempts to COW some extent buffer of the extent btree for * example, it will trigger allocation of a new metadata block group with a * suitable profile (SINGLE profile in the example of the degraded mount of * the RAID1 filesystem); * * 3) The task has reserved enough transaction units / metadata space, but when * it attempts to COW an extent buffer from the extent or device btree for * example, it does not find any free extent in any metadata block group, * therefore forced to try to allocate a new metadata block group. * This is because some other task allocated all available extents in the * meanwhile - this typically happens with tasks that don't reserve space * properly, either intentionally or as a bug. One example where this is * done intentionally is fsync, as it does not reserve any transaction units * and ends up allocating a variable number of metadata extents for log * tree extent buffers; * * 4) The task has reserved enough transaction units / metadata space, but right * before it tries to allocate the last extent buffer it needs, a discard * operation comes in and, temporarily, removes the last free space entry from * the only metadata block group that had free space (discard starts by * removing a free space entry from a block group, then does the discard * operation and, once it's done, it adds back the free space entry to the * block group). * * We also need this 2 phases setup when adding a device to a filesystem with * a seed device - we must create new metadata and system chunks without adding * any of the block group items to the chunk, extent and device btrees. If we * did not do it this way, we would get ENOSPC when attempting to update those * btrees, since all the chunks from the seed device are read-only. * * Phase 1 does the updates and insertions to the chunk btree because if we had * it done in phase 2 and have a thundering herd of tasks allocating chunks in * parallel, we risk having too many system chunks allocated by many tasks if * many tasks reach phase 1 without the previous ones completing phase 2. In the * extreme case this leads to exhaustion of the system chunk array in the * superblock. This is easier to trigger if using a btree node/leaf size of 64K * and with RAID filesystems (so we have more device items in the chunk btree). * This has happened before and commit eafa4fd0ad0607 ("btrfs: fix exhaustion of * the system chunk array due to concurrent allocations") provides more details. * * Allocation of system chunks does not happen through this function. A task that * needs to update the chunk btree (the only btree that uses system chunks), must * preallocate chunk space by calling either check_system_chunk() or * btrfs_reserve_chunk_metadata() - the former is used when allocating a data or * metadata chunk or when removing a chunk, while the later is used before doing * a modification to the chunk btree - use cases for the later are adding, * removing and resizing a device as well as relocation of a system chunk. * See the comment below for more details. * * The reservation of system space, done through check_system_chunk(), as well * as all the updates and insertions into the chunk btree must be done while * holding fs_info->chunk_mutex. This is important to guarantee that while COWing * an extent buffer from the chunks btree we never trigger allocation of a new * system chunk, which would result in a deadlock (trying to lock twice an * extent buffer of the chunk btree, first time before triggering the chunk * allocation and the second time during chunk allocation while attempting to * update the chunks btree). The system chunk array is also updated while holding * that mutex. The same logic applies to removing chunks - we must reserve system * space, update the chunk btree and the system chunk array in the superblock * while holding fs_info->chunk_mutex. * * This function, btrfs_chunk_alloc(), belongs to phase 1. * * If @force is CHUNK_ALLOC_FORCE: * - return 1 if it successfully allocates a chunk, * - return errors including -ENOSPC otherwise. * If @force is NOT CHUNK_ALLOC_FORCE: * - return 0 if it doesn't need to allocate a new chunk, * - return 1 if it successfully allocates a chunk, * - return errors including -ENOSPC otherwise. */ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, enum btrfs_chunk_alloc_enum force) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *space_info; struct btrfs_block_group *ret_bg; bool wait_for_alloc = false; bool should_alloc = false; bool from_extent_allocation = false; int ret = 0; if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) { from_extent_allocation = true; force = CHUNK_ALLOC_FORCE; } /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; /* * Allocation of system chunks can not happen through this path, as we * could end up in a deadlock if we are allocating a data or metadata * chunk and there is another task modifying the chunk btree. * * This is because while we are holding the chunk mutex, we will attempt * to add the new chunk item to the chunk btree or update an existing * device item in the chunk btree, while the other task that is modifying * the chunk btree is attempting to COW an extent buffer while holding a * lock on it and on its parent - if the COW operation triggers a system * chunk allocation, then we can deadlock because we are holding the * chunk mutex and we may need to access that extent buffer or its parent * in order to add the chunk item or update a device item. * * Tasks that want to modify the chunk tree should reserve system space * before updating the chunk btree, by calling either * btrfs_reserve_chunk_metadata() or check_system_chunk(). * It's possible that after a task reserves the space, it still ends up * here - this happens in the cases described above at do_chunk_alloc(). * The task will have to either retry or fail. */ if (flags & BTRFS_BLOCK_GROUP_SYSTEM) return -ENOSPC; space_info = btrfs_find_space_info(fs_info, flags); ASSERT(space_info); do { spin_lock(&space_info->lock); if (force < space_info->force_alloc) force = space_info->force_alloc; should_alloc = should_alloc_chunk(fs_info, space_info, force); if (space_info->full) { /* No more free physical space */ if (should_alloc) ret = -ENOSPC; else ret = 0; spin_unlock(&space_info->lock); return ret; } else if (!should_alloc) { spin_unlock(&space_info->lock); return 0; } else if (space_info->chunk_alloc) { /* * Someone is already allocating, so we need to block * until this someone is finished and then loop to * recheck if we should continue with our allocation * attempt. */ wait_for_alloc = true; force = CHUNK_ALLOC_NO_FORCE; spin_unlock(&space_info->lock); mutex_lock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->chunk_mutex); } else { /* Proceed with allocation */ space_info->chunk_alloc = 1; wait_for_alloc = false; spin_unlock(&space_info->lock); } cond_resched(); } while (wait_for_alloc); mutex_lock(&fs_info->chunk_mutex); trans->allocating_chunk = true; /* * If we have mixed data/metadata chunks we want to make sure we keep * allocating mixed chunks instead of individual chunks. */ if (btrfs_mixed_space_info(space_info)) flags |= (BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA); /* * if we're doing a data chunk, go ahead and make sure that * we keep a reasonable number of metadata chunks allocated in the * FS as well. */ if (flags & BTRFS_BLOCK_GROUP_DATA && fs_info->metadata_ratio) { fs_info->data_chunk_allocations++; if (!(fs_info->data_chunk_allocations % fs_info->metadata_ratio)) force_metadata_allocation(fs_info); } ret_bg = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; if (IS_ERR(ret_bg)) { ret = PTR_ERR(ret_bg); } else if (from_extent_allocation && (flags & BTRFS_BLOCK_GROUP_DATA)) { /* * New block group is likely to be used soon. Try to activate * it now. Failure is OK for now. */ btrfs_zone_activate(ret_bg); } if (!ret) btrfs_put_block_group(ret_bg); spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) space_info->full = 1; else goto out; } else { ret = 1; space_info->max_extent_size = 0; } space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; out: space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); mutex_unlock(&fs_info->chunk_mutex); return ret; } static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type) { u64 num_dev; num_dev = btrfs_raid_array[btrfs_bg_flags_to_raid_index(type)].devs_max; if (!num_dev) num_dev = fs_info->fs_devices->rw_devices; return num_dev; } static void reserve_chunk_space(struct btrfs_trans_handle *trans, u64 bytes, u64 type) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *info; u64 left; int ret = 0; /* * Needed because we can end up allocating a system chunk and for an * atomic and race free space reservation in the chunk block reserve. */ lockdep_assert_held(&fs_info->chunk_mutex); info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); spin_lock(&info->lock); left = info->total_bytes - btrfs_space_info_used(info, true); spin_unlock(&info->lock); if (left < bytes && btrfs_test_opt(fs_info, ENOSPC_DEBUG)) { btrfs_info(fs_info, "left=%llu, need=%llu, flags=%llu", left, bytes, type); btrfs_dump_space_info(fs_info, info, 0, 0); } if (left < bytes) { u64 flags = btrfs_system_alloc_profile(fs_info); struct btrfs_block_group *bg; /* * Ignore failure to create system chunk. We might end up not * needing it, as we might not need to COW all nodes/leafs from * the paths we visit in the chunk tree (they were already COWed * or created in the current transaction for example). */ bg = btrfs_create_chunk(trans, flags); if (IS_ERR(bg)) { ret = PTR_ERR(bg); } else { /* * We have a new chunk. We also need to activate it for * zoned filesystem. */ ret = btrfs_zoned_activate_one_bg(fs_info, info, true); if (ret < 0) return; /* * If we fail to add the chunk item here, we end up * trying again at phase 2 of chunk allocation, at * btrfs_create_pending_block_groups(). So ignore * any error here. An ENOSPC here could happen, due to * the cases described at do_chunk_alloc() - the system * block group we just created was just turned into RO * mode by a scrub for example, or a running discard * temporarily removed its free space entries, etc. */ btrfs_chunk_alloc_add_chunk_item(trans, bg); } } if (!ret) { ret = btrfs_block_rsv_add(fs_info, &fs_info->chunk_block_rsv, bytes, BTRFS_RESERVE_NO_FLUSH); if (!ret) trans->chunk_bytes_reserved += bytes; } } /* * Reserve space in the system space for allocating or removing a chunk. * The caller must be holding fs_info->chunk_mutex. */ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type) { struct btrfs_fs_info *fs_info = trans->fs_info; const u64 num_devs = get_profile_num_devs(fs_info, type); u64 bytes; /* num_devs device items to update and 1 chunk item to add or remove. */ bytes = btrfs_calc_metadata_size(fs_info, num_devs) + btrfs_calc_insert_metadata_size(fs_info, 1); reserve_chunk_space(trans, bytes, type); } /* * Reserve space in the system space, if needed, for doing a modification to the * chunk btree. * * @trans: A transaction handle. * @is_item_insertion: Indicate if the modification is for inserting a new item * in the chunk btree or if it's for the deletion or update * of an existing item. * * This is used in a context where we need to update the chunk btree outside * block group allocation and removal, to avoid a deadlock with a concurrent * task that is allocating a metadata or data block group and therefore needs to * update the chunk btree while holding the chunk mutex. After the update to the * chunk btree is done, btrfs_trans_release_chunk_metadata() should be called. * */ void btrfs_reserve_chunk_metadata(struct btrfs_trans_handle *trans, bool is_item_insertion) { struct btrfs_fs_info *fs_info = trans->fs_info; u64 bytes; if (is_item_insertion) bytes = btrfs_calc_insert_metadata_size(fs_info, 1); else bytes = btrfs_calc_metadata_size(fs_info, 1); mutex_lock(&fs_info->chunk_mutex); reserve_chunk_space(trans, bytes, BTRFS_BLOCK_GROUP_SYSTEM); mutex_unlock(&fs_info->chunk_mutex); } void btrfs_put_block_group_cache(struct btrfs_fs_info *info) { struct btrfs_block_group *block_group; block_group = btrfs_lookup_first_block_group(info, 0); while (block_group) { btrfs_wait_block_group_cache_done(block_group); spin_lock(&block_group->lock); if (test_and_clear_bit(BLOCK_GROUP_FLAG_IREF, &block_group->runtime_flags)) { struct btrfs_inode *inode = block_group->inode; block_group->inode = NULL; spin_unlock(&block_group->lock); ASSERT(block_group->io_ctl.inode == NULL); iput(&inode->vfs_inode); } else { spin_unlock(&block_group->lock); } block_group = btrfs_next_block_group(block_group); } } /* * Must be called only after stopping all workers, since we could have block * group caching kthreads running, and therefore they could race with us if we * freed the block groups before stopping them. */ int btrfs_free_block_groups(struct btrfs_fs_info *info) { struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_caching_control *caching_ctl; struct rb_node *n; if (btrfs_is_zoned(info)) { if (info->active_meta_bg) { btrfs_put_block_group(info->active_meta_bg); info->active_meta_bg = NULL; } if (info->active_system_bg) { btrfs_put_block_group(info->active_system_bg); info->active_system_bg = NULL; } } write_lock(&info->block_group_cache_lock); while (!list_empty(&info->caching_block_groups)) { caching_ctl = list_entry(info->caching_block_groups.next, struct btrfs_caching_control, list); list_del(&caching_ctl->list); btrfs_put_caching_control(caching_ctl); } write_unlock(&info->block_group_cache_lock); spin_lock(&info->unused_bgs_lock); while (!list_empty(&info->unused_bgs)) { block_group = list_first_entry(&info->unused_bgs, struct btrfs_block_group, bg_list); list_del_init(&block_group->bg_list); btrfs_put_block_group(block_group); } while (!list_empty(&info->reclaim_bgs)) { block_group = list_first_entry(&info->reclaim_bgs, struct btrfs_block_group, bg_list); list_del_init(&block_group->bg_list); btrfs_put_block_group(block_group); } spin_unlock(&info->unused_bgs_lock); spin_lock(&info->zone_active_bgs_lock); while (!list_empty(&info->zone_active_bgs)) { block_group = list_first_entry(&info->zone_active_bgs, struct btrfs_block_group, active_bg_list); list_del_init(&block_group->active_bg_list); btrfs_put_block_group(block_group); } spin_unlock(&info->zone_active_bgs_lock); write_lock(&info->block_group_cache_lock); while ((n = rb_last(&info->block_group_cache_tree.rb_root)) != NULL) { block_group = rb_entry(n, struct btrfs_block_group, cache_node); rb_erase_cached(&block_group->cache_node, &info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); write_unlock(&info->block_group_cache_lock); down_write(&block_group->space_info->groups_sem); list_del(&block_group->list); up_write(&block_group->space_info->groups_sem); /* * We haven't cached this block group, which means we could * possibly have excluded extents on this block group. */ if (block_group->cached == BTRFS_CACHE_NO || block_group->cached == BTRFS_CACHE_ERROR) btrfs_free_excluded_extents(block_group); btrfs_remove_free_space_cache(block_group); ASSERT(block_group->cached != BTRFS_CACHE_STARTED); ASSERT(list_empty(&block_group->dirty_list)); ASSERT(list_empty(&block_group->io_list)); ASSERT(list_empty(&block_group->bg_list)); ASSERT(refcount_read(&block_group->refs) == 1); ASSERT(block_group->swap_extents == 0); btrfs_put_block_group(block_group); write_lock(&info->block_group_cache_lock); } write_unlock(&info->block_group_cache_lock); btrfs_release_global_block_rsv(info); while (!list_empty(&info->space_info)) { space_info = list_entry(info->space_info.next, struct btrfs_space_info, list); /* * Do not hide this behind enospc_debug, this is actually * important and indicates a real bug if this happens. */ if (WARN_ON(space_info->bytes_pinned > 0 || space_info->bytes_may_use > 0)) btrfs_dump_space_info(info, space_info, 0, 0); /* * If there was a failure to cleanup a log tree, very likely due * to an IO failure on a writeback attempt of one or more of its * extent buffers, we could not do proper (and cheap) unaccounting * of their reserved space, so don't warn on bytes_reserved > 0 in * that case. */ if (!(space_info->flags & BTRFS_BLOCK_GROUP_METADATA) || !BTRFS_FS_LOG_CLEANUP_ERROR(info)) { if (WARN_ON(space_info->bytes_reserved > 0)) btrfs_dump_space_info(info, space_info, 0, 0); } WARN_ON(space_info->reclaim_size > 0); list_del(&space_info->list); btrfs_sysfs_remove_space_info(space_info); } return 0; } void btrfs_freeze_block_group(struct btrfs_block_group *cache) { atomic_inc(&cache->frozen); } void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; bool cleanup; spin_lock(&block_group->lock); cleanup = (atomic_dec_and_test(&block_group->frozen) && test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)); spin_unlock(&block_group->lock); if (cleanup) { struct btrfs_chunk_map *map; map = btrfs_find_chunk_map(fs_info, block_group->start, 1); /* Logic error, can't happen. */ ASSERT(map); btrfs_remove_chunk_map(fs_info, map); /* Once for our lookup reference. */ btrfs_free_chunk_map(map); /* * We may have left one free space entry and other possible * tasks trimming this block group have left 1 entry each one. * Free them if any. */ btrfs_remove_free_space_cache(block_group); } } bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg) { bool ret = true; spin_lock(&bg->lock); if (bg->ro) ret = false; else bg->swap_extents++; spin_unlock(&bg->lock); return ret; } void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount) { spin_lock(&bg->lock); ASSERT(!bg->ro); ASSERT(bg->swap_extents >= amount); bg->swap_extents -= amount; spin_unlock(&bg->lock); } enum btrfs_block_group_size_class btrfs_calc_block_group_size_class(u64 size) { if (size <= SZ_128K) return BTRFS_BG_SZ_SMALL; if (size <= SZ_8M) return BTRFS_BG_SZ_MEDIUM; return BTRFS_BG_SZ_LARGE; } /* * Handle a block group allocating an extent in a size class * * @bg: The block group we allocated in. * @size_class: The size class of the allocation. * @force_wrong_size_class: Whether we are desperate enough to allow * mismatched size classes. * * Returns: 0 if the size class was valid for this block_group, -EAGAIN in the * case of a race that leads to the wrong size class without * force_wrong_size_class set. * * find_free_extent will skip block groups with a mismatched size class until * it really needs to avoid ENOSPC. In that case it will set * force_wrong_size_class. However, if a block group is newly allocated and * doesn't yet have a size class, then it is possible for two allocations of * different sizes to race and both try to use it. The loser is caught here and * has to retry. */ int btrfs_use_block_group_size_class(struct btrfs_block_group *bg, enum btrfs_block_group_size_class size_class, bool force_wrong_size_class) { ASSERT(size_class != BTRFS_BG_SZ_NONE); /* The new allocation is in the right size class, do nothing */ if (bg->size_class == size_class) return 0; /* * The new allocation is in a mismatched size class. * This means one of two things: * * 1. Two tasks in find_free_extent for different size_classes raced * and hit the same empty block_group. Make the loser try again. * 2. A call to find_free_extent got desperate enough to set * 'force_wrong_slab'. Don't change the size_class, but allow the * allocation. */ if (bg->size_class != BTRFS_BG_SZ_NONE) { if (force_wrong_size_class) return 0; return -EAGAIN; } /* * The happy new block group case: the new allocation is the first * one in the block_group so we set size_class. */ bg->size_class = size_class; return 0; } bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg) { if (btrfs_is_zoned(bg->fs_info)) return false; if (!btrfs_is_block_group_data_only(bg)) return false; return true; } |
| 202 25 996 61 25 167 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * SME code for cfg80211 * both driver SME event handling and the SME implementation * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020, 2022-2024 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/wireless.h> #include <linux/export.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> #include "nl80211.h" #include "reg.h" #include "rdev-ops.h" /* * Software SME in cfg80211, using auth/assoc/deauth calls to the * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ struct cfg80211_conn { struct cfg80211_connect_params params; /* these are sub-states of the _CONNECTING sme_state */ enum { CFG80211_CONN_SCANNING, CFG80211_CONN_SCAN_AGAIN, CFG80211_CONN_AUTHENTICATE_NEXT, CFG80211_CONN_AUTHENTICATING, CFG80211_CONN_AUTH_FAILED_TIMEOUT, CFG80211_CONN_ASSOCIATE_NEXT, CFG80211_CONN_ASSOCIATING, CFG80211_CONN_ASSOC_FAILED, CFG80211_CONN_ASSOC_FAILED_TIMEOUT, CFG80211_CONN_DEAUTH, CFG80211_CONN_ABANDON, CFG80211_CONN_CONNECTED, } state; u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; const u8 *ie; size_t ie_len; bool auto_auth, prev_bssid_valid; }; static void cfg80211_sme_free(struct wireless_dev *wdev) { if (!wdev->conn) return; kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; } static int cfg80211_conn_scan(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_scan_request *request; int n_channels, err; lockdep_assert_wiphy(wdev->wiphy); if (rdev->scan_req || rdev->scan_msg) return -EBUSY; if (wdev->conn->params.channel) n_channels = 1; else n_channels = ieee80211_get_num_supported_channels(wdev->wiphy); request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) + sizeof(request->channels[0]) * n_channels, GFP_KERNEL); if (!request) return -ENOMEM; if (wdev->conn->params.channel) { enum nl80211_band band = wdev->conn->params.channel->band; struct ieee80211_supported_band *sband = wdev->wiphy->bands[band]; if (!sband) { kfree(request); return -EINVAL; } request->channels[0] = wdev->conn->params.channel; request->rates[band] = (1 << sband->n_bitrates) - 1; } else { int i = 0, j; enum nl80211_band band; struct ieee80211_supported_band *bands; struct ieee80211_channel *channel; for (band = 0; band < NUM_NL80211_BANDS; band++) { bands = wdev->wiphy->bands[band]; if (!bands) continue; for (j = 0; j < bands->n_channels; j++) { channel = &bands->channels[j]; if (channel->flags & IEEE80211_CHAN_DISABLED) continue; request->channels[i++] = channel; } request->rates[band] = (1 << bands->n_bitrates) - 1; } n_channels = i; } request->n_channels = n_channels; request->ssids = (void *)&request->channels[n_channels]; request->n_ssids = 1; memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len); request->ssids[0].ssid_len = wdev->conn->params.ssid_len; eth_broadcast_addr(request->bssid); request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; rdev->scan_req = request; err = cfg80211_scan(rdev); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; nl80211_send_scan_start(rdev, wdev); dev_hold(wdev->netdev); } else { rdev->scan_req = NULL; kfree(request); } return err; } static int cfg80211_conn_do_work(struct wireless_dev *wdev, enum nl80211_timeout_reason *treason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_connect_params *params; struct cfg80211_auth_request auth_req = {}; struct cfg80211_assoc_request req = {}; int err; lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn) return 0; params = &wdev->conn->params; switch (wdev->conn->state) { case CFG80211_CONN_SCANNING: /* didn't find it during scan ... */ return -ENOENT; case CFG80211_CONN_SCAN_AGAIN: return cfg80211_conn_scan(wdev); case CFG80211_CONN_AUTHENTICATE_NEXT: if (WARN_ON(!rdev->ops->auth)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_AUTHENTICATING; auth_req.key = params->key; auth_req.key_len = params->key_len; auth_req.key_idx = params->key_idx; auth_req.auth_type = params->auth_type; auth_req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); auth_req.link_id = -1; err = cfg80211_mlme_auth(rdev, wdev->netdev, &auth_req); cfg80211_put_bss(&rdev->wiphy, auth_req.bss); return err; case CFG80211_CONN_AUTH_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_AUTH; return -ENOTCONN; case CFG80211_CONN_ASSOCIATE_NEXT: if (WARN_ON(!rdev->ops->assoc)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_ASSOCIATING; if (wdev->conn->prev_bssid_valid) req.prev_bssid = wdev->conn->prev_bssid; req.ie = params->ie; req.ie_len = params->ie_len; req.use_mfp = params->mfp != NL80211_MFP_NO; req.crypto = params->crypto; req.flags = params->flags; req.ht_capa = params->ht_capa; req.ht_capa_mask = params->ht_capa_mask; req.vht_capa = params->vht_capa; req.vht_capa_mask = params->vht_capa_mask; req.link_id = -1; req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); if (!req.bss) { err = -ENOENT; } else { err = cfg80211_mlme_assoc(rdev, wdev->netdev, &req, NULL); cfg80211_put_bss(&rdev->wiphy, req.bss); } if (err) cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return err; case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_ASSOC; fallthrough; case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return -ENOTCONN; case CFG80211_CONN_DEAUTH: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); fallthrough; case CFG80211_CONN_ABANDON: /* free directly, disconnected event already sent */ cfg80211_sme_free(wdev); return 0; default: return 0; } } void cfg80211_conn_work(struct work_struct *work) { struct cfg80211_registered_device *rdev = container_of(work, struct cfg80211_registered_device, conn_work); struct wireless_dev *wdev; u8 bssid_buf[ETH_ALEN], *bssid = NULL; enum nl80211_timeout_reason treason; wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; if (!netif_running(wdev->netdev)) continue; if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) continue; if (wdev->conn->params.bssid) { memcpy(bssid_buf, wdev->conn->params.bssid, ETH_ALEN); bssid = bssid_buf; } treason = NL80211_TIMEOUT_UNSPECIFIED; if (cfg80211_conn_do_work(wdev, &treason)) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = -1; cr.links[0].bssid = bssid; cr.timeout_reason = treason; __cfg80211_connect_result(wdev->netdev, &cr, false); } } wiphy_unlock(&rdev->wiphy); } static void cfg80211_step_auth_next(struct cfg80211_conn *conn, struct cfg80211_bss *bss) { memcpy(conn->bssid, bss->bssid, ETH_ALEN); conn->params.bssid = conn->bssid; conn->params.channel = bss->channel; conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; } /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; lockdep_assert_wiphy(wdev->wiphy); bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; cfg80211_step_auth_next(wdev->conn, bss); schedule_work(&rdev->conn_work); return bss; } void cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn) return; if (wdev->conn->state != CFG80211_CONN_SCANNING && wdev->conn->state != CFG80211_CONN_SCAN_AGAIN) return; bss = cfg80211_get_conn_bss(wdev); if (bss) cfg80211_put_bss(&rdev->wiphy, bss); else schedule_work(&rdev->conn_work); } void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; u16 status_code = le16_to_cpu(mgmt->u.auth.status_code); lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) return; if (status_code == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG && wdev->conn->auto_auth && wdev->conn->params.auth_type != NL80211_AUTHTYPE_NETWORK_EAP) { /* select automatically between only open, shared, leap */ switch (wdev->conn->params.auth_type) { case NL80211_AUTHTYPE_OPEN_SYSTEM: if (wdev->connect_keys) wdev->conn->params.auth_type = NL80211_AUTHTYPE_SHARED_KEY; else wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; case NL80211_AUTHTYPE_SHARED_KEY: wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; default: /* huh? */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; break; } wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; schedule_work(&rdev->conn_work); } else if (status_code != WLAN_STATUS_SUCCESS) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = status_code; cr.links[0].bssid = mgmt->bssid; cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED; __cfg80211_connect_result(wdev->netdev, &cr, false); } else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); } } bool cfg80211_sme_rx_assoc_resp(struct wireless_dev *wdev, u16 status) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return false; if (status == WLAN_STATUS_SUCCESS) { wdev->conn->state = CFG80211_CONN_CONNECTED; return false; } if (wdev->conn->prev_bssid_valid) { /* * Some stupid APs don't accept reassoc, so we * need to fall back to trying regular assoc; * return true so no event is sent to userspace. */ wdev->conn->prev_bssid_valid = false; wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); return true; } wdev->conn->state = CFG80211_CONN_ASSOC_FAILED; schedule_work(&rdev->conn_work); return false; } void cfg80211_sme_deauth(struct wireless_dev *wdev) { cfg80211_sme_free(wdev); } void cfg80211_sme_auth_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_AUTH_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_disassoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_DEAUTH; schedule_work(&rdev->conn_work); } void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ASSOC_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ABANDON; schedule_work(&rdev->conn_work); } static void cfg80211_wdev_release_bsses(struct wireless_dev *wdev) { unsigned int link; for_each_valid_link(wdev, link) { if (!wdev->links[link].client.current_bss) continue; cfg80211_unhold_bss(wdev->links[link].client.current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->links[link].client.current_bss->pub); wdev->links[link].client.current_bss = NULL; } } void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask) { unsigned int link; for_each_valid_link(wdev, link) { if (!wdev->links[link].client.current_bss || !(link_mask & BIT(link))) continue; cfg80211_unhold_bss(wdev->links[link].client.current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->links[link].client.current_bss->pub); wdev->links[link].client.current_bss = NULL; } } static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, const u8 *ies, size_t ies_len, const u8 **out_ies, size_t *out_ies_len) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *buf; size_t offs; if (!rdev->wiphy.extended_capabilities_len || (ies && cfg80211_find_ie(WLAN_EID_EXT_CAPABILITY, ies, ies_len))) { *out_ies = kmemdup(ies, ies_len, GFP_KERNEL); if (!*out_ies) return -ENOMEM; *out_ies_len = ies_len; return 0; } buf = kmalloc(ies_len + rdev->wiphy.extended_capabilities_len + 2, GFP_KERNEL); if (!buf) return -ENOMEM; if (ies_len) { static const u8 before_extcapa[] = { /* not listing IEs expected to be created by driver */ WLAN_EID_RSN, WLAN_EID_QOS_CAPA, WLAN_EID_RRM_ENABLED_CAPABILITIES, WLAN_EID_MOBILITY_DOMAIN, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_BSS_COEX_2040, }; offs = ieee80211_ie_split(ies, ies_len, before_extcapa, ARRAY_SIZE(before_extcapa), 0); memcpy(buf, ies, offs); /* leave a whole for extended capabilities IE */ memcpy(buf + offs + rdev->wiphy.extended_capabilities_len + 2, ies + offs, ies_len - offs); } else { offs = 0; } /* place extended capabilities IE (with only driver capabilities) */ buf[offs] = WLAN_EID_EXT_CAPABILITY; buf[offs + 1] = rdev->wiphy.extended_capabilities_len; memcpy(buf + offs + 2, rdev->wiphy.extended_capabilities, rdev->wiphy.extended_capabilities_len); *out_ies = buf; *out_ies_len = ies_len + rdev->wiphy.extended_capabilities_len + 2; return 0; } static int cfg80211_sme_connect(struct wireless_dev *wdev, struct cfg80211_connect_params *connect, const u8 *prev_bssid) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; int err; if (!rdev->ops->auth || !rdev->ops->assoc) return -EOPNOTSUPP; cfg80211_wdev_release_bsses(wdev); if (wdev->connected) { cfg80211_sme_free(wdev); wdev->connected = false; } if (wdev->conn) return -EINPROGRESS; wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); if (!wdev->conn) return -ENOMEM; /* * Copy all parameters, and treat explicitly IEs, BSSID, SSID. */ memcpy(&wdev->conn->params, connect, sizeof(*connect)); if (connect->bssid) { wdev->conn->params.bssid = wdev->conn->bssid; memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN); } if (cfg80211_sme_get_conn_ies(wdev, connect->ie, connect->ie_len, &wdev->conn->ie, &wdev->conn->params.ie_len)) { kfree(wdev->conn); wdev->conn = NULL; return -ENOMEM; } wdev->conn->params.ie = wdev->conn->ie; if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) { wdev->conn->auto_auth = true; /* start with open system ... should mostly work */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } else { wdev->conn->auto_auth = false; } wdev->conn->params.ssid = wdev->u.client.ssid; wdev->conn->params.ssid_len = wdev->u.client.ssid_len; /* see if we have the bss already */ bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (prev_bssid) { memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); wdev->conn->prev_bssid_valid = true; } /* we're good if we have a matching bss struct */ if (bss) { enum nl80211_timeout_reason treason; cfg80211_step_auth_next(wdev->conn, bss); err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { /* otherwise we'll need to scan for the AP first */ err = cfg80211_conn_scan(wdev); /* * If we can't scan right now, then we need to scan again * after the current scan finished, since the parameters * changed (unless we find a good AP anyway). */ if (err == -EBUSY) { err = 0; wdev->conn->state = CFG80211_CONN_SCAN_AGAIN; } } if (err) cfg80211_sme_free(wdev); return err; } static int cfg80211_sme_disconnect(struct wireless_dev *wdev, u16 reason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err; if (!wdev->conn) return 0; if (!rdev->ops->deauth) return -EOPNOTSUPP; if (wdev->conn->state == CFG80211_CONN_SCANNING || wdev->conn->state == CFG80211_CONN_SCAN_AGAIN) { err = 0; goto out; } /* wdev->conn->params.bssid must be set if > SCANNING */ err = cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->conn->params.bssid, NULL, 0, reason, false); out: cfg80211_sme_free(wdev); return err; } /* * code shared for in-device and software SME */ static bool cfg80211_is_all_idle(void) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; bool is_all_idle = true; /* * All devices must be idle as otherwise if you are actively * scanning some new beacon hints could be learned and would * count as new regulatory hints. * Also if there is any other active beaconing interface we * need not issue a disconnect hint and reset any info such * as chan dfs state, etc. */ for_each_rdev(rdev) { wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (wdev->conn || wdev->connected || cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; } wiphy_unlock(&rdev->wiphy); } return is_all_idle; } static void disconnect_work(struct work_struct *work) { rtnl_lock(); if (cfg80211_is_all_idle()) regulatory_hint_disconnect(); rtnl_unlock(); } DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); static void cfg80211_connect_result_release_bsses(struct wireless_dev *wdev, struct cfg80211_connect_resp_params *cr) { unsigned int link; for_each_valid_link(cr, link) { if (!cr->links[link].bss) continue; cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } } /* * API calls for drivers implementing connect/disconnect and * SME event handling */ /* This method must consume bss one way or another */ void __cfg80211_connect_result(struct net_device *dev, struct cfg80211_connect_resp_params *cr, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; const struct element *country_elem = NULL; const struct element *ssid; const u8 *country_data; u8 country_datalen; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif unsigned int link; const u8 *connected_addr; bool bss_not_found = false; lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (cr->valid_links) { if (WARN_ON(!cr->ap_mld_addr)) goto out; for_each_valid_link(cr, link) { if (WARN_ON(!cr->links[link].addr)) goto out; } if (WARN_ON(wdev->connect_keys)) goto out; } wdev->unprot_beacon_reported = 0; nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr, GFP_KERNEL); connected_addr = cr->valid_links ? cr->ap_mld_addr : cr->links[0].bssid; #ifdef CONFIG_CFG80211_WEXT if (wextev && !cr->valid_links) { if (cr->req_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->req_ie_len; wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, cr->req_ie); } if (cr->resp_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->resp_ie_len; wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, cr->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; if (connected_addr && cr->status == WLAN_STATUS_SUCCESS) { memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; } wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } #endif if (cr->status == WLAN_STATUS_SUCCESS) { if (!wiphy_to_rdev(wdev->wiphy)->ops->connect) { for_each_valid_link(cr, link) { if (WARN_ON_ONCE(!cr->links[link].bss)) break; } } for_each_valid_link(cr, link) { /* don't do extra lookups for failures */ if (cr->links[link].status != WLAN_STATUS_SUCCESS) continue; if (cr->links[link].bss) continue; cr->links[link].bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->links[link].bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (!cr->links[link].bss) { bss_not_found = true; break; } cfg80211_hold_bss(bss_from_pub(cr->links[link].bss)); } } cfg80211_wdev_release_bsses(wdev); if (cr->status != WLAN_STATUS_SUCCESS) { kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; cfg80211_connect_result_release_bsses(wdev, cr); cfg80211_sme_free(wdev); return; } if (WARN_ON(bss_not_found)) { cfg80211_connect_result_release_bsses(wdev, cr); return; } memset(wdev->links, 0, sizeof(wdev->links)); for_each_valid_link(cr, link) { if (cr->links[link].status == WLAN_STATUS_SUCCESS) continue; cr->valid_links &= ~BIT(link); /* don't require bss pointer for failed links */ if (!cr->links[link].bss) continue; cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } wdev->valid_links = cr->valid_links; for_each_valid_link(cr, link) wdev->links[link].client.current_bss = bss_from_pub(cr->links[link].bss); wdev->connected = true; ether_addr_copy(wdev->u.client.connected_addr, connected_addr); if (cr->valid_links) { for_each_valid_link(cr, link) memcpy(wdev->links[link].addr, cr->links[link].addr, ETH_ALEN); } cfg80211_upload_connect_keys(wdev); rcu_read_lock(); for_each_valid_link(cr, link) { country_elem = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_COUNTRY); if (country_elem) break; } if (!country_elem) { rcu_read_unlock(); return; } country_datalen = country_elem->datalen; country_data = kmemdup(country_elem->data, country_datalen, GFP_ATOMIC); rcu_read_unlock(); if (!country_data) return; regulatory_hint_country_ie(wdev->wiphy, cr->links[link].bss->channel->band, country_data, country_datalen); kfree(country_data); if (!wdev->u.client.ssid_len) { rcu_read_lock(); for_each_valid_link(cr, link) { ssid = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_SSID); if (!ssid || !ssid->datalen) continue; memcpy(wdev->u.client.ssid, ssid->data, ssid->datalen); wdev->u.client.ssid_len = ssid->datalen; break; } rcu_read_unlock(); } return; out: for_each_valid_link(cr, link) cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } static void cfg80211_update_link_bss(struct wireless_dev *wdev, struct cfg80211_bss **bss) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_internal_bss *ibss; if (!*bss) return; ibss = bss_from_pub(*bss); if (list_empty(&ibss->list)) { struct cfg80211_bss *found = NULL, *tmp = *bss; found = cfg80211_get_bss(wdev->wiphy, NULL, (*bss)->bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (found) { /* The same BSS is already updated so use it * instead, as it has latest info. */ *bss = found; } else { /* Update with BSS provided by driver, it will * be freshly added and ref cnted, we can free * the old one. * * signal_valid can be false, as we are not * expecting the BSS to be found. * * keep the old timestamp to avoid confusion */ cfg80211_bss_update(rdev, ibss, false, ibss->ts); } cfg80211_put_bss(wdev->wiphy, tmp); } } /* Consumes bss object(s) one way or another */ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_connect_resp_params *params, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; size_t link_info_size = 0; unsigned int link; for_each_valid_link(params, link) { cfg80211_update_link_bss(wdev, ¶ms->links[link].bss); link_info_size += params->links[link].bssid ? ETH_ALEN : 0; link_info_size += params->links[link].addr ? ETH_ALEN : 0; } ev = kzalloc(sizeof(*ev) + (params->ap_mld_addr ? ETH_ALEN : 0) + params->req_ie_len + params->resp_ie_len + params->fils.kek_len + params->fils.pmk_len + (params->fils.pmkid ? WLAN_PMKID_LEN : 0) + link_info_size, gfp); if (!ev) { for_each_valid_link(params, link) cfg80211_put_bss(wdev->wiphy, params->links[link].bss); return; } ev->type = EVENT_CONNECT_RESULT; next = ((u8 *)ev) + sizeof(*ev); if (params->ap_mld_addr) { ev->cr.ap_mld_addr = next; memcpy((void *)ev->cr.ap_mld_addr, params->ap_mld_addr, ETH_ALEN); next += ETH_ALEN; } if (params->req_ie_len) { ev->cr.req_ie = next; ev->cr.req_ie_len = params->req_ie_len; memcpy((void *)ev->cr.req_ie, params->req_ie, params->req_ie_len); next += params->req_ie_len; } if (params->resp_ie_len) { ev->cr.resp_ie = next; ev->cr.resp_ie_len = params->resp_ie_len; memcpy((void *)ev->cr.resp_ie, params->resp_ie, params->resp_ie_len); next += params->resp_ie_len; } if (params->fils.kek_len) { ev->cr.fils.kek = next; ev->cr.fils.kek_len = params->fils.kek_len; memcpy((void *)ev->cr.fils.kek, params->fils.kek, params->fils.kek_len); next += params->fils.kek_len; } if (params->fils.pmk_len) { ev->cr.fils.pmk = next; ev->cr.fils.pmk_len = params->fils.pmk_len; memcpy((void *)ev->cr.fils.pmk, params->fils.pmk, params->fils.pmk_len); next += params->fils.pmk_len; } if (params->fils.pmkid) { ev->cr.fils.pmkid = next; memcpy((void *)ev->cr.fils.pmkid, params->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->cr.fils.update_erp_next_seq_num = params->fils.update_erp_next_seq_num; if (params->fils.update_erp_next_seq_num) ev->cr.fils.erp_next_seq_num = params->fils.erp_next_seq_num; ev->cr.valid_links = params->valid_links; for_each_valid_link(params, link) { if (params->links[link].bss) cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; memcpy((void *)ev->cr.links[link].addr, params->links[link].addr, ETH_ALEN); next += ETH_ALEN; } if (params->links[link].bssid) { ev->cr.links[link].bssid = next; memcpy((void *)ev->cr.links[link].bssid, params->links[link].bssid, ETH_ALEN); next += ETH_ALEN; } } ev->cr.status = params->status; ev->cr.timeout_reason = params->timeout_reason; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_connect_done); /* Consumes bss object one way or another */ void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info) { #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif unsigned int link; const u8 *connected_addr; lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (WARN_ON(!wdev->connected)) goto out; if (info->valid_links) { if (WARN_ON(!info->ap_mld_addr)) goto out; for_each_valid_link(info, link) { if (WARN_ON(!info->links[link].addr)) goto out; } } cfg80211_wdev_release_bsses(wdev); for_each_valid_link(info, link) { if (WARN_ON(!info->links[link].bss)) goto out; } memset(wdev->links, 0, sizeof(wdev->links)); wdev->valid_links = info->valid_links; for_each_valid_link(info, link) { cfg80211_hold_bss(bss_from_pub(info->links[link].bss)); wdev->links[link].client.current_bss = bss_from_pub(info->links[link].bss); } connected_addr = info->valid_links ? info->ap_mld_addr : info->links[0].bss->bssid; ether_addr_copy(wdev->u.client.connected_addr, connected_addr); if (info->valid_links) { for_each_valid_link(info, link) memcpy(wdev->links[link].addr, info->links[link].addr, ETH_ALEN); } wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), wdev->netdev, info, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT if (!info->valid_links) { if (info->req_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->req_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCREQIE, &wrqu, info->req_ie); } if (info->resp_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->resp_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, &wrqu, info->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); } #endif return; out: for_each_valid_link(info, link) cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } /* Consumes info->links.bss object(s) one way or another */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; unsigned int link; size_t link_info_size = 0; bool bss_not_found = false; for_each_valid_link(info, link) { link_info_size += info->links[link].addr ? ETH_ALEN : 0; link_info_size += info->links[link].bssid ? ETH_ALEN : 0; if (info->links[link].bss) continue; info->links[link].bss = cfg80211_get_bss(wdev->wiphy, info->links[link].channel, info->links[link].bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (!info->links[link].bss) { bss_not_found = true; break; } } if (WARN_ON(bss_not_found)) goto out; ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len + info->fils.kek_len + info->fils.pmk_len + (info->fils.pmkid ? WLAN_PMKID_LEN : 0) + (info->ap_mld_addr ? ETH_ALEN : 0) + link_info_size, gfp); if (!ev) goto out; ev->type = EVENT_ROAMED; next = ((u8 *)ev) + sizeof(*ev); if (info->req_ie_len) { ev->rm.req_ie = next; ev->rm.req_ie_len = info->req_ie_len; memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len); next += info->req_ie_len; } if (info->resp_ie_len) { ev->rm.resp_ie = next; ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); next += info->resp_ie_len; } if (info->fils.kek_len) { ev->rm.fils.kek = next; ev->rm.fils.kek_len = info->fils.kek_len; memcpy((void *)ev->rm.fils.kek, info->fils.kek, info->fils.kek_len); next += info->fils.kek_len; } if (info->fils.pmk_len) { ev->rm.fils.pmk = next; ev->rm.fils.pmk_len = info->fils.pmk_len; memcpy((void *)ev->rm.fils.pmk, info->fils.pmk, info->fils.pmk_len); next += info->fils.pmk_len; } if (info->fils.pmkid) { ev->rm.fils.pmkid = next; memcpy((void *)ev->rm.fils.pmkid, info->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->rm.fils.update_erp_next_seq_num = info->fils.update_erp_next_seq_num; if (info->fils.update_erp_next_seq_num) ev->rm.fils.erp_next_seq_num = info->fils.erp_next_seq_num; if (info->ap_mld_addr) { ev->rm.ap_mld_addr = next; memcpy((void *)ev->rm.ap_mld_addr, info->ap_mld_addr, ETH_ALEN); next += ETH_ALEN; } ev->rm.valid_links = info->valid_links; for_each_valid_link(info, link) { ev->rm.links[link].bss = info->links[link].bss; if (info->links[link].addr) { ev->rm.links[link].addr = next; memcpy((void *)ev->rm.links[link].addr, info->links[link].addr, ETH_ALEN); next += ETH_ALEN; } if (info->links[link].bssid) { ev->rm.links[link].bssid = next; memcpy((void *)ev->rm.links[link].bssid, info->links[link].bssid, ETH_ALEN); next += ETH_ALEN; } } spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); return; out: for_each_valid_link(info, link) cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } EXPORT_SYMBOL(cfg80211_roamed); void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len) { lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT && wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO)) return; if (wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) { if (WARN_ON(!wdev->connected) || WARN_ON(!ether_addr_equal(wdev->u.client.connected_addr, peer_addr))) return; } nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, peer_addr, td_bitmap, td_bitmap_len); } void cfg80211_port_authorized(struct net_device *dev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; if (WARN_ON(!peer_addr)) return; ev = kzalloc(sizeof(*ev) + td_bitmap_len, gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.peer_addr, peer_addr, ETH_ALEN); ev->pa.td_bitmap = ((u8 *)ev) + sizeof(*ev); ev->pa.td_bitmap_len = td_bitmap_len; memcpy((void *)ev->pa.td_bitmap, td_bitmap, td_bitmap_len); /* * Use the wdev event list so that if there are pending * connected/roamed events, they will be reported first. */ spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_port_authorized); void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int i; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; cfg80211_wdev_release_bsses(wdev); wdev->valid_links = 0; wdev->connected = false; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); /* stop critical protocol if supported */ if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { rdev->crit_proto_nlportid = 0; rdev_crit_proto_stop(rdev, wdev); } /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ if (rdev->ops->del_key) { int max_key_idx = 5; if (wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, -1, i, false, NULL); } rdev_set_qos_map(rdev, dev, NULL); #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); wdev->wext.connect.ssid_len = 0; #endif schedule_work(&cfg80211_disconnect_work); cfg80211_schedule_channels_check(wdev); } void cfg80211_disconnected(struct net_device *dev, u16 reason, const u8 *ie, size_t ie_len, bool locally_generated, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; ev = kzalloc(sizeof(*ev) + ie_len, gfp); if (!ev) return; ev->type = EVENT_DISCONNECTED; ev->dc.ie = ((u8 *)ev) + sizeof(*ev); ev->dc.ie_len = ie_len; memcpy((void *)ev->dc.ie, ie, ie_len); ev->dc.reason = reason; ev->dc.locally_generated = locally_generated; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_disconnected); /* * API calls for nl80211/wext compatibility code */ int cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, struct cfg80211_cached_keys *connkeys, const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; lockdep_assert_wiphy(wdev->wiphy); /* * If we have an ssid_len, we're trying to connect or are * already connected, so reject a new SSID unless it's the * same (which is the case for re-association.) */ if (wdev->u.client.ssid_len && (wdev->u.client.ssid_len != connect->ssid_len || memcmp(wdev->u.client.ssid, connect->ssid, wdev->u.client.ssid_len))) return -EALREADY; /* * If connected, reject (re-)association unless prev_bssid * matches the current BSSID. */ if (wdev->connected) { if (!prev_bssid) return -EALREADY; if (!ether_addr_equal(prev_bssid, wdev->u.client.connected_addr)) return -ENOTCONN; } /* * Reject if we're in the process of connecting with WEP, * this case isn't very interesting and trying to handle * it would make the code much more complex. */ if (wdev->connect_keys) return -EINPROGRESS; cfg80211_oper_and_ht_capa(&connect->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); cfg80211_oper_and_vht_capa(&connect->vht_capa_mask, rdev->wiphy.vht_capa_mod_mask); if (connkeys && connkeys->def >= 0) { int idx; u32 cipher; idx = connkeys->def; cipher = connkeys->params[idx].cipher; /* If given a WEP key we may need it for shared key auth */ if (cipher == WLAN_CIPHER_SUITE_WEP40 || cipher == WLAN_CIPHER_SUITE_WEP104) { connect->key_idx = idx; connect->key = connkeys->params[idx].key; connect->key_len = connkeys->params[idx].key_len; /* * If ciphers are not set (e.g. when going through * iwconfig), we have to set them appropriately here. */ if (connect->crypto.cipher_group == 0) connect->crypto.cipher_group = cipher; if (connect->crypto.n_ciphers_pairwise == 0) { connect->crypto.n_ciphers_pairwise = 1; connect->crypto.ciphers_pairwise[0] = cipher; } } } else { if (WARN_ON(connkeys)) return -EINVAL; /* connect can point to wdev->wext.connect which * can hold key data from a previous connection */ connect->key = NULL; connect->key_len = 0; connect->key_idx = 0; } wdev->connect_keys = connkeys; memcpy(wdev->u.client.ssid, connect->ssid, connect->ssid_len); wdev->u.client.ssid_len = connect->ssid_len; wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : IEEE80211_BSS_TYPE_ESS; if (!rdev->ops->connect) err = cfg80211_sme_connect(wdev, connect, prev_bssid); else err = rdev_connect(rdev, dev, connect); if (err) { wdev->connect_keys = NULL; /* * This could be reassoc getting refused, don't clear * ssid_len in that case. */ if (!wdev->connected) wdev->u.client.ssid_len = 0; return err; } return 0; } int cfg80211_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err = 0; lockdep_assert_wiphy(wdev->wiphy); kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->conn_owner_nlportid = 0; if (wdev->conn) err = cfg80211_sme_disconnect(wdev, reason); else if (!rdev->ops->disconnect) cfg80211_mlme_down(rdev, dev); else if (wdev->u.client.ssid_len) err = rdev_disconnect(rdev, dev, reason); /* * Clear ssid_len unless we actually were fully connected, * in which case cfg80211_disconnected() will take care of * this later. */ if (!wdev->connected) wdev->u.client.ssid_len = 0; return err; } /* * Used to clean up after the connection / connection attempt owner socket * disconnects */ void cfg80211_autodisconnect_wk(struct work_struct *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, disconnect_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); wiphy_lock(wdev->wiphy); if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, wdev->netdev, -1, false); break; case NL80211_IFTYPE_MESH_POINT: cfg80211_leave_mesh(rdev, wdev->netdev); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: /* * Use disconnect_bssid if still connecting and * ops->disconnect not implemented. Otherwise we can * use cfg80211_disconnect. */ if (rdev->ops->disconnect || wdev->connected) cfg80211_disconnect(rdev, wdev->netdev, WLAN_REASON_DEAUTH_LEAVING, true); else cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->disconnect_bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); break; default: break; } } wiphy_unlock(wdev->wiphy); } |
| 65 64 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/minmax.h> #include <linux/syscall_user_dispatch.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; if (!tsk->ptrace || (current != tsk->parent) || ((get_dumpable(mm) != SUID_DUMP_USER) && !ptracer_capable(tsk, mm->user_ns))) { mmput(mm); return 0; } ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(child, SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* * Ensure that nothing can wake it up, even SIGKILL * * A task is switched to this state while a ptrace operation is in progress; * such that the ptrace operation is uninterruptible. */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { unsigned long flags; /* * The child may be awake and may have cleared * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); } } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state && WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN))) ret = -ESRCH; return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int check_ptrace_options(unsigned long data) { if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || current->ptrace & PT_SUSPEND_SECCOMP) return -EPERM; } return 0; } static inline void ptrace_set_stopped(struct task_struct *task, bool seize) { guard(spinlock)(&task->sighand->siglock); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); } } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; if (seize) { if (addr != 0) return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) return -EIO; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); if (unlikely(task->flags & PF_KTHREAD)) return -EPERM; if (same_thread_group(task, current)) return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, &task->signal->cred_guard_mutex) { scoped_guard (task_lock, task) { retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (retval) return retval; } scoped_guard (write_lock_irq, &tasklist_lock) { if (unlikely(task->exit_state)) return -EPERM; if (task->ptrace) return -EPERM; task->ptrace = flags; ptrace_link(task, current); ptrace_set_stopped(task, seize); } } /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); proc_ptrace_connector(task, PTRACE_ATTACH); return 0; } /** * ptrace_traceme -- helper for PTRACE_TRACEME * * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ static int ptrace_traceme(void) { int ret = -EPERM; write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { ret = security_ptrace_traceme(current->parent); /* * Check PF_EXITING to ensure ->real_parent has not passed * exit_ptrace(). Otherwise we don't report the error but * pretend ->real_parent untraces us right after return. */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); return ret; } /* * Called with irqs disabled, returns true if childs should reap themselves. */ static int ignoring_children(struct sighand_struct *sigh) { int ret; spin_lock(&sigh->siglock); ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); spin_unlock(&sigh->siglock); return ret; } /* * Called with tasklist_lock held for writing. * Unlink a traced task, and clean it up if it was a traced zombie. * Return true if it needs to be reaped with release_task(). * (We can't call release_task() here because we already hold tasklist_lock.) * * If it's a zombie, our attachedness prevented normal parent notification * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * * If it's our own child, there is no notification to do. But if our normal * children self-reap, then this child was prevented by ptrace and we must * reap it now, in that case we must also wake up sub-threads sleeping in * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { bool dead; __ptrace_unlink(p); if (p->exit_state != EXIT_ZOMBIE) return false; dead = !thread_group_leader(p); if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); else if (ignoring_children(tracer->sighand)) { __wake_up_parent(p, tracer); dead = true; } } /* Mark it as in the process of being reaped. */ if (dead) p->exit_state = EXIT_DEAD; return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); write_lock_irq(&tasklist_lock); /* * We rely on ptrace_freeze_traced(). It can't be killed and * untraced by another thread, it can't be a zombie. */ WARN_ON(!child->ptrace || child->exit_state); /* * tasklist_lock avoids the race with wait_task_stopped(), see * the comment in ptrace_resume(). */ child->exit_code = data; __ptrace_detach(current, child); write_unlock_irq(&tasklist_lock); proc_ptrace_connector(child, PTRACE_DETACH); return 0; } /* * Detach all tasks we were using ptrace on. Called with tasklist held * for writing. */ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) { struct task_struct *p, *n; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); } } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; return -EIO; } if (copy_to_user(dst, buf, retval)) return -EFAULT; copied += retval; src += retval; dst += retval; len -= retval; } return copied; } int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; return -EIO; } copied += retval; src += retval; dst += retval; len -= retval; } return copied; } static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; int ret; ret = check_ptrace_options(data); if (ret) return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); flags |= (data << PT_OPT_FLAG_SHIFT); child->ptrace = flags; return 0; } static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(info, child->last_siginfo); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(child->last_siginfo, info); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_peek_siginfo(struct task_struct *child, unsigned long addr, unsigned long data) { struct ptrace_peeksiginfo_args arg; struct sigpending *pending; struct sigqueue *q; int ret, i; ret = copy_from_user(&arg, (void __user *) addr, sizeof(struct ptrace_peeksiginfo_args)); if (ret) return -EFAULT; if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) return -EINVAL; /* unknown flags */ if (arg.nr < 0) return -EINVAL; /* Ensure arg.off fits in an unsigned long */ if (arg.off > ULONG_MAX) return 0; if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else pending = &child->pending; for (i = 0; i < arg.nr; ) { kernel_siginfo_t info; unsigned long off = arg.off + i; bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info)) { ret = -EFAULT; break; } } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; if (copy_siginfo_to_user(uinfo, &info)) { ret = -EFAULT; break; } } data += sizeof(siginfo_t); i++; if (signal_pending(current)) break; cond_resched(); } if (i > 0) return i; return ret; } #ifdef CONFIG_RSEQ static long ptrace_get_rseq_configuration(struct task_struct *task, unsigned long size, void __user *data) { struct ptrace_rseq_configuration conf = { .rseq_abi_pointer = (u64)(uintptr_t)task->rseq, .rseq_abi_size = task->rseq_len, .signature = task->rseq_sig, .flags = 0, }; size = min_t(unsigned long, size, sizeof(conf)); if (copy_to_user(data, &conf, size)) return -EFAULT; return sizeof(conf); } #endif #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) #else #define is_singleblock(request) 0 #endif #ifdef PTRACE_SYSEMU #define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) #else #define is_sysemu_singlestep(request) 0 #endif static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { if (!valid_signal(data)) return -EIO; if (request == PTRACE_SYSCALL) set_task_syscall_work(child, SYSCALL_TRACE); else clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) set_task_syscall_work(child, SYSCALL_EMU); else clear_task_syscall_work(child, SYSCALL_EMU); #endif if (is_singleblock(request)) { if (unlikely(!arch_has_block_step())) return -EIO; user_enable_block_step(child); } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { if (unlikely(!arch_has_single_step())) return -EIO; user_enable_single_step(child); } else { user_disable_single_step(child); } /* * Change ->exit_code and ->state under siglock to avoid the race * with wait_task_stopped() in between; a non-zero ->exit_code will * wrongly look like another report from tracee. * * Note that we need siglock even if ->exit_code == data and/or this * status was not reported yet, the new status must not be cleared by * wait_task_stopped() after resume. */ spin_lock_irq(&child->sighand->siglock); child->exit_code = data; child->jobctl &= ~JOBCTL_TRACED; wake_up_state(child, __TASK_TRACED); spin_unlock_irq(&child->sighand->siglock); return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static const struct user_regset * find_regset(const struct user_regset_view *view, unsigned int type) { const struct user_regset *regset; int n; for (n = 0; n < view->n; ++n) { regset = view->regsets + n; if (regset->core_note_type == type) return regset; } return NULL; } static int ptrace_regset(struct task_struct *task, int req, unsigned int type, struct iovec *kiov) { const struct user_regset_view *view = task_user_regset_view(task); const struct user_regset *regset = find_regset(view, type); int regset_no; if (!regset || (kiov->iov_len % regset->size) != 0) return -EINVAL; regset_no = regset - view->regsets; kiov->iov_len = min(kiov->iov_len, (__kernel_size_t) (regset->n * regset->size)); if (req == PTRACE_GETREGSET) return copy_regset_to_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); else return copy_regset_from_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); } /* * This is declared in linux/regset.h and defined in machine-dependent * code. We put the export here, near the primary machine-neutral use, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); static unsigned long ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { unsigned long args[ARRAY_SIZE(info->entry.args)]; int i; info->op = PTRACE_SYSCALL_INFO_ENTRY; info->entry.nr = syscall_get_nr(child, regs); syscall_get_arguments(child, regs, args); for (i = 0; i < ARRAY_SIZE(args); i++) info->entry.args[i] = args[i]; /* args is the last field in struct ptrace_syscall_info.entry */ return offsetofend(struct ptrace_syscall_info, entry.args); } static unsigned long ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { /* * As struct ptrace_syscall_info.entry is currently a subset * of struct ptrace_syscall_info.seccomp, it makes sense to * initialize that subset using ptrace_get_syscall_info_entry(). * This can be reconsidered in the future if these structures * diverge significantly enough. */ ptrace_get_syscall_info_entry(child, regs, info); info->op = PTRACE_SYSCALL_INFO_SECCOMP; info->seccomp.ret_data = child->ptrace_message; /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } static unsigned long ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { info->op = PTRACE_SYSCALL_INFO_EXIT; info->exit.rval = syscall_get_error(child, regs); info->exit.is_error = !!info->exit.rval; if (!info->exit.is_error) info->exit.rval = syscall_get_return_value(child, regs); /* is_error is the last field in struct ptrace_syscall_info.exit */ return offsetofend(struct ptrace_syscall_info, exit.is_error); } static int ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, void __user *datavp) { struct pt_regs *regs = task_pt_regs(child); struct ptrace_syscall_info info = { .op = PTRACE_SYSCALL_INFO_NONE, .arch = syscall_get_arch(child), .instruction_pointer = instruction_pointer(regs), .stack_pointer = user_stack_pointer(regs), }; unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); unsigned long write_size; /* * This does not need lock_task_sighand() to access * child->last_siginfo because ptrace_freeze_traced() * called earlier by ptrace_check_attach() ensures that * the tracee cannot go away and clear its last_siginfo. */ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { case SIGTRAP | 0x80: switch (child->ptrace_message) { case PTRACE_EVENTMSG_SYSCALL_ENTRY: actual_size = ptrace_get_syscall_info_entry(child, regs, &info); break; case PTRACE_EVENTMSG_SYSCALL_EXIT: actual_size = ptrace_get_syscall_info_exit(child, regs, &info); break; } break; case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info); break; } write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: return generic_ptrace_peekdata(child, addr, data); case PTRACE_POKETEXT: case PTRACE_POKEDATA: return generic_ptrace_pokedata(child, addr, data); #ifdef PTRACE_OLDSETOPTIONS case PTRACE_OLDSETOPTIONS: #endif case PTRACE_SETOPTIONS: ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: ret = put_user(child->ptrace_message, datalp); break; case PTRACE_PEEKSIGINFO: ret = ptrace_peek_siginfo(child, addr, data); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user(&siginfo, datavp); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; case PTRACE_GETSIGMASK: { sigset_t *mask; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (test_tsk_restore_sigmask(child)) mask = &child->saved_sigmask; else mask = &child->blocked; if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; } case PTRACE_SETSIGMASK: { sigset_t new_set; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { ret = -EFAULT; break; } sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); /* * Every thread does recalc_sigpending() after resume, so * retarget_shared_pending() and recalc_sigpending() are not * called here. */ spin_lock_irq(&child->sighand->siglock); child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); clear_tsk_restore_sigmask(child); ret = 0; break; } case PTRACE_INTERRUPT: /* * Stop tracee without any side-effect on signal or job * control. At least one trap is guaranteed to happen * after this request. If @child is already trapped, the * current trap is not disturbed and another trap will * happen after the current trap is ended with PTRACE_CONT. * * The actual trap might not be PTRACE_EVENT_STOP trap but * the pending condition is cleared regardless. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; /* * INTERRUPT doesn't disturb existing trap sans one * exception. If ptracer issued LISTEN for the current * STOP, this INTERRUPT should clear LISTEN and re-trap * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; break; case PTRACE_LISTEN: /* * Listen for events. Tracee must be in STOP. It's not * resumed per-se but is not considered to be in TRACED by * wait(2) or ptrace(2). If an async event (e.g. group * stop state change) happens, tracee will enter STOP trap * again. Alternatively, ptracer can issue INTERRUPT to * finish listening and re-trap tracee into STOP. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; si = child->last_siginfo; if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { child->jobctl |= JOBCTL_LISTENING; /* * If NOTIFY is set, it means event happened between * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); break; case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { struct mm_struct *mm = get_task_mm(child); unsigned long tmp = 0; ret = -ESRCH; if (!mm) break; switch (addr) { case PTRACE_GETFDPIC_EXEC: tmp = mm->context.exec_fdpic_loadmap; break; case PTRACE_GETFDPIC_INTERP: tmp = mm->context.interp_fdpic_loadmap; break; default: break; } mmput(mm); ret = put_user(tmp, datalp); break; } #endif case PTRACE_SINGLESTEP: #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif #ifdef PTRACE_SYSEMU case PTRACE_SYSEMU: case PTRACE_SYSEMU_SINGLESTEP: #endif case PTRACE_SYSCALL: case PTRACE_CONT: return ptrace_resume(child, request, data); case PTRACE_KILL: send_sig_info(SIGKILL, SEND_SIG_NOINFO, child); return 0; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct iovec __user *uiov = datavp; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || __get_user(kiov.iov_len, &uiov->iov_len)) return -EFAULT; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; #endif case PTRACE_SECCOMP_GET_FILTER: ret = seccomp_get_filter(child, addr, datavp); break; case PTRACE_SECCOMP_GET_METADATA: ret = seccomp_get_metadata(child, addr, datavp); break; #ifdef CONFIG_RSEQ case PTRACE_GET_RSEQ_CONFIGURATION: ret = ptrace_get_rseq_configuration(child, addr, datavp); break; #endif case PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_set_config(child, addr, datavp); break; case PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_get_config(child, addr, datavp); break; default: break; } return ret; } SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, unsigned long, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); out: return ret; } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data) { unsigned long tmp; int copied; copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); } int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data) { int copied; copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } #if defined CONFIG_COMPAT int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; kernel_siginfo_t siginfo; int ret; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else ret = put_user(word, datap); break; case PTRACE_POKETEXT: case PTRACE_POKEDATA: ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; case PTRACE_GETEVENTMSG: ret = put_user((compat_ulong_t) child->ptrace_message, datap); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user32( (struct compat_siginfo __user *) datap, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user32( &siginfo, (struct compat_siginfo __user *) datap); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct compat_iovec __user *uiov = (struct compat_iovec __user *) datap; compat_uptr_t ptr; compat_size_t len; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || __get_user(len, &uiov->iov_len)) return -EFAULT; kiov.iov_base = compat_ptr(ptr); kiov.iov_len = len; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } #endif default: ret = ptrace_request(child, request, addr, data); } return ret; } COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); } out_put_task_struct: put_task_struct(child); out: return ret; } #endif /* CONFIG_COMPAT */ |
| 3 25 52 111 25 2 7 1 25 25 12 17 13 13 1 25 25 9 4 2 3 4 2 2 1 1 2 4 1 3 3 6 1 3 3 3 6 110 111 51 51 59 1 13 9 9 38 27 25 25 33 32 2 33 33 38 27 38 17 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/msdos.c * * Code extracted from drivers/block/genhd.c * Copyright (C) 1991-1998 Linus Torvalds * * Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug * in the early extended-partition checks and added DM partitions * * Support for DiskManager v6.0x added by Mark Lord, * with information provided by OnTrack. This now works for linux fdisk * and LILO, as well as loadlin and bootln. Note that disks other than * /dev/hda *must* have a "DOS" type 0x51 partition in the first slot (hda1). * * More flexible handling of extended partitions - aeb, 950831 * * Check partition table on IDE disks for common CHS translations * * Re-organised Feb 1998 Russell King * * BSD disklabel support by Yossi Gottlieb <yogo@math.tau.ac.il> * updated by Marc Espie <Marc.Espie@openbsd.org> * * Unixware slices support by Andrzej Krzysztofowicz <ankry@mif.pg.gda.pl> * and Krzysztof G. Baranowski <kgb@knm.org.pl> */ #include <linux/msdos_fs.h> #include <linux/msdos_partition.h> #include "check.h" #include "efi.h" /* * Many architectures don't like unaligned accesses, while * the nr_sects and start_sect partition table entries are * at a 2 (mod 4) address. */ #include <asm/unaligned.h> static inline sector_t nr_sects(struct msdos_partition *p) { return (sector_t)get_unaligned_le32(&p->nr_sects); } static inline sector_t start_sect(struct msdos_partition *p) { return (sector_t)get_unaligned_le32(&p->start_sect); } static inline int is_extended_partition(struct msdos_partition *p) { return (p->sys_ind == DOS_EXTENDED_PARTITION || p->sys_ind == WIN98_EXTENDED_PARTITION || p->sys_ind == LINUX_EXTENDED_PARTITION); } #define MSDOS_LABEL_MAGIC1 0x55 #define MSDOS_LABEL_MAGIC2 0xAA static inline int msdos_magic_present(unsigned char *p) { return (p[0] == MSDOS_LABEL_MAGIC1 && p[1] == MSDOS_LABEL_MAGIC2); } /* Value is EBCDIC 'IBMA' */ #define AIX_LABEL_MAGIC1 0xC9 #define AIX_LABEL_MAGIC2 0xC2 #define AIX_LABEL_MAGIC3 0xD4 #define AIX_LABEL_MAGIC4 0xC1 static int aix_magic_present(struct parsed_partitions *state, unsigned char *p) { struct msdos_partition *pt = (struct msdos_partition *) (p + 0x1be); Sector sect; unsigned char *d; int slot, ret = 0; if (!(p[0] == AIX_LABEL_MAGIC1 && p[1] == AIX_LABEL_MAGIC2 && p[2] == AIX_LABEL_MAGIC3 && p[3] == AIX_LABEL_MAGIC4)) return 0; /* * Assume the partition table is valid if Linux partitions exists. * Note that old Solaris/x86 partitions use the same indicator as * Linux swap partitions, so we consider that a Linux partition as * well. */ for (slot = 1; slot <= 4; slot++, pt++) { if (pt->sys_ind == SOLARIS_X86_PARTITION || pt->sys_ind == LINUX_RAID_PARTITION || pt->sys_ind == LINUX_DATA_PARTITION || pt->sys_ind == LINUX_LVM_PARTITION || is_extended_partition(pt)) return 0; } d = read_part_sector(state, 7, §); if (d) { if (d[0] == '_' && d[1] == 'L' && d[2] == 'V' && d[3] == 'M') ret = 1; put_dev_sector(sect); } return ret; } static void set_info(struct parsed_partitions *state, int slot, u32 disksig) { struct partition_meta_info *info = &state->parts[slot].info; snprintf(info->uuid, sizeof(info->uuid), "%08x-%02x", disksig, slot); info->volname[0] = 0; state->parts[slot].has_info = true; } /* * Create devices for each logical partition in an extended partition. * The logical partitions form a linked list, with each entry being * a partition table with two entries. The first entry * is the real data partition (with a start relative to the partition * table start). The second is a pointer to the next logical partition * (with a start relative to the entire extended partition). * We do not create a Linux partition for the partition tables, but * only for the actual data partitions. */ static void parse_extended(struct parsed_partitions *state, sector_t first_sector, sector_t first_size, u32 disksig) { struct msdos_partition *p; Sector sect; unsigned char *data; sector_t this_sector, this_size; sector_t sector_size; int loopct = 0; /* number of links followed without finding a data partition */ int i; sector_size = queue_logical_block_size(state->disk->queue) / 512; this_sector = first_sector; this_size = first_size; while (1) { if (++loopct > 100) return; if (state->next == state->limit) return; data = read_part_sector(state, this_sector, §); if (!data) return; if (!msdos_magic_present(data + 510)) goto done; p = (struct msdos_partition *) (data + 0x1be); /* * Usually, the first entry is the real data partition, * the 2nd entry is the next extended partition, or empty, * and the 3rd and 4th entries are unused. * However, DRDOS sometimes has the extended partition as * the first entry (when the data partition is empty), * and OS/2 seems to use all four entries. */ /* * First process the data partition(s) */ for (i = 0; i < 4; i++, p++) { sector_t offs, size, next; if (!nr_sects(p) || is_extended_partition(p)) continue; /* Check the 3rd and 4th entries - these sometimes contain random garbage */ offs = start_sect(p)*sector_size; size = nr_sects(p)*sector_size; next = this_sector + offs; if (i >= 2) { if (offs + size > this_size) continue; if (next < first_sector) continue; if (next + size > first_sector + first_size) continue; } put_partition(state, state->next, next, size); set_info(state, state->next, disksig); if (p->sys_ind == LINUX_RAID_PARTITION) state->parts[state->next].flags = ADDPART_FLAG_RAID; loopct = 0; if (++state->next == state->limit) goto done; } /* * Next, process the (first) extended partition, if present. * (So far, there seems to be no reason to make * parse_extended() recursive and allow a tree * of extended partitions.) * It should be a link to the next logical partition. */ p -= 4; for (i = 0; i < 4; i++, p++) if (nr_sects(p) && is_extended_partition(p)) break; if (i == 4) goto done; /* nothing left to do */ this_sector = first_sector + start_sect(p) * sector_size; this_size = nr_sects(p) * sector_size; put_dev_sector(sect); } done: put_dev_sector(sect); } #define SOLARIS_X86_NUMSLICE 16 #define SOLARIS_X86_VTOC_SANE (0x600DDEEEUL) struct solaris_x86_slice { __le16 s_tag; /* ID tag of partition */ __le16 s_flag; /* permission flags */ __le32 s_start; /* start sector no of partition */ __le32 s_size; /* # of blocks in partition */ }; struct solaris_x86_vtoc { unsigned int v_bootinfo[3]; /* info needed by mboot */ __le32 v_sanity; /* to verify vtoc sanity */ __le32 v_version; /* layout version */ char v_volume[8]; /* volume name */ __le16 v_sectorsz; /* sector size in bytes */ __le16 v_nparts; /* number of partitions */ unsigned int v_reserved[10]; /* free space */ struct solaris_x86_slice v_slice[SOLARIS_X86_NUMSLICE]; /* slice headers */ unsigned int timestamp[SOLARIS_X86_NUMSLICE]; /* timestamp */ char v_asciilabel[128]; /* for compatibility */ }; /* james@bpgc.com: Solaris has a nasty indicator: 0x82 which also indicates linux swap. Be careful before believing this is Solaris. */ static void parse_solaris_x86(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_SOLARIS_X86_PARTITION Sector sect; struct solaris_x86_vtoc *v; int i; short max_nparts; v = read_part_sector(state, offset + 1, §); if (!v) return; if (le32_to_cpu(v->v_sanity) != SOLARIS_X86_VTOC_SANE) { put_dev_sector(sect); return; } { char tmp[1 + BDEVNAME_SIZE + 10 + 11 + 1]; snprintf(tmp, sizeof(tmp), " %s%d: <solaris:", state->name, origin); strlcat(state->pp_buf, tmp, PAGE_SIZE); } if (le32_to_cpu(v->v_version) != 1) { char tmp[64]; snprintf(tmp, sizeof(tmp), " cannot handle version %d vtoc>\n", le32_to_cpu(v->v_version)); strlcat(state->pp_buf, tmp, PAGE_SIZE); put_dev_sector(sect); return; } /* Ensure we can handle previous case of VTOC with 8 entries gracefully */ max_nparts = le16_to_cpu(v->v_nparts) > 8 ? SOLARIS_X86_NUMSLICE : 8; for (i = 0; i < max_nparts && state->next < state->limit; i++) { struct solaris_x86_slice *s = &v->v_slice[i]; char tmp[3 + 10 + 1 + 1]; if (s->s_size == 0) continue; snprintf(tmp, sizeof(tmp), " [s%d]", i); strlcat(state->pp_buf, tmp, PAGE_SIZE); /* solaris partitions are relative to current MS-DOS * one; must add the offset of the current partition */ put_partition(state, state->next++, le32_to_cpu(s->s_start)+offset, le32_to_cpu(s->s_size)); } put_dev_sector(sect); strlcat(state->pp_buf, " >\n", PAGE_SIZE); #endif } /* check against BSD src/sys/sys/disklabel.h for consistency */ #define BSD_DISKMAGIC (0x82564557UL) /* The disk magic number */ #define BSD_MAXPARTITIONS 16 #define OPENBSD_MAXPARTITIONS 16 #define BSD_FS_UNUSED 0 /* disklabel unused partition entry ID */ struct bsd_disklabel { __le32 d_magic; /* the magic number */ __s16 d_type; /* drive type */ __s16 d_subtype; /* controller/d_type specific */ char d_typename[16]; /* type name, e.g. "eagle" */ char d_packname[16]; /* pack identifier */ __u32 d_secsize; /* # of bytes per sector */ __u32 d_nsectors; /* # of data sectors per track */ __u32 d_ntracks; /* # of tracks per cylinder */ __u32 d_ncylinders; /* # of data cylinders per unit */ __u32 d_secpercyl; /* # of data sectors per cylinder */ __u32 d_secperunit; /* # of data sectors per unit */ __u16 d_sparespertrack; /* # of spare sectors per track */ __u16 d_sparespercyl; /* # of spare sectors per cylinder */ __u32 d_acylinders; /* # of alt. cylinders per unit */ __u16 d_rpm; /* rotational speed */ __u16 d_interleave; /* hardware sector interleave */ __u16 d_trackskew; /* sector 0 skew, per track */ __u16 d_cylskew; /* sector 0 skew, per cylinder */ __u32 d_headswitch; /* head switch time, usec */ __u32 d_trkseek; /* track-to-track seek, usec */ __u32 d_flags; /* generic flags */ #define NDDATA 5 __u32 d_drivedata[NDDATA]; /* drive-type specific information */ #define NSPARE 5 __u32 d_spare[NSPARE]; /* reserved for future use */ __le32 d_magic2; /* the magic number (again) */ __le16 d_checksum; /* xor of data incl. partitions */ /* filesystem and partition information: */ __le16 d_npartitions; /* number of partitions in following */ __le32 d_bbsize; /* size of boot area at sn0, bytes */ __le32 d_sbsize; /* max size of fs superblock, bytes */ struct bsd_partition { /* the partition table */ __le32 p_size; /* number of sectors in partition */ __le32 p_offset; /* starting sector */ __le32 p_fsize; /* filesystem basic fragment size */ __u8 p_fstype; /* filesystem type, see below */ __u8 p_frag; /* filesystem fragments per block */ __le16 p_cpg; /* filesystem cylinders per group */ } d_partitions[BSD_MAXPARTITIONS]; /* actually may be more */ }; #if defined(CONFIG_BSD_DISKLABEL) /* * Create devices for BSD partitions listed in a disklabel, under a * dos-like partition. See parse_extended() for more information. */ static void parse_bsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin, char *flavour, int max_partitions) { Sector sect; struct bsd_disklabel *l; struct bsd_partition *p; char tmp[64]; l = read_part_sector(state, offset + 1, §); if (!l) return; if (le32_to_cpu(l->d_magic) != BSD_DISKMAGIC) { put_dev_sector(sect); return; } snprintf(tmp, sizeof(tmp), " %s%d: <%s:", state->name, origin, flavour); strlcat(state->pp_buf, tmp, PAGE_SIZE); if (le16_to_cpu(l->d_npartitions) < max_partitions) max_partitions = le16_to_cpu(l->d_npartitions); for (p = l->d_partitions; p - l->d_partitions < max_partitions; p++) { sector_t bsd_start, bsd_size; if (state->next == state->limit) break; if (p->p_fstype == BSD_FS_UNUSED) continue; bsd_start = le32_to_cpu(p->p_offset); bsd_size = le32_to_cpu(p->p_size); /* FreeBSD has relative offset if C partition offset is zero */ if (memcmp(flavour, "bsd\0", 4) == 0 && le32_to_cpu(l->d_partitions[2].p_offset) == 0) bsd_start += offset; if (offset == bsd_start && size == bsd_size) /* full parent partition, we have it already */ continue; if (offset > bsd_start || offset+size < bsd_start+bsd_size) { strlcat(state->pp_buf, "bad subpartition - ignored\n", PAGE_SIZE); continue; } put_partition(state, state->next++, bsd_start, bsd_size); } put_dev_sector(sect); if (le16_to_cpu(l->d_npartitions) > max_partitions) { snprintf(tmp, sizeof(tmp), " (ignored %d more)", le16_to_cpu(l->d_npartitions) - max_partitions); strlcat(state->pp_buf, tmp, PAGE_SIZE); } strlcat(state->pp_buf, " >\n", PAGE_SIZE); } #endif static void parse_freebsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_BSD_DISKLABEL parse_bsd(state, offset, size, origin, "bsd", BSD_MAXPARTITIONS); #endif } static void parse_netbsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_BSD_DISKLABEL parse_bsd(state, offset, size, origin, "netbsd", BSD_MAXPARTITIONS); #endif } static void parse_openbsd(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_BSD_DISKLABEL parse_bsd(state, offset, size, origin, "openbsd", OPENBSD_MAXPARTITIONS); #endif } #define UNIXWARE_DISKMAGIC (0xCA5E600DUL) /* The disk magic number */ #define UNIXWARE_DISKMAGIC2 (0x600DDEEEUL) /* The slice table magic nr */ #define UNIXWARE_NUMSLICE 16 #define UNIXWARE_FS_UNUSED 0 /* Unused slice entry ID */ struct unixware_slice { __le16 s_label; /* label */ __le16 s_flags; /* permission flags */ __le32 start_sect; /* starting sector */ __le32 nr_sects; /* number of sectors in slice */ }; struct unixware_disklabel { __le32 d_type; /* drive type */ __le32 d_magic; /* the magic number */ __le32 d_version; /* version number */ char d_serial[12]; /* serial number of the device */ __le32 d_ncylinders; /* # of data cylinders per device */ __le32 d_ntracks; /* # of tracks per cylinder */ __le32 d_nsectors; /* # of data sectors per track */ __le32 d_secsize; /* # of bytes per sector */ __le32 d_part_start; /* # of first sector of this partition*/ __le32 d_unknown1[12]; /* ? */ __le32 d_alt_tbl; /* byte offset of alternate table */ __le32 d_alt_len; /* byte length of alternate table */ __le32 d_phys_cyl; /* # of physical cylinders per device */ __le32 d_phys_trk; /* # of physical tracks per cylinder */ __le32 d_phys_sec; /* # of physical sectors per track */ __le32 d_phys_bytes; /* # of physical bytes per sector */ __le32 d_unknown2; /* ? */ __le32 d_unknown3; /* ? */ __le32 d_pad[8]; /* pad */ struct unixware_vtoc { __le32 v_magic; /* the magic number */ __le32 v_version; /* version number */ char v_name[8]; /* volume name */ __le16 v_nslices; /* # of slices */ __le16 v_unknown1; /* ? */ __le32 v_reserved[10]; /* reserved */ struct unixware_slice v_slice[UNIXWARE_NUMSLICE]; /* slice headers */ } vtoc; }; /* 408 */ /* * Create devices for Unixware partitions listed in a disklabel, under a * dos-like partition. See parse_extended() for more information. */ static void parse_unixware(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_UNIXWARE_DISKLABEL Sector sect; struct unixware_disklabel *l; struct unixware_slice *p; l = read_part_sector(state, offset + 29, §); if (!l) return; if (le32_to_cpu(l->d_magic) != UNIXWARE_DISKMAGIC || le32_to_cpu(l->vtoc.v_magic) != UNIXWARE_DISKMAGIC2) { put_dev_sector(sect); return; } { char tmp[1 + BDEVNAME_SIZE + 10 + 12 + 1]; snprintf(tmp, sizeof(tmp), " %s%d: <unixware:", state->name, origin); strlcat(state->pp_buf, tmp, PAGE_SIZE); } p = &l->vtoc.v_slice[1]; /* I omit the 0th slice as it is the same as whole disk. */ while (p - &l->vtoc.v_slice[0] < UNIXWARE_NUMSLICE) { if (state->next == state->limit) break; if (p->s_label != UNIXWARE_FS_UNUSED) put_partition(state, state->next++, le32_to_cpu(p->start_sect), le32_to_cpu(p->nr_sects)); p++; } put_dev_sector(sect); strlcat(state->pp_buf, " >\n", PAGE_SIZE); #endif } #define MINIX_NR_SUBPARTITIONS 4 /* * Minix 2.0.0/2.0.2 subpartition support. * Anand Krishnamurthy <anandk@wiproge.med.ge.com> * Rajeev V. Pillai <rajeevvp@yahoo.com> */ static void parse_minix(struct parsed_partitions *state, sector_t offset, sector_t size, int origin) { #ifdef CONFIG_MINIX_SUBPARTITION Sector sect; unsigned char *data; struct msdos_partition *p; int i; data = read_part_sector(state, offset, §); if (!data) return; p = (struct msdos_partition *)(data + 0x1be); /* The first sector of a Minix partition can have either * a secondary MBR describing its subpartitions, or * the normal boot sector. */ if (msdos_magic_present(data + 510) && p->sys_ind == MINIX_PARTITION) { /* subpartition table present */ char tmp[1 + BDEVNAME_SIZE + 10 + 9 + 1]; snprintf(tmp, sizeof(tmp), " %s%d: <minix:", state->name, origin); strlcat(state->pp_buf, tmp, PAGE_SIZE); for (i = 0; i < MINIX_NR_SUBPARTITIONS; i++, p++) { if (state->next == state->limit) break; /* add each partition in use */ if (p->sys_ind == MINIX_PARTITION) put_partition(state, state->next++, start_sect(p), nr_sects(p)); } strlcat(state->pp_buf, " >\n", PAGE_SIZE); } put_dev_sector(sect); #endif /* CONFIG_MINIX_SUBPARTITION */ } static struct { unsigned char id; void (*parse)(struct parsed_partitions *, sector_t, sector_t, int); } subtypes[] = { {FREEBSD_PARTITION, parse_freebsd}, {NETBSD_PARTITION, parse_netbsd}, {OPENBSD_PARTITION, parse_openbsd}, {MINIX_PARTITION, parse_minix}, {UNIXWARE_PARTITION, parse_unixware}, {SOLARIS_X86_PARTITION, parse_solaris_x86}, {NEW_SOLARIS_X86_PARTITION, parse_solaris_x86}, {0, NULL}, }; int msdos_partition(struct parsed_partitions *state) { sector_t sector_size; Sector sect; unsigned char *data; struct msdos_partition *p; struct fat_boot_sector *fb; int slot; u32 disksig; sector_size = queue_logical_block_size(state->disk->queue) / 512; data = read_part_sector(state, 0, §); if (!data) return -1; /* * Note order! (some AIX disks, e.g. unbootable kind, * have no MSDOS 55aa) */ if (aix_magic_present(state, data)) { put_dev_sector(sect); #ifdef CONFIG_AIX_PARTITION return aix_partition(state); #else strlcat(state->pp_buf, " [AIX]", PAGE_SIZE); return 0; #endif } if (!msdos_magic_present(data + 510)) { put_dev_sector(sect); return 0; } /* * Now that the 55aa signature is present, this is probably * either the boot sector of a FAT filesystem or a DOS-type * partition table. Reject this in case the boot indicator * is not 0 or 0x80. */ p = (struct msdos_partition *) (data + 0x1be); for (slot = 1; slot <= 4; slot++, p++) { if (p->boot_ind != 0 && p->boot_ind != 0x80) { /* * Even without a valid boot indicator value * its still possible this is valid FAT filesystem * without a partition table. */ fb = (struct fat_boot_sector *) data; if (slot == 1 && fb->reserved && fb->fats && fat_valid_media(fb->media)) { strlcat(state->pp_buf, "\n", PAGE_SIZE); put_dev_sector(sect); return 1; } else { put_dev_sector(sect); return 0; } } } #ifdef CONFIG_EFI_PARTITION p = (struct msdos_partition *) (data + 0x1be); for (slot = 1 ; slot <= 4 ; slot++, p++) { /* If this is an EFI GPT disk, msdos should ignore it. */ if (p->sys_ind == EFI_PMBR_OSTYPE_EFI_GPT) { put_dev_sector(sect); return 0; } } #endif p = (struct msdos_partition *) (data + 0x1be); disksig = le32_to_cpup((__le32 *)(data + 0x1b8)); /* * Look for partitions in two passes: * First find the primary and DOS-type extended partitions. * On the second pass look inside *BSD, Unixware and Solaris partitions. */ state->next = 5; for (slot = 1 ; slot <= 4 ; slot++, p++) { sector_t start = start_sect(p)*sector_size; sector_t size = nr_sects(p)*sector_size; if (!size) continue; if (is_extended_partition(p)) { /* * prevent someone doing mkfs or mkswap on an * extended partition, but leave room for LILO * FIXME: this uses one logical sector for > 512b * sector, although it may not be enough/proper. */ sector_t n = 2; n = min(size, max(sector_size, n)); put_partition(state, slot, start, n); strlcat(state->pp_buf, " <", PAGE_SIZE); parse_extended(state, start, size, disksig); strlcat(state->pp_buf, " >", PAGE_SIZE); continue; } put_partition(state, slot, start, size); set_info(state, slot, disksig); if (p->sys_ind == LINUX_RAID_PARTITION) state->parts[slot].flags = ADDPART_FLAG_RAID; if (p->sys_ind == DM6_PARTITION) strlcat(state->pp_buf, "[DM]", PAGE_SIZE); if (p->sys_ind == EZD_PARTITION) strlcat(state->pp_buf, "[EZD]", PAGE_SIZE); } strlcat(state->pp_buf, "\n", PAGE_SIZE); /* second pass - output for each on a separate line */ p = (struct msdos_partition *) (0x1be + data); for (slot = 1 ; slot <= 4 ; slot++, p++) { unsigned char id = p->sys_ind; int n; if (!nr_sects(p)) continue; for (n = 0; subtypes[n].parse && id != subtypes[n].id; n++) ; if (!subtypes[n].parse) continue; subtypes[n].parse(state, start_sect(p) * sector_size, nr_sects(p) * sector_size, slot); } put_dev_sector(sect); return 1; } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * UDP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/udp.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data * YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file. */ #include <linux/bpf-cgroup.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/indirect_call_wrapper.h> #include <trace/events/udp.h> #include <net/addrconf.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/raw.h> #include <net/seg6.h> #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/busy_poll.h> #include <net/sock_reuseport.h> #include <net/gro.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <trace/events/skb.h> #include "udp_impl.h" static void udpv6_destruct_sock(struct sock *sk) { udp_destruct_common(sk); inet6_sock_destruct(sk); } int udpv6_init_sock(struct sock *sk) { udp_lib_init_sock(sk); sk->sk_destruct = udpv6_destruct_sock; set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } INDIRECT_CALLABLE_SCOPE u32 udp6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, sizeof(udp6_ehash_secret)); net_get_random_once(&udp_ipv6_hash_secret, sizeof(udp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum); unsigned int hash2_partial = ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; return udp_lib_get_port(sk, snum, hash2_nulladdr); } void udp_v6_rehash(struct sock *sk) { u16 new_hash = ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); } static int compute_score(struct sock *sk, struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, int dif, int sdif) { int bound_dev_if, score; struct inet_sock *inet; bool dev_match; if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || sk->sk_family != PF_INET6) return -1; if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score = 0; inet = inet_sk(sk); if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; score++; } if (!ipv6_addr_any(&sk->sk_v6_daddr)) { if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) return -1; score++; } bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); dev_match = udp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif); if (!dev_match) return -1; if (bound_dev_if) score++; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } /* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; int score, badness; bool need_rescore; result = NULL; badness = -1; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { need_rescore = false; rescore: score = compute_score(need_rescore ? result : sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; if (need_rescore) continue; if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; } result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), saddr, sport, daddr, hnum, udp6_ehashfn); if (!result) { result = sk; continue; } /* Fall back to scoring if group has connections */ if (!reuseport_has_conns(sk)) return result; /* Reuseport logic returned an error, keep original score. */ if (IS_ERR(result)) continue; /* compute_score is too long of a function to be * inlined, and calling it again here yields * measureable overhead for some * workloads. Work around it by jumping * backwards to rescore 'result'. */ need_rescore = true; goto rescore; } } return result; } /* rcu_read_lock() must be held */ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; struct sock *result, *sk; hash2 = ipv6_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; /* Lookup connected or non-wildcard sockets */ result = udp6_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) goto done; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled) && udptable == net->ipv4.udp_table) { sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), saddr, sport, daddr, hnum, dif, udp6_ehashfn); if (sk) { result = sk; goto done; } } /* Got non-wildcard socket or error on first lookup */ if (result) goto done; /* Lookup wildcard sockets */ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; result = udp6_lib_lookup2(net, saddr, sport, &in6addr_any, hnum, dif, sdif, hslot2, skb); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(__udp6_lib_lookup); static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { const struct ipv6hdr *iph = ipv6_hdr(skb); return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), inet6_sdif(skb), udptable, skb); } struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, &iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { struct sock *sk; sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, 0, net->ipv4.udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(udp6_lib_lookup); #endif /* do not use the scratch area len for jumbogram: their length execeeds the * scratch area space; note that the IP6CB flags is still in the first * cacheline, so checking for jumbograms is cheap */ static int udp6_skb_len(struct sk_buff *skb) { return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb); } /* * This should be easy, if there is something there we * return it, otherwise we block. */ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; unsigned int ulen, copied; int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); struct udp_mib __percpu *mib; bool checksum_valid = false; int is_udp4; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, &off, &err); if (!skb) return err; ulen = udp6_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); mib = __UDPX_MIB(sk, is_udp4); /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial * coverage checksum (UDP-Lite), do it before the copy. */ if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { checksum_valid = udp_skb_csum_unnecessary(skb) || !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } if (checksum_valid || udp_skb_csum_unnecessary(skb)) { if (udp_skb_is_linear(skb)) err = copy_linear_skb(skb, copied, off, &msg->msg_iter); else err = skb_copy_datagram_msg(skb, off, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; } if (unlikely(err)) { if (!peeking) { atomic_inc(&sk->sk_drops); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } kfree_skb(skb); return err; } if (!peeking) SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS); sock_recv_cmsgs(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); sin6->sin6_family = AF_INET6; sin6->sin6_port = udp_hdr(skb)->source; sin6->sin6_flowinfo = 0; if (is_udp4) { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin6->sin6_addr); sin6->sin6_scope_id = 0; } else { sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); } *addr_len = sizeof(*sin6); BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, (struct sockaddr *)sin6, addr_len); } if (udp_test_bit(GRO_ENABLED, sk)) udp_cmsg_recv(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (is_udp4) { if (inet_cmsg_flags(inet)) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); } else { if (np->rxopt.all) ip6_datagram_recv_specific_ctl(sk, msg, skb); } err = copied; if (flags & MSG_TRUNC) err = ulen; skb_consume_udp(sk, skb, peeking ? -err : err); return err; csum_copy_err: if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, udp_skb_destructor)) { SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS); SNMP_INC_STATS(mib, UDP_MIB_INERRORS); } kfree_skb(skb); /* starting over for a new packet, but check if we need to yield */ cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); } EXPORT_SYMBOL(udpv6_encap_enable); /* Handler for tunnels with arbitrary destination ports: no socket lookup, go * through error handlers in encapsulations looking for a match. */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); const struct ip6_tnl_encap_ops *encap; encap = rcu_dereference(ip6tun_encaps[i]); if (!encap) continue; handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } return -ENOENT; } /* Try to match ICMP errors to UDP tunnels by looking up a socket without * reversing source and destination port: this will match tunnels that force the * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that * lwtunnels might actually break this assumption by being configured with * different destination ports on endpoints, in this case we won't be able to * trace ICMP messages back to them. * * If this doesn't match any socket, probe tunnels with arbitrary destination * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port * we've sent packets to won't necessarily match the local destination port. * * Then ask the tunnel implementation to match the error against a valid * association. * * Return an error if we can't find a match, the socket if we need further * processing, zero otherwise. */ static struct sock *__udp6_lib_err_encap(struct net *net, const struct ipv6hdr *hdr, int offset, struct udphdr *uh, struct udp_table *udptable, struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, __be32 info) { int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); /* Network header needs to point to the outer IPv6 header inside ICMP */ skb_reset_network_header(skb); /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, offset); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (lookup && lookup(sk, skb)) sk = NULL; goto out; } sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source, &hdr->saddr, uh->dest, inet6_iif(skb), 0, udptable, skb); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } out: if (!sk) { sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code, offset, info)); } skb_set_transport_header(skb, transport_offset); skb_set_network_header(skb, network_offset); return sk; } int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info, struct udp_table *udptable) { struct ipv6_pinfo *np; const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct in6_addr *saddr = &hdr->saddr; const struct in6_addr *daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; struct udphdr *uh = (struct udphdr *)(skb->data+offset); bool tunnel = false; struct sock *sk; int harderr; int err; struct net *net = dev_net(skb->dev); sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, udptable, sk, skb, opt, type, code, info); if (!sk) return 0; } else sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return PTR_ERR(sk); } tunnel = true; } harderr = icmpv6_err_convert(type, code, &err); np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { if (!ip6_sk_accept_pmtu(sk)) goto out; ip6_sk_update_pmtu(skb, sk, info); if (READ_ONCE(np->pmtudisc) != IPV6_PMTUDISC_DONT) harderr = 1; } if (type == NDISC_REDIRECT) { if (tunnel) { ip6_redirect(skb, sock_net(sk), inet6_iif(skb), READ_ONCE(sk->sk_mark), sk->sk_uid); } else { ip6_sk_redirect(skb, sk); } goto out; } /* Tunnels don't have an application socket: don't pass errors back */ if (tunnel) { if (udp_sk(sk)->encap_err_rcv) udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1)); goto out; } if (!inet6_test_bit(RECVERR6, sk)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else { ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1)); } sk->sk_err = err; sk_error_report(sk); out: return 0; } static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; if (!ipv6_addr_any(&sk->sk_v6_daddr)) { sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); sk_incoming_cpu_update(sk); } else { sk_mark_napi_id_once(sk, skb); } rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); enum skb_drop_reason drop_reason; /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) { UDP6_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; } else { UDP6_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, is_udplite); drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); trace_udp_fail_queue_rcv_skb(rc, sk, skb); sk_skb_reason_drop(sk, skb, drop_reason); return -1; } return 0; } static __inline__ int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { return __udp6_lib_err(skb, opt, type, code, offset, info, dev_net(skb->dev)->ipv4.udp_table); } static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } nf_reset_ct(skb); if (static_branch_unlikely(&udpv6_encap_needed_key) && READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* * This is an encapsulation socket so pass the skb to * the socket's udp_encap_rcv() hook. Otherwise, just * fall through and pass this up the UDP socket. * up->encap_rcv() returns the following value: * =0 if skb was successfully passed to the encap * handler or was discarded by it. * >0 if skb should be passed on to UDP. * <0 if skb should be resubmitted as proto -N */ /* if we're overly short, let UDP handle it */ encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; /* Verify checksum before giving to encap */ if (udp_lib_checksum_complete(skb)) goto csum_error; ret = encap_rcv(sk, skb); if (ret <= 0) { __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); return -ret; } } /* FALLTHROUGH -- it's a UDP Packet */ } /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ if (udp_test_bit(UDPLITE_RECV_CC, sk) && UDP_SKB_CB(skb)->partial_cov) { u16 pcrlen = READ_ONCE(up->pcrlen); if (pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } if (UDP_SKB_CB(skb)->cscov < pcrlen) { net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n", UDP_SKB_CB(skb)->cscov, pcrlen); goto drop; } } prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto drop; } udp_csum_pull_header(skb); skb_dst_drop(skb); return __udpv6_queue_rcv_skb(sk, skb); csum_error: drop_reason = SKB_DROP_REASON_UDP_CSUM; __UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); sk_skb_reason_drop(sk, skb, drop_reason); return -1; } static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff *next, *segs; int ret; if (likely(!udp_unexpected_gso(sk, skb))) return udpv6_queue_rcv_one_skb(sk, skb); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, false); skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); udp_post_segment_fix_csum(skb); ret = udpv6_queue_rcv_one_skb(sk, skb); if (ret > 0) ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret, true); } return 0; } static bool __udp_v6_is_mcast_sock(struct net *net, const struct sock *sk, __be16 loc_port, const struct in6_addr *loc_addr, __be16 rmt_port, const struct in6_addr *rmt_addr, int dif, int sdif, unsigned short hnum) { const struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) return false; if (udp_sk(sk)->udp_port_hash != hnum || sk->sk_family != PF_INET6 || (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || !udp_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif) || (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; if (!inet6_mc_check(sk, loc_addr, rmt_addr)) return false; return true; } static void udp6_csum_zero_error(struct sk_buff *skb) { /* RFC 2460 section 8.1 says that we SHOULD log * this error. Well, it is reasonable. */ net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); } /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. */ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, struct udp_table *udptable, int proto) { struct sock *sk, *first = NULL; const struct udphdr *uh = udp_hdr(skb); unsigned short hnum = ntohs(uh->dest); struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); unsigned int offset = offsetof(typeof(*sk), sk_node); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); int dif = inet6_iif(skb); int sdif = inet6_sdif(skb); struct hlist_node *node; struct sk_buff *nskb; if (use_hash2) { hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) & udptable->mask; hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr, uh->source, saddr, dif, sdif, hnum)) continue; /* If zero checksum and no_check is not on for * the socket then skip it. */ if (!uh->check && !udp_get_no_check6_rx(sk)) continue; if (!first) { first = sk; continue; } nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { atomic_inc(&sk->sk_drops); __UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); __UDP6_INC_STATS(net, UDP_MIB_INERRORS, IS_UDPLITE(sk)); continue; } if (udpv6_queue_rcv_skb(sk, nskb) > 0) consume_skb(nskb); } /* Also lookup *:port if we are using hash2 and haven't done so yet. */ if (use_hash2 && hash2 != hash2_any) { hash2 = hash2_any; goto start_lookup; } if (first) { if (udpv6_queue_rcv_skb(first, skb) > 0) consume_skb(skb); } else { kfree_skb(skb); __UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI, proto == IPPROTO_UDPLITE); } return 0; } static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { if (udp_sk_rx_dst_set(sk, dst)) sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and * return code conversion for ip layer consumption */ static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, struct udphdr *uh) { int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo); ret = udpv6_queue_rcv_skb(sk, skb); /* a return value > 0 means to resubmit the input */ if (ret > 0) return ret; return 0; } int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); struct sock *sk = NULL; struct udphdr *uh; bool refcounted; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto discard; saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; uh = udp_hdr(skb); ulen = ntohs(uh->len); if (ulen > skb->len) goto short_packet; if (proto == IPPROTO_UDP) { /* UDP validates ulen. */ /* Check for jumbo payload */ if (ulen == 0) ulen = skb->len; if (ulen < sizeof(*uh)) goto short_packet; if (ulen < skb->len) { if (pskb_trim_rcsum(skb, ulen)) goto short_packet; saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; uh = udp_hdr(skb); } } if (udp6_csum_init(skb, uh, proto)) goto csum_error; /* Check if the socket is already available, e.g. due to early demux */ sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, &refcounted, udp6_ehashfn); if (IS_ERR(sk)) goto no_sk; if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_get_no_check6_rx(sk)) { if (refcounted) sock_put(sk); goto report_csum_error; } ret = udp6_unicast_rcv_skb(sk, skb, uh); if (refcounted) sock_put(sk); return ret; } /* * Multicast receive code */ if (ipv6_addr_is_multicast(daddr)) return __udp6_lib_mcast_deliver(net, skb, saddr, daddr, udptable, proto); /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { if (!uh->check && !udp_get_no_check6_rx(sk)) goto report_csum_error; return udp6_unicast_rcv_skb(sk, skb, uh); } no_sk: reason = SKB_DROP_REASON_NO_SOCKET; if (!uh->check) goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; nf_reset_ct(skb); if (udp_lib_checksum_complete(skb)) goto csum_error; __UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); sk_skb_reason_drop(sk, skb, reason); return 0; short_packet: if (reason == SKB_DROP_REASON_NOT_SPECIFIED) reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", proto == IPPROTO_UDPLITE ? "-Lite" : "", saddr, ntohs(uh->source), ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; report_csum_error: udp6_csum_zero_error(skb); csum_error: if (reason == SKB_DROP_REASON_NOT_SPECIFIED) reason = SKB_DROP_REASON_UDP_CSUM; __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: __UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); sk_skb_reason_drop(sk, skb, reason); return 0; } static struct sock *__udp6_lib_demux_lookup(struct net *net, __be16 loc_port, const struct in6_addr *loc_addr, __be16 rmt_port, const struct in6_addr *rmt_addr, int dif, int sdif) { struct udp_table *udptable = net->ipv4.udp_table; unsigned short hnum = ntohs(loc_port); unsigned int hash2, slot2; struct udp_hslot *hslot2; __portpair ports; struct sock *sk; hash2 = ipv6_portaddr_hash(net, loc_addr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; ports = INET_COMBINED_PORTS(rmt_port, hnum); udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (sk->sk_state == TCP_ESTABLISHED && inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; } return NULL; } void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; struct sock *sk; struct dst_entry *dst; int dif = skb->dev->ifindex; int sdif = inet6_sdif(skb); if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) return; uh = udp_hdr(skb); if (skb->pkt_type == PACKET_HOST) sk = __udp6_lib_demux_lookup(net, uh->dest, &ipv6_hdr(skb)->daddr, uh->source, &ipv6_hdr(skb)->saddr, dif, sdif); else return; if (!sk) return; skb->sk = sk; DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst) { /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); } } INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP); } /* * Throw away all pending data and cancel the corking. Socket is locked. */ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); if (up->pending == AF_INET) udp_flush_pending_frames(sk); else if (up->pending) { up->len = 0; WRITE_ONCE(up->pending, 0); ip6_flush_pending_frames(sk); } } static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* The following checks are replicated from __ip6_datagram_connect() * and intended to prevent BPF program called below from accessing * bytes that are out of the bound specified by user in addr_len. */ if (uaddr->sa_family == AF_INET) { if (ipv6_only_sock(sk)) return -EAFNOSUPPORT; return udp_pre_connect(sk, uaddr, addr_len); } if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } /** * udp6_hwcsum_outgoing - handle outgoing HW checksumming * @sk: socket we are sending on * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) * @saddr: source address * @daddr: destination address * @len: length of packet */ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int len) { unsigned int offset; struct udphdr *uh = udp_hdr(skb); struct sk_buff *frags = skb_shinfo(skb)->frag_list; __wsum csum = 0; if (!frags) { /* Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0); } else { /* * HW-checksum won't work as there are two or more * fragments on the socket so that all csums of sk_buffs * should be together */ offset = skb_transport_offset(skb); skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); csum = skb->csum; skb->ip_summed = CHECKSUM_NONE; do { csum = csum_add(csum, frags->csum); } while ((frags = frags->next)); uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } } /* * Sending */ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, struct inet_cork *cork) { struct sock *sk = skb->sk; struct udphdr *uh; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; int offset = skb_transport_offset(skb); int len = skb->len - offset; int datalen = len - sizeof(*uh); /* * Create a UDP header */ uh = udp_hdr(skb); uh->source = fl6->fl6_sport; uh->dest = fl6->fl6_dport; uh->len = htons(len); uh->check = 0; if (cork->gso_size) { const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); if (hlen + cork->gso_size > cork->fragsize) { kfree_skb(skb); return -EINVAL; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } if (udp_get_no_check6_tx(sk)) { kfree_skb(skb); return -EINVAL; } if (is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } if (datalen > cork->gso_size) { skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, cork->gso_size); } goto csum_partial; } if (is_udplite) csum = udplite_csum(skb); else if (udp_get_no_check6_tx(sk)) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ csum_partial: udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len); goto send; } else csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: err = ip6_send_skb(skb); if (err) { if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk)) { UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; } } else { UDP6_INC_STATS(sock_net(sk), UDP_MIB_OUTDATAGRAMS, is_udplite); } return err; } static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udp_sock *up = udp_sk(sk); int err = 0; if (up->pending == AF_INET) return udp_push_pending_frames(sk); skb = ip6_finish_skb(sk); if (!skb) goto out; err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6, &inet_sk(sk)->cork.base); out: up->len = 0; WRITE_ONCE(up->pending, 0); return err; } int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; struct inet_cork_full cork; struct flowi6 *fl6 = &cork.fl.u.ip6; struct dst_entry *dst; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ if (sin6) { if (addr_len < offsetof(struct sockaddr, sa_data)) return -EINVAL; switch (sin6->sin6_family) { case AF_INET6: if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; daddr = &sin6->sin6_addr; if (ipv6_addr_any(daddr) && ipv6_addr_v4mapped(&np->saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), daddr); break; case AF_INET: goto do_udp_sendmsg; case AF_UNSPEC: msg->msg_name = sin6 = NULL; msg->msg_namelen = addr_len = 0; daddr = NULL; break; default: return -EINVAL; } } else if (!READ_ONCE(up->pending)) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } else daddr = NULL; if (daddr) { if (ipv6_addr_v4mapped(daddr)) { struct sockaddr_in sin; sin.sin_family = AF_INET; sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport; sin.sin_addr.s_addr = daddr->s6_addr32[3]; msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: err = ipv6_only_sock(sk) ? -ENETUNREACH : udp_sendmsg(sk, msg, len); msg->msg_name = sin6; msg->msg_namelen = addr_len; return err; } } /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; if (READ_ONCE(up->pending)) { if (READ_ONCE(up->pending) == AF_INET) return udp_sendmsg(sk, msg, len); /* * There are pending frames. * The socket lock must be held while it's corked. */ lock_sock(sk); if (likely(up->pending)) { if (unlikely(up->pending != AF_INET6)) { release_sock(sk); return -EAFNOSUPPORT; } dst = NULL; goto do_append_data; } release_sock(sk); } ulen += sizeof(struct udphdr); memset(fl6, 0, sizeof(*fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; fl6->fl6_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (inet6_test_bit(SNDFLOW, sk)) { fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6->flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; fl6->fl6_dport = inet->inet_dport; daddr = &sk->sk_v6_daddr; fl6->flowlabel = np->flow_label; connected = true; } if (!fl6->flowi6_oif) fl6->flowi6_oif = READ_ONCE(sk->sk_bound_dev_if); if (!fl6->flowi6_oif) fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; fl6->flowi6_uid = sk->sk_uid; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); if (err > 0) { err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6, &ipc6); connected = false; } if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); ipc6.opt = opt; fl6->flowi6_proto = sk->sk_protocol; fl6->flowi6_mark = ipc6.sockc.mark; fl6->daddr = *daddr; if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr)) fl6->saddr = np->saddr; fl6->fl6_sport = inet->inet_sport; if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, &addr_len, &fl6->saddr); if (err) goto out_no_dst; if (sin6) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { /* BPF program rewrote IPv6-only by IPv4-mapped * IPv6. It's currently unsupported. */ err = -ENOTSUPP; goto out_no_dst; } if (sin6->sin6_port == 0) { /* BPF program set invalid port. Reject it. */ err = -EINVAL; goto out_no_dst; } fl6->fl6_dport = sin6->sin6_port; fl6->daddr = sin6->sin6_addr; } } if (ipv6_addr_any(&fl6->daddr)) fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ final_p = fl6_update_dst(fl6, opt, &final); if (final_p) connected = false; if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) { fl6->flowi6_oif = READ_ONCE(np->mcast_oif); connected = false; } else if (!fl6->flowi6_oif) fl6->flowi6_oif = READ_ONCE(np->ucast_oif); security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel); dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, dst_rt6_info(dst), msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_v6_send_skb(skb, fl6, &cork.base); /* ip6_make_skb steals dst reference */ goto out_no_dst; } lock_sock(sk); if (unlikely(up->pending)) { /* The socket is already corked while preparing it. */ /* ... which is an evident application bug. --ANK */ release_sock(sk); net_dbg_ratelimited("udp cork app bug 2\n"); err = -EINVAL; goto out; } WRITE_ONCE(up->pending, AF_INET6); do_append_data: if (ipc6.dontfrag < 0) ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk); up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, fl6, dst_rt6_info(dst), corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) err = udp_v6_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) WRITE_ONCE(up->pending, 0); if (err > 0) err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0; release_sock(sk); out: dst_release(dst); out_no_dst: fl6_sock_release(flowlabel); txopt_put(opt_to_free); if (!err) return len; /* * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting * ENOBUFS might not be good (it's not tunable per se), but otherwise * we don't have a good statistic (IpOutDiscards but it can be too many * things). We could add another new stat but at least for now that * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } EXPORT_SYMBOL(udpv6_sendmsg); static void udpv6_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) return; lock_sock(sk); if (up->pending && !udp_test_bit(CORK, sk)) udp_v6_push_pending_frames(sk); release_sock(sk); } void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); /* protects from races with udp_abort() */ sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); if (static_branch_unlikely(&udpv6_encap_needed_key)) { if (up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } if (udp_test_bit(ENCAP_ENABLED, sk)) { static_branch_dec(&udpv6_encap_needed_key); udp_encap_disable(); } } } /* * Socket option code for UDP */ int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_v6_push_pending_frames); return ipv6_setsockopt(sk, level, optname, optval, optlen); } int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_getsockopt(sk, level, optname, optval, optlen); return ipv6_getsockopt(sk, level, optname, optval, optlen); } /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS int udp6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { int bucket = ((struct udp_iter_state *)seq->private)->bucket; const struct inet_sock *inet = inet_sk((const struct sock *)v); __u16 srcp = ntohs(inet->inet_sport); __u16 destp = ntohs(inet->inet_dport); __ip6_dgram_sock_seq_show(seq, v, srcp, destp, udp_rqueue_get(v), bucket); } return 0; } const struct seq_operations udp6_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, .stop = udp_seq_stop, .show = udp6_seq_show, }; EXPORT_SYMBOL(udp6_seq_ops); static struct udp_seq_afinfo udp6_seq_afinfo = { .family = AF_INET6, .udp_table = NULL, }; int __net_init udp6_proc_init(struct net *net) { if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops, sizeof(struct udp_iter_state), &udp6_seq_afinfo)) return -ENOMEM; return 0; } void udp6_proc_exit(struct net *net) { remove_proc_entry("udp6", net->proc_net); } #endif /* CONFIG_PROC_FS */ /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { .name = "UDPv6", .owner = THIS_MODULE, .close = udp_lib_close, .pre_connect = udpv6_pre_connect, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udpv6_init_sock, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, .splice_eof = udpv6_splice_eof, .release_cb = ip6_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif .memory_allocated = &udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6), .h.udp_table = NULL, .diag_destroy = udp_abort, }; static struct inet_protosw udpv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }; int __init udpv6_init(void) { int ret; net_hotdata.udpv6_protocol = (struct inet6_protocol) { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); if (ret) goto out; ret = inet6_register_protosw(&udpv6_protosw); if (ret) goto out_udpv6_protocol; out: return ret; out_udpv6_protocol: inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); } |
| 65 21 310 204 317 317 316 317 6 20 409 397 18 12 16 7 17 11 11 11 5 5 5 13 13 6 7 6 13 13 13 13 12 1 1 1 13 5 12 10 9 10 3 287 290 11 13 13 409 407 402 401 18 8 5 18 250 250 248 65 2 248 201 48 303 140 161 258 304 51 259 259 146 259 259 146 9 250 247 250 250 250 259 303 303 141 162 265 37 301 265 37 304 302 54 249 236 14 304 416 365 66 393 393 393 392 391 392 391 314 313 310 315 138 12 137 154 36 3 154 322 39 323 105 46 91 96 90 76 105 83 168 14 153 154 154 6 6 102 69 27 151 110 106 122 92 99 105 308 308 32 304 304 304 87 87 64 85 304 315 157 235 314 82 298 283 315 284 284 284 167 167 165 2 165 2 315 311 271 112 289 96 247 175 59 171 150 302 247 209 37 169 186 58 58 58 389 369 10 2 60 6 54 21 2 2 21 37 32 18 18 32 32 32 301 302 219 179 302 301 2 2 2 2 2 1 2 343 343 32 1 200 47 33 184 187 383 385 65 22 386 75 358 235 180 97 39 70 340 384 65 384 385 363 18 17 197 53 386 360 385 360 26 389 245 184 23 244 33 318 128 386 295 294 386 294 219 165 386 236 311 32 285 17 17 2 2 302 386 385 293 380 58 386 21 385 293 293 294 293 293 294 294 293 294 293 294 294 293 294 294 294 5 292 1 139 155 291 292 1 1 1 1 1 1 1 1 1 1 294 287 39 293 294 294 294 294 293 294 278 15 294 294 18 18 18 14 4 18 18 18 18 18 18 18 18 18 12 12 12 12 12 370 1 371 4 368 367 369 368 319 138 1 369 224 144 145 131 53 369 367 320 319 317 1 317 1 317 33 33 33 122 33 33 9 26 26 9 8 26 26 26 33 387 229 149 127 128 108 28 127 28 64 46 5 9 2 18 9 128 81 60 117 128 120 128 124 7 84 59 58 395 389 75 20 19 1 1 106 106 105 106 75 397 212 243 23 79 79 75 27 75 143 152 151 152 152 152 151 249 250 395 101 55 55 55 55 96 96 55 52 53 10 51 9 53 96 96 96 96 96 67 67 67 67 16 67 66 64 3 85 64 1 20 20 20 3 20 20 20 20 20 20 497 153 419 417 50 51 417 1 50 50 50 50 389 365 362 363 212 258 257 216 51 397 397 396 397 366 106 106 153 312 152 311 305 149 397 85 85 85 85 85 85 20 65 65 418 419 378 49 38 67 46 46 1 323 322 361 75 389 19 162 289 2 319 85 318 397 355 56 319 37 46 396 164 19 163 163 163 22 140 137 138 8 1 130 138 138 137 169 155 28 168 2 169 155 28 163 5 11 160 20 5 6 129 64 64 165 4 4 6 6 11 6 1 6 2 2 1 4 4 4 3 4 5 1 8 8 8 14 14 14 2 2 10 10 1 9 11 4 7 9 1 8 12 13 1 12 7 2 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 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 | // 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 lists (sbi->s_mb_largest_free_orders) * * Locking: sbi->s_mb_largest_free_orders_locks(array of rw locks) * * This is an array of lists where the index in the array represents the * largest free order in the buddy bitmap of the participating group infos of * that list. So, there are exactly MB_NUM_ORDERS(sb) (which means total * number of buddy bitmap orders possible) number of lists. Group-infos are * placed in appropriate lists. * * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * * This is an array of lists where in the i-th list 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 list for completely empty groups * so we only have MB_NUM_ORDERS(sb) lists. * * 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_linear_limit * * 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_linear_limit" * 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 bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr); 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_order; if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) return; new_order = mb_avg_fragment_size_order(sb, grp->bb_free / grp->bb_fragments); if (new_order == grp->bb_avg_fragment_size_order) return; if (grp->bb_avg_fragment_size_order != -1) { write_lock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); list_del(&grp->bb_avg_fragment_size_node); write_unlock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); } grp->bb_avg_fragment_size_order = new_order; write_lock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); list_add_tail(&grp->bb_avg_fragment_size_node, &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); write_unlock(&sbi->s_mb_avg_fragment_size_locks[ grp->bb_avg_fragment_size_order]); } /* * Choose next group by traversing largest_free_order lists. Updates *new_cr if * cr level needs an update. */ static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *iter; int i; if (ac->ac_status == AC_STATUS_FOUND) return; if (unlikely(sbi->s_mb_stats && ac->ac_flags & EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED)) atomic_inc(&sbi->s_bal_p2_aligned_bad_suggestions); for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { if (list_empty(&sbi->s_mb_largest_free_orders[i])) continue; read_lock(&sbi->s_mb_largest_free_orders_locks[i]); if (list_empty(&sbi->s_mb_largest_free_orders[i])) { read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); continue; } list_for_each_entry(iter, &sbi->s_mb_largest_free_orders[i], bb_largest_free_order_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[CR_POWER2_ALIGNED]); if (likely(ext4_mb_good_group(ac, iter->bb_group, CR_POWER2_ALIGNED))) { *group = iter->bb_group; ac->ac_flags |= EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED; read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); return; } } read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); } /* Increment cr and search again if no group is found */ *new_cr = CR_GOAL_LEN_FAST; } /* * Find a suitable group of given order from the average fragments list. */ static struct ext4_group_info * ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int order) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct list_head *frag_list = &sbi->s_mb_avg_fragment_size[order]; rwlock_t *frag_list_lock = &sbi->s_mb_avg_fragment_size_locks[order]; struct ext4_group_info *grp = NULL, *iter; enum criteria cr = ac->ac_criteria; if (list_empty(frag_list)) return NULL; read_lock(frag_list_lock); if (list_empty(frag_list)) { read_unlock(frag_list_lock); return NULL; } list_for_each_entry(iter, frag_list, bb_avg_fragment_size_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[cr]); if (likely(ext4_mb_good_group(ac, iter->bb_group, cr))) { grp = iter; break; } } read_unlock(frag_list_lock); return grp; } /* * Choose next group by traversing average fragment size list of suitable * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = NULL; int i; if (unlikely(ac->ac_flags & EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_goal_fast_bad_suggestions); } for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); i < MB_NUM_ORDERS(ac->ac_sb); i++) { grp = ext4_mb_find_good_group_avg_frag_lists(ac, i); if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED; return; } } /* * 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) *new_cr = CR_BEST_AVAIL_LEN; else *new_cr = CR_GOAL_LEN_SLOW; } /* * 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 void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = NULL; int i, order, min_order; unsigned long num_stripe_clusters = 0; if (unlikely(ac->ac_flags & EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_best_avail_bad_suggestions); } /* * 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); 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); grp = ext4_mb_find_good_group_avg_frag_lists(ac, frag_order); if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED; return; } } /* 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; *new_cr = CR_GOAL_LEN_SLOW; } 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; } /* * Return next linear group for allocation. */ static ext4_group_t 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. */ return group + 1 >= ngroups ? 0 : group + 1; } /* * ext4_mb_choose_next_group: choose next group for allocation. * * @ac Allocation Context * @new_cr This is an output parameter. If the there is no good group * available at current CR level, this field is updated to indicate * the new cr level that should be used. * @group This is an input / output parameter. As an input it indicates the * next group that the allocator intends to use for allocation. As * output, this field indicates the next group that should be used as * determined by the optimization functions. * @ngroups Total number of groups */ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups) { *new_cr = ac->ac_criteria; if (!should_optimize_scan(ac)) { *group = next_linear_group(*group, ngroups); return; } /* * 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 (ac->ac_groups_linear_remaining) { *group = next_linear_group(*group, ngroups); ac->ac_groups_linear_remaining--; return; } if (*new_cr == CR_POWER2_ALIGNED) { ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group); } else if (*new_cr == CR_GOAL_LEN_FAST) { ext4_mb_choose_next_group_goal_fast(ac, new_cr, group); } else if (*new_cr == CR_BEST_AVAIL_LEN) { ext4_mb_choose_next_group_best_avail(ac, new_cr, group); } else { /* * 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); } } /* * 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 i; for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) if (grp->bb_counters[i] > 0) break; /* No need to move between order lists? */ if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || i == grp->bb_largest_free_order) { grp->bb_largest_free_order = i; return; } if (grp->bb_largest_free_order >= 0) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_del_init(&grp->bb_largest_free_order_node); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } grp->bb_largest_free_order = i; if (grp->bb_largest_free_order >= 0 && grp->bb_free) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_add_tail(&grp->bb_largest_free_order_node, &sbi->s_mb_largest_free_orders[grp->bb_largest_free_order]); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } } 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) { spin_lock(&sbi->s_md_lock); sbi->s_mb_last_group = ac->ac_f_ex.fe_group; sbi->s_mb_last_start = ac->ac_f_ex.fe_start; spin_unlock(&sbi->s_md_lock); } /* * 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_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_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; } } /* * 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; } /* * 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 noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; enum criteria new_cr, cr = CR_GOAL_LEN_FAST; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); ngroups = ext4_get_groups_count(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; 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) { /* TBD: may be hot point */ spin_lock(&sbi->s_md_lock); ac->ac_g_ex.fe_group = sbi->s_mb_last_group; ac->ac_g_ex.fe_start = sbi->s_mb_last_start; spin_unlock(&sbi->s_md_lock); } /* * 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. */ if (ac->ac_2order) cr = CR_POWER2_ALIGNED; repeat: for (; cr < EXT4_MB_NUM_CRS && ac->ac_status == AC_STATUS_CONTINUE; cr++) { ac->ac_criteria = cr; /* * searching for the right group start * from the goal value specified */ group = ac->ac_g_ex.fe_group; ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; nr = 0; for (i = 0, new_cr = cr; i < ngroups; i++, ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { int ret = 0; cond_resched(); if (new_cr != cr) { cr = new_cr; goto repeat; } /* * 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 */ if ((prefetch_grp == group) && (ext4_mb_cr_expensive(cr) || prefetch_ios < sbi->s_mb_prefetch_limit)) { nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { nr = 1 << sbi->s_log_groups_per_flex; nr -= group & (nr - 1); nr = min(nr, sbi->s_mb_prefetch); } prefetch_grp = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); } /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!first_err) first_err = ret; continue; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) goto out; ext4_lock_group(sb, group); /* * We need to check again after locking the * block group */ ret = ext4_mb_good_group(ac, group, cr); if (ret == 0) { ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); continue; } ac->ac_groups_scanned++; if (cr == CR_POWER2_ALIGNED) ext4_mb_simple_scan_group(ac, &e4b); else { bool is_stripe_aligned = sbi->s_stripe && !(ac->ac_g_ex.fe_len % EXT4_B2C(sbi, sbi->s_stripe)); if ((cr == CR_GOAL_LEN_FAST || cr == CR_BEST_AVAIL_LEN) && is_stripe_aligned) ext4_mb_scan_aligned(ac, &e4b); if (ac->ac_status == AC_STATUS_CONTINUE) ext4_mb_complex_scan_group(ac, &e4b); } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); if (ac->ac_status != AC_STATUS_CONTINUE) break; } /* Processed all groups and haven't found blocks */ if (sbi->s_mb_stats && i == ngroups) atomic64_inc(&sbi->s_bal_cX_failed[cr]); if (i == ngroups && ac->ac_criteria == CR_BEST_AVAIL_LEN) /* 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 (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) { /* * 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; cr = 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]); out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = 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, cr, err); if (nr) ext4_mb_prefetch_fini(sb, prefetch_grp, 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); struct sg { struct ext4_group_info info; ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; } sg; 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.info.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.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); seq_puts(seq, " ]"); if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) seq_puts(seq, " Block bitmap corrupted!"); seq_puts(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])); seq_printf(seq, "\t\tbad_suggestions: %u\n", atomic_read(&sbi->s_bal_p2_aligned_bad_suggestions)); /* 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])); seq_printf(seq, "\t\tbad_suggestions: %u\n", atomic_read(&sbi->s_bal_goal_fast_bad_suggestions)); /* 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])); seq_printf(seq, "\t\tbad_suggestions: %u\n", atomic_read(&sbi->s_bal_best_avail_bad_suggestions)); /* 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\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; 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; read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], bb_avg_fragment_size_node) count++; read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); 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; read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); 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; INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); 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); } 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 list_head), GFP_KERNEL); if (!sbi->s_mb_avg_fragment_size) { ret = -ENOMEM; goto out; } sbi->s_mb_avg_fragment_size_locks = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), GFP_KERNEL); if (!sbi->s_mb_avg_fragment_size_locks) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) { INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); if (!sbi->s_mb_largest_free_orders) { ret = -ENOMEM; goto out; } sbi->s_mb_largest_free_orders_locks = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), GFP_KERNEL); if (!sbi->s_mb_largest_free_orders_locks) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) { INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); } spin_lock_init(&sbi->s_md_lock); 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_B2C(sbi, sbi->s_stripe)); } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { ret = -ENOMEM; goto out; } 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: kfree(sbi->s_mb_avg_fragment_size); kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); 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(); } kfree(sbi->s_mb_avg_fragment_size); kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); 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); } 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); spin_lock(&EXT4_SB(sb)->s_md_lock); EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count; spin_unlock(&EXT4_SB(sb)->s_md_lock); 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. * If the volume is mounted with -o discard, online discard * is supported and the free blocks will be trimmed online. */ if (!test_opt(sb, DISCARD)) 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_unbound_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_forced_shutdown(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_forced_shutdown(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, ", ac->ac_pa ? "yes" : "no"); 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, ret ? "yes" : "no"); 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 void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi, struct ext4_free_data *entry, struct ext4_free_data *new_entry, struct rb_root *entry_rb_root) { if ((entry->efd_tid != new_entry->efd_tid) || (entry->efd_group != new_entry->efd_group)) return; if (entry->efd_start_cluster + entry->efd_count == new_entry->efd_start_cluster) { new_entry->efd_start_cluster = entry->efd_start_cluster; new_entry->efd_count += entry->efd_count; } else if (new_entry->efd_start_cluster + new_entry->efd_count == entry->efd_start_cluster) { new_entry->efd_count += entry->efd_count; } else return; spin_lock(&sbi->s_md_lock); list_del(&entry->efd_list); spin_unlock(&sbi->s_md_lock); rb_erase(&entry->efd_node, entry_rb_root); kmem_cache_free(ext4_free_data_cachep, entry); } 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; 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_node **n = &db->bb_free_root.rb_node, *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; } } rb_link_node(new_node, parent, n); rb_insert_color(new_node, &db->bb_free_root); /* Now try to see the extent can be merged to left and right */ node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } spin_lock(&sbi->s_md_lock); list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]); sbi->s_mb_free_pending += clusters; 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); } else 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(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 start, ext4_grpblk_t end, ext4_mballoc_query_range_fn formatter, void *priv) { void *bitmap; ext4_grpblk_t 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, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; 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 |
| 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "nop.h" struct io_nop { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct file *file; int result; }; int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { unsigned int flags; struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); flags = READ_ONCE(sqe->nop_flags); if (flags & ~IORING_NOP_INJECT_RESULT) return -EINVAL; if (flags & IORING_NOP_INJECT_RESULT) nop->result = READ_ONCE(sqe->len); else nop->result = 0; return 0; } int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); if (nop->result < 0) req_set_fail(req); io_req_set_res(req, nop->result, 0); return IOU_OK; } |
| 7310 7077 2368 37 1810 1596 24 6121 1133 66 2 1136 764 59 2002 4371 6231 459 4295 1918 2504 1366 3366 3363 263 542 521 521 520 521 382 154 517 518 1162 73 1373 1372 156 156 156 155 385 262 343 34 2 801 800 36 1357 2396 320 1470 3308 1515 200 718 93 722 1 736 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* Are there any inode/mount/sb objects watched with priority prio or above? */ static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, int prio) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return false; return atomic_long_read(&sbinfo->watched_objects[prio]); } /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { return fsnotify_sb_has_priority_watchers(sb, 0); } /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path; /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; path = &file->f_path; /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ if (mask & ALL_FSNOTIFY_PERM_EVENTS && !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, FSNOTIFY_PRIO_CONTENT)) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { __u32 fsnotify_mask = FS_ACCESS_PERM; /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection * must not be held. */ lockdep_assert_once(file_write_not_started(file)); if (!(perm_mask & MAY_READ)) return 0; return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_file_perm - permission hook before file access */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return fsnotify_file_area_perm(file, perm_mask, NULL, 0); } /* * fsnotify_open_perm - permission hook before file open */ static inline int fsnotify_open_perm(struct file *file) { int ret; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } return fsnotify_file(file, FS_OPEN_PERM); } #else static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; } static inline int fsnotify_open_perm(struct file *file) { return 0; } #endif /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 20 130 6 6 1 37 106 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM nilfs2 #if !defined(_TRACE_NILFS2_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NILFS2_H #include <linux/tracepoint.h> struct nilfs_sc_info; #define show_collection_stage(type) \ __print_symbolic(type, \ { NILFS_ST_INIT, "ST_INIT" }, \ { NILFS_ST_GC, "ST_GC" }, \ { NILFS_ST_FILE, "ST_FILE" }, \ { NILFS_ST_IFILE, "ST_IFILE" }, \ { NILFS_ST_CPFILE, "ST_CPFILE" }, \ { NILFS_ST_SUFILE, "ST_SUFILE" }, \ { NILFS_ST_DAT, "ST_DAT" }, \ { NILFS_ST_SR, "ST_SR" }, \ { NILFS_ST_DSYNC, "ST_DSYNC" }, \ { NILFS_ST_DONE, "ST_DONE"}) TRACE_EVENT(nilfs2_collection_stage_transition, TP_PROTO(struct nilfs_sc_info *sci), TP_ARGS(sci), TP_STRUCT__entry( __field(void *, sci) __field(int, stage) ), TP_fast_assign( __entry->sci = sci; __entry->stage = sci->sc_stage.scnt; ), TP_printk("sci = %p stage = %s", __entry->sci, show_collection_stage(__entry->stage)) ); #ifndef TRACE_HEADER_MULTI_READ enum nilfs2_transaction_transition_state { TRACE_NILFS2_TRANSACTION_BEGIN, TRACE_NILFS2_TRANSACTION_COMMIT, TRACE_NILFS2_TRANSACTION_ABORT, TRACE_NILFS2_TRANSACTION_TRYLOCK, TRACE_NILFS2_TRANSACTION_LOCK, TRACE_NILFS2_TRANSACTION_UNLOCK, }; #endif #define show_transaction_state(type) \ __print_symbolic(type, \ { TRACE_NILFS2_TRANSACTION_BEGIN, "BEGIN" }, \ { TRACE_NILFS2_TRANSACTION_COMMIT, "COMMIT" }, \ { TRACE_NILFS2_TRANSACTION_ABORT, "ABORT" }, \ { TRACE_NILFS2_TRANSACTION_TRYLOCK, "TRYLOCK" }, \ { TRACE_NILFS2_TRANSACTION_LOCK, "LOCK" }, \ { TRACE_NILFS2_TRANSACTION_UNLOCK, "UNLOCK" }) TRACE_EVENT(nilfs2_transaction_transition, TP_PROTO(struct super_block *sb, struct nilfs_transaction_info *ti, int count, unsigned int flags, enum nilfs2_transaction_transition_state state), TP_ARGS(sb, ti, count, flags, state), TP_STRUCT__entry( __field(void *, sb) __field(void *, ti) __field(int, count) __field(unsigned int, flags) __field(int, state) ), TP_fast_assign( __entry->sb = sb; __entry->ti = ti; __entry->count = count; __entry->flags = flags; __entry->state = state; ), TP_printk("sb = %p ti = %p count = %d flags = %x state = %s", __entry->sb, __entry->ti, __entry->count, __entry->flags, show_transaction_state(__entry->state)) ); TRACE_EVENT(nilfs2_segment_usage_check, TP_PROTO(struct inode *sufile, __u64 segnum, unsigned long cnt), TP_ARGS(sufile, segnum, cnt), TP_STRUCT__entry( __field(struct inode *, sufile) __field(__u64, segnum) __field(unsigned long, cnt) ), TP_fast_assign( __entry->sufile = sufile; __entry->segnum = segnum; __entry->cnt = cnt; ), TP_printk("sufile = %p segnum = %llu cnt = %lu", __entry->sufile, __entry->segnum, __entry->cnt) ); TRACE_EVENT(nilfs2_segment_usage_allocated, TP_PROTO(struct inode *sufile, __u64 segnum), TP_ARGS(sufile, segnum), TP_STRUCT__entry( __field(struct inode *, sufile) __field(__u64, segnum) ), TP_fast_assign( __entry->sufile = sufile; __entry->segnum = segnum; ), TP_printk("sufile = %p segnum = %llu", __entry->sufile, __entry->segnum) ); TRACE_EVENT(nilfs2_segment_usage_freed, TP_PROTO(struct inode *sufile, __u64 segnum), TP_ARGS(sufile, segnum), TP_STRUCT__entry( __field(struct inode *, sufile) __field(__u64, segnum) ), TP_fast_assign( __entry->sufile = sufile; __entry->segnum = segnum; ), TP_printk("sufile = %p segnum = %llu", __entry->sufile, __entry->segnum) ); TRACE_EVENT(nilfs2_mdt_insert_new_block, TP_PROTO(struct inode *inode, unsigned long ino, unsigned long block), TP_ARGS(inode, ino, block), TP_STRUCT__entry( __field(struct inode *, inode) __field(unsigned long, ino) __field(unsigned long, block) ), TP_fast_assign( __entry->inode = inode; __entry->ino = ino; __entry->block = block; ), TP_printk("inode = %p ino = %lu block = %lu", __entry->inode, __entry->ino, __entry->block) ); TRACE_EVENT(nilfs2_mdt_submit_block, TP_PROTO(struct inode *inode, unsigned long ino, unsigned long blkoff, enum req_op mode), TP_ARGS(inode, ino, blkoff, mode), TP_STRUCT__entry( __field(struct inode *, inode) __field(unsigned long, ino) __field(unsigned long, blkoff) /* * Use field_struct() to avoid is_signed_type() on the * bitwise type enum req_op. */ __field_struct(enum req_op, mode) ), TP_fast_assign( __entry->inode = inode; __entry->ino = ino; __entry->blkoff = blkoff; __entry->mode = mode; ), TP_printk("inode = %p ino = %lu blkoff = %lu mode = %x", __entry->inode, __entry->ino, __entry->blkoff, __entry->mode) ); #endif /* _TRACE_NILFS2_H */ /* This part must be outside protection */ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE nilfs2 #include <trace/define_trace.h> |
| 2454 2454 1 2452 2367 1 2367 859 859 860 955 4942 945 941 9 5 8 9 15 15 1502 469 11 465 11 1337 11 1338 61 57 1506 1506 158 6 93 117 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/xarray.h> /** * idr_alloc_u32() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @nextid: Pointer to an ID. * @max: The maximum ID to allocate (inclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @nextid and @max. * Note that @max is inclusive whereas the @end parameter to idr_alloc() * is exclusive. The new ID is assigned to @nextid before the pointer * is inserted into the IDR, so if @nextid points into the object pointed * to by @ptr, a concurrent lookup will not find an uninitialised ID. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. If an error occurred, * @nextid is unchanged. */ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, unsigned long max, gfp_t gfp) { struct radix_tree_iter iter; void __rcu **slot; unsigned int base = idr->idr_base; unsigned int id = *nextid; if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base); if (IS_ERR(slot)) return PTR_ERR(slot); *nextid = iter.index + base; /* there is a memory barrier inside radix_tree_iter_replace() */ radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); return 0; } EXPORT_SYMBOL_GPL(idr_alloc_u32); /** * idr_alloc() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = start; int ret; if (WARN_ON_ONCE(start < 0)) return -EINVAL; ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp); if (ret) return ret; return id; } EXPORT_SYMBOL_GPL(idr_alloc); /** * idr_alloc_cyclic() - Allocate an ID cyclically. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * The search for an unused ID will start at the last ID allocated and will * wrap around to @start if no free IDs are found before reaching @end. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = idr->idr_next; int err, max = end > 0 ? end - 1 : INT_MAX; if ((int)id < start) id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); if ((err == -ENOSPC) && (id > start)) { id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); } if (err) return err; idr->idr_next = id + 1; return id; } EXPORT_SYMBOL(idr_alloc_cyclic); /** * idr_remove() - Remove an ID from the IDR. * @idr: IDR handle. * @id: Pointer ID. * * Removes this ID from the IDR. If the ID was not previously in the IDR, * this function returns %NULL. * * Since this function modifies the IDR, the caller should provide their * own locking to ensure that concurrent modification of the same IDR is * not possible. * * Return: The pointer formerly associated with this ID. */ void *idr_remove(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL); } EXPORT_SYMBOL_GPL(idr_remove); /** * idr_find() - Return pointer for given ID. * @idr: IDR handle. * @id: Pointer ID. * * Looks up the pointer associated with this ID. A %NULL pointer may * indicate that @id is not allocated or that the %NULL pointer was * associated with this ID. * * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. * * Return: The pointer associated with this ID. */ void *idr_find(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base); } EXPORT_SYMBOL_GPL(idr_find); /** * idr_for_each() - Iterate through all stored pointers. * @idr: IDR handle. * @fn: Function to be called for each pointer. * @data: Data passed to callback function. * * The callback function will be called for each entry in @idr, passing * the ID, the entry and @data. * * If @fn returns anything other than %0, the iteration stops and that * value is returned from this function. * * idr_for_each() can be called concurrently with idr_alloc() and * idr_remove() if protected by RCU. Newly added entries may not be * seen and deleted entries may be seen, but adding and removing entries * will not cause other entries to be skipped, nor spurious ones to be seen. */ int idr_for_each(const struct idr *idr, int (*fn)(int id, void *p, void *data), void *data) { struct radix_tree_iter iter; void __rcu **slot; int base = idr->idr_base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; unsigned long id = iter.index + base; if (WARN_ON_ONCE(id > INT_MAX)) break; ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } return 0; } EXPORT_SYMBOL(idr_for_each); /** * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { entry = rcu_dereference_raw(*slot); if (!entry) continue; if (!xa_is_internal(entry)) break; if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) break; slot = radix_tree_iter_retry(&iter); } if (!slot) return NULL; *nextid = iter.index + base; return entry; } EXPORT_SYMBOL(idr_get_next_ul); /** * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next(struct idr *idr, int *nextid) { unsigned long id = *nextid; void *entry = idr_get_next_ul(idr, &id); if (WARN_ON_ONCE(id > INT_MAX)) return NULL; *nextid = id; return entry; } EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. * @idr: IDR handle. * @ptr: New pointer to associate with the ID. * @id: ID to change. * * Replace the pointer registered with an ID and return the old value. * This function can be called under the RCU read lock concurrently with * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * * Returns: the old value on success. %-ENOENT indicates that @id was not * found. %-EINVAL indicates that @ptr was not valid. */ void *idr_replace(struct idr *idr, void *ptr, unsigned long id) { struct radix_tree_node *node; void __rcu **slot = NULL; void *entry; id -= idr->idr_base; entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); __radix_tree_replace(&idr->idr_rt, node, slot, ptr); return entry; } EXPORT_SYMBOL(idr_replace); /** * DOC: IDA description * * The IDA is an ID allocator which does not provide the ability to * associate an ID with a pointer. As such, it only needs to store one * bit per ID, and so is more space efficient than an IDR. To use an IDA, * define it using DEFINE_IDA() (or embed a &struct ida in a data structure, * then initialise it using ida_init()). To allocate a new ID, call * ida_alloc(), ida_alloc_min(), ida_alloc_max() or ida_alloc_range(). * To free an ID, call ida_free(). * * ida_destroy() can be used to dispose of an IDA without needing to * free the individual IDs in it. You can use ida_is_empty() to find * out whether the IDA has any IDs currently allocated. * * The IDA handles its own locking. It is safe to call any of the IDA * functions without synchronisation in your code. * * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward * limitation, it should be quite straightforward to raise the maximum. */ /* * Developer's notes: * * The IDA uses the functionality provided by the XArray to store bitmaps in * each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap * have been set. * * I considered telling the XArray that each slot is an order-10 node * and indexing by bit number, but the XArray can't allow a single multi-index * entry in the head, which would significantly increase memory consumption * for the IDA. So instead we divide the index by the number of bits in the * leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given * leaf, instead of allocating a 128-byte bitmap, we store the bits * as a value entry. Value entries never have the XA_FREE_MARK cleared * because we can always convert them into a bitmap entry. * * It would be possible to optimise further; once we've run out of a * single 128-byte bitmap, we currently switch to a 576-byte node, put * the 128-byte bitmap in the first entry and then start allocating extra * 128-byte entries. We could instead use the 512 bytes of the node's * data as a bitmap before moving to that scheme. I do not believe this * is a worthwhile optimisation; Rasmus Villemoes surveyed the current * users of the IDA and almost none of them use more than 1024 entries. * Those that do use more than the 8192 IDs that the 512 bytes would * provide. * * The IDA always uses a lock to alloc/free. If we add a 'test_bit' * equivalent, it will still need locking. Going to RCU lookup would require * using RCU to free bitmaps, and that's not trivial without embedding an * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte * bitmap, which is excessive. */ /** * ida_alloc_range() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and @max, inclusive. The allocated ID will * not exceed %INT_MAX, even if @max is larger. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, gfp_t gfp) { XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS); unsigned bit = min % IDA_BITMAP_BITS; unsigned long flags; struct ida_bitmap *bitmap, *alloc = NULL; if ((int)min < 0) return -ENOSPC; if ((int)max < 0) max = INT_MAX; retry: xas_lock_irqsave(&xas, flags); next: bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK); if (xas.xa_index > min / IDA_BITMAP_BITS) bit = 0; if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (xa_is_value(bitmap)) { unsigned long tmp = xa_to_value(bitmap); if (bit < BITS_PER_XA_VALUE) { bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit < BITS_PER_XA_VALUE) { tmp |= 1UL << bit; xas_store(&xas, xa_mk_value(tmp)); goto out; } } bitmap = alloc; if (!bitmap) bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); if (!bitmap) goto alloc; bitmap->bitmap[0] = tmp; xas_store(&xas, bitmap); if (xas_error(&xas)) { bitmap->bitmap[0] = 0; goto out; } } if (bitmap) { bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit == IDA_BITMAP_BITS) goto next; __set_bit(bit, bitmap->bitmap); if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) xas_clear_mark(&xas, XA_FREE_MARK); } else { if (bit < BITS_PER_XA_VALUE) { bitmap = xa_mk_value(1UL << bit); } else { bitmap = alloc; if (!bitmap) bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); if (!bitmap) goto alloc; __set_bit(bit, bitmap->bitmap); } xas_store(&xas, bitmap); } out: xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) { xas.xa_index = min / IDA_BITMAP_BITS; bit = min % IDA_BITMAP_BITS; goto retry; } if (bitmap != alloc) kfree(alloc); if (xas_error(&xas)) return xas_error(&xas); return xas.xa_index * IDA_BITMAP_BITS + bit; alloc: xas_unlock_irqrestore(&xas, flags); alloc = kzalloc(sizeof(*bitmap), gfp); if (!alloc) return -ENOMEM; xas_set(&xas, min / IDA_BITMAP_BITS); bit = min % IDA_BITMAP_BITS; goto retry; nospc: xas_unlock_irqrestore(&xas, flags); kfree(alloc); return -ENOSPC; } EXPORT_SYMBOL(ida_alloc_range); /** * ida_free() - Release an allocated ID. * @ida: IDA handle. * @id: Previously allocated ID. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_free(struct ida *ida, unsigned int id) { XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS); unsigned bit = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; unsigned long flags; if ((int)id < 0) return; xas_lock_irqsave(&xas, flags); bitmap = xas_load(&xas); if (xa_is_value(bitmap)) { unsigned long v = xa_to_value(bitmap); if (bit >= BITS_PER_XA_VALUE) goto err; if (!(v & (1UL << bit))) goto err; v &= ~(1UL << bit); if (!v) goto delete; xas_store(&xas, xa_mk_value(v)); } else { if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { kfree(bitmap); delete: xas_store(&xas, NULL); } } xas_unlock_irqrestore(&xas, flags); return; err: xas_unlock_irqrestore(&xas, flags); WARN(1, "ida_free called for id=%d which is not allocated.\n", id); } EXPORT_SYMBOL(ida_free); /** * ida_destroy() - Free all IDs. * @ida: IDA handle. * * Calling this function frees all IDs and releases all resources used * by an IDA. When this call returns, the IDA is empty and can be reused * or freed. If the IDA is already empty, there is no need to call this * function. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_destroy(struct ida *ida) { XA_STATE(xas, &ida->xa, 0); struct ida_bitmap *bitmap; unsigned long flags; xas_lock_irqsave(&xas, flags); xas_for_each(&xas, bitmap, ULONG_MAX) { if (!xa_is_value(bitmap)) kfree(bitmap); xas_store(&xas, NULL); } xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(ida_destroy); #ifndef __KERNEL__ extern void xa_dump_index(unsigned long index, unsigned int shift); #define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS) static void ida_dump_entry(void *entry, unsigned long index) { unsigned long i; if (!entry) return; if (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); unsigned int shift = node->shift + IDA_CHUNK_SHIFT + XA_CHUNK_SHIFT; xa_dump_index(index * IDA_BITMAP_BITS, shift); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) ida_dump_entry(node->slots[i], index | (i << node->shift)); } else if (xa_is_value(entry)) { xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG)); pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry); } else { struct ida_bitmap *bitmap = entry; xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT); pr_cont("bitmap: %p data", bitmap); for (i = 0; i < IDA_BITMAP_LONGS; i++) pr_cont(" %lx", bitmap->bitmap[i]); pr_cont("\n"); } } static void ida_dump(struct ida *ida) { struct xarray *xa = &ida->xa; pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head, xa->xa_flags >> ROOT_TAG_SHIFT); ida_dump_entry(xa->xa_head, 0); } #endif |
| 1 1 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic show_mem() implementation * * Copyright (C) 2008 Johannes Weiner <hannes@saeurebad.de> */ #include <linux/blkdev.h> #include <linux/cma.h> #include <linux/cpuset.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/swap.h> #include <linux/vmstat.h> #include "internal.h" #include "swap.h" atomic_long_t _totalram_pages __read_mostly; EXPORT_SYMBOL(_totalram_pages); unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; static inline void show_node(struct zone *zone) { if (IS_ENABLED(CONFIG_NUMA)) printk("Node %d ", zone_to_nid(zone)); } long si_mem_available(void) { long available; unsigned long pagecache; unsigned long wmark_low = 0; unsigned long reclaimable; struct zone *zone; for_each_zone(zone) wmark_low += low_wmark_pages(zone); /* * Estimate the amount of memory available for userspace allocations, * without causing swapping or OOM. */ available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages; /* * Not all the page cache can be freed, otherwise the system will * start swapping or thrashing. Assume at least half of the page * cache, or the low watermark worth of cache, needs to stay. */ pagecache = global_node_page_state(NR_ACTIVE_FILE) + global_node_page_state(NR_INACTIVE_FILE); pagecache -= min(pagecache / 2, wmark_low); available += pagecache; /* * Part of the reclaimable slab and other kernel memory consists of * items that are in use, and cannot be freed. Cap this estimate at the * low watermark. */ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); reclaimable -= min(reclaimable / 2, wmark_low); available += reclaimable; if (available < 0) available = 0; return available; } EXPORT_SYMBOL_GPL(si_mem_available); void si_meminfo(struct sysinfo *val) { val->totalram = totalram_pages(); val->sharedram = global_node_page_state(NR_SHMEM); val->freeram = global_zone_page_state(NR_FREE_PAGES); val->bufferram = nr_blockdev_pages(); val->totalhigh = totalhigh_pages(); val->freehigh = nr_free_highpages(); val->mem_unit = PAGE_SIZE; } EXPORT_SYMBOL(si_meminfo); #ifdef CONFIG_NUMA void si_meminfo_node(struct sysinfo *val, int nid) { int zone_type; /* needs to be signed */ unsigned long managed_pages = 0; unsigned long managed_highpages = 0; unsigned long free_highpages = 0; pg_data_t *pgdat = NODE_DATA(nid); for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) managed_pages += zone_managed_pages(&pgdat->node_zones[zone_type]); val->totalram = managed_pages; val->sharedram = node_page_state(pgdat, NR_SHMEM); val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES); #ifdef CONFIG_HIGHMEM for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { struct zone *zone = &pgdat->node_zones[zone_type]; if (is_highmem(zone)) { managed_highpages += zone_managed_pages(zone); free_highpages += zone_page_state(zone, NR_FREE_PAGES); } } val->totalhigh = managed_highpages; val->freehigh = free_highpages; #else val->totalhigh = managed_highpages; val->freehigh = free_highpages; #endif val->mem_unit = PAGE_SIZE; } #endif /* * Determine whether the node should be displayed or not, depending on whether * SHOW_MEM_FILTER_NODES was passed to show_free_areas(). */ static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask) { if (!(flags & SHOW_MEM_FILTER_NODES)) return false; /* * no node mask - aka implicit memory numa policy. Do not bother with * the synchronization - read_mems_allowed_begin - because we do not * have to be precise here. */ if (!nodemask) nodemask = &cpuset_current_mems_allowed; return !node_isset(nid, *nodemask); } static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { [MIGRATE_UNMOVABLE] = 'U', [MIGRATE_MOVABLE] = 'M', [MIGRATE_RECLAIMABLE] = 'E', [MIGRATE_HIGHATOMIC] = 'H', #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif #ifdef CONFIG_MEMORY_ISOLATION [MIGRATE_ISOLATE] = 'I', #endif }; char tmp[MIGRATE_TYPES + 1]; char *p = tmp; int i; for (i = 0; i < MIGRATE_TYPES; i++) { if (type & (1 << i)) *p++ = types[i]; } *p = '\0'; printk(KERN_CONT "(%s) ", tmp); } static bool node_has_managed_zones(pg_data_t *pgdat, int max_zone_idx) { int zone_idx; for (zone_idx = 0; zone_idx <= max_zone_idx; zone_idx++) if (zone_managed_pages(pgdat->node_zones + zone_idx)) return true; return false; } /* * Show free area list (used inside shift_scroll-lock stuff) * We also calculate the percentage fragmentation. We do this by counting the * memory on each free list with the exception of the first item on the list. * * Bits in @filter: * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's * cpuset. */ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) { unsigned long free_pcp = 0; int cpu, nid; struct zone *zone; pg_data_t *pgdat; for_each_populated_zone(zone) { if (zone_idx(zone) > max_zone_idx) continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; for_each_online_cpu(cpu) free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" " active_file:%lu inactive_file:%lu isolated_file:%lu\n" " unevictable:%lu dirty:%lu writeback:%lu\n" " slab_reclaimable:%lu slab_unreclaimable:%lu\n" " mapped:%lu shmem:%lu pagetables:%lu\n" " sec_pagetables:%lu bounce:%lu\n" " kernel_misc_reclaimable:%lu\n" " free:%lu free_pcp:%lu free_cma:%lu\n", global_node_page_state(NR_ACTIVE_ANON), global_node_page_state(NR_INACTIVE_ANON), global_node_page_state(NR_ISOLATED_ANON), global_node_page_state(NR_ACTIVE_FILE), global_node_page_state(NR_INACTIVE_FILE), global_node_page_state(NR_ISOLATED_FILE), global_node_page_state(NR_UNEVICTABLE), global_node_page_state(NR_FILE_DIRTY), global_node_page_state(NR_WRITEBACK), global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B), global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B), global_node_page_state(NR_FILE_MAPPED), global_node_page_state(NR_SHMEM), global_node_page_state(NR_PAGETABLE), global_node_page_state(NR_SECONDARY_PAGETABLE), global_zone_page_state(NR_BOUNCE), global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE), global_zone_page_state(NR_FREE_PAGES), free_pcp, global_zone_page_state(NR_FREE_CMA_PAGES)); for_each_online_pgdat(pgdat) { if (show_mem_node_skip(filter, pgdat->node_id, nodemask)) continue; if (!node_has_managed_zones(pgdat, max_zone_idx)) continue; printk("Node %d" " active_anon:%lukB" " inactive_anon:%lukB" " active_file:%lukB" " inactive_file:%lukB" " unevictable:%lukB" " isolated(anon):%lukB" " isolated(file):%lukB" " mapped:%lukB" " dirty:%lukB" " writeback:%lukB" " shmem:%lukB" #ifdef CONFIG_TRANSPARENT_HUGEPAGE " shmem_thp:%lukB" " shmem_pmdmapped:%lukB" " anon_thp:%lukB" #endif " writeback_tmp:%lukB" " kernel_stack:%lukB" #ifdef CONFIG_SHADOW_CALL_STACK " shadow_call_stack:%lukB" #endif " pagetables:%lukB" " sec_pagetables:%lukB" " all_unreclaimable? %s" "\n", pgdat->node_id, K(node_page_state(pgdat, NR_ACTIVE_ANON)), K(node_page_state(pgdat, NR_INACTIVE_ANON)), K(node_page_state(pgdat, NR_ACTIVE_FILE)), K(node_page_state(pgdat, NR_INACTIVE_FILE)), K(node_page_state(pgdat, NR_UNEVICTABLE)), K(node_page_state(pgdat, NR_ISOLATED_ANON)), K(node_page_state(pgdat, NR_ISOLATED_FILE)), K(node_page_state(pgdat, NR_FILE_MAPPED)), K(node_page_state(pgdat, NR_FILE_DIRTY)), K(node_page_state(pgdat, NR_WRITEBACK)), K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE K(node_page_state(pgdat, NR_SHMEM_THPS)), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), K(node_page_state(pgdat, NR_ANON_THPS)), #endif K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), node_page_state(pgdat, NR_KERNEL_STACK_KB), #ifdef CONFIG_SHADOW_CALL_STACK node_page_state(pgdat, NR_KERNEL_SCS_KB), #endif K(node_page_state(pgdat, NR_PAGETABLE)), K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? "yes" : "no"); } for_each_populated_zone(zone) { int i; if (zone_idx(zone) > max_zone_idx) continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; free_pcp = 0; for_each_online_cpu(cpu) free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; show_node(zone); printk(KERN_CONT "%s" " free:%lukB" " boost:%lukB" " min:%lukB" " low:%lukB" " high:%lukB" " reserved_highatomic:%luKB" " active_anon:%lukB" " inactive_anon:%lukB" " active_file:%lukB" " inactive_file:%lukB" " unevictable:%lukB" " writepending:%lukB" " present:%lukB" " managed:%lukB" " mlocked:%lukB" " bounce:%lukB" " free_pcp:%lukB" " local_pcp:%ukB" " free_cma:%lukB" "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), K(zone->watermark_boost), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), K(zone->nr_reserved_highatomic), K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)), K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)), K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)), K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)), K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)), K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)), K(zone->present_pages), K(zone_managed_pages(zone)), K(zone_page_state(zone, NR_MLOCK)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), K(this_cpu_read(zone->per_cpu_pageset->count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) printk(KERN_CONT " %ld", zone->lowmem_reserve[i]); printk(KERN_CONT "\n"); } for_each_populated_zone(zone) { unsigned int order; unsigned long nr[NR_PAGE_ORDERS], flags, total = 0; unsigned char types[NR_PAGE_ORDERS]; if (zone_idx(zone) > max_zone_idx) continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; show_node(zone); printk(KERN_CONT "%s: ", zone->name); spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < NR_PAGE_ORDERS; order++) { struct free_area *area = &zone->free_area[order]; int type; nr[order] = area->nr_free; total += nr[order] << order; types[order] = 0; for (type = 0; type < MIGRATE_TYPES; type++) { if (!free_area_empty(area, type)) types[order] |= 1 << type; } } spin_unlock_irqrestore(&zone->lock, flags); for (order = 0; order < NR_PAGE_ORDERS; order++) { printk(KERN_CONT "%lu*%lukB ", nr[order], K(1UL) << order); if (nr[order]) show_migration_types(types[order]); } printk(KERN_CONT "= %lukB\n", K(total)); } for_each_online_node(nid) { if (show_mem_node_skip(filter, nid, nodemask)) continue; hugetlb_show_meminfo_node(nid); } printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES)); show_swap_cache_info(); } void __show_mem(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) { unsigned long total = 0, reserved = 0, highmem = 0; struct zone *zone; printk("Mem-Info:\n"); show_free_areas(filter, nodemask, max_zone_idx); for_each_populated_zone(zone) { total += zone->present_pages; reserved += zone->present_pages - zone_managed_pages(zone); if (is_highmem(zone)) highmem += zone->present_pages; } printk("%lu pages RAM\n", total); printk("%lu pages HighMem/MovableOnly\n", highmem); printk("%lu pages reserved\n", reserved); #ifdef CONFIG_CMA printk("%lu pages cma reserved\n", totalcma_pages); #endif #ifdef CONFIG_MEMORY_FAILURE printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages)); #endif #ifdef CONFIG_MEM_ALLOC_PROFILING { struct codetag_bytes tags[10]; size_t i, nr; nr = alloc_tag_top_users(tags, ARRAY_SIZE(tags), false); if (nr) { pr_notice("Memory allocations:\n"); for (i = 0; i < nr; i++) { struct codetag *ct = tags[i].ct; struct alloc_tag *tag = ct_to_alloc_tag(ct); struct alloc_tag_counters counter = alloc_tag_read(tag); /* Same as alloc_tag_to_text() but w/o intermediate buffer */ if (ct->modname) pr_notice("%12lli %8llu %s:%u [%s] func:%s\n", counter.bytes, counter.calls, ct->filename, ct->lineno, ct->modname, ct->function); else pr_notice("%12lli %8llu %s:%u func:%s\n", counter.bytes, counter.calls, ct->filename, ct->lineno, ct->function); } } } #endif } |
| 12 1 11 13 11 2 11 10 11 11 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/symlink.c - operations for initializing and mounting sysfs * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/fs.h> #include <linux/magic.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <net/net_namespace.h> #include "sysfs.h" static struct kernfs_root *sysfs_root; struct kernfs_node *sysfs_root_kn; static int sysfs_get_tree(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; int ret; ret = kernfs_get_tree(fc); if (ret) return ret; if (kfc->new_sb_created) fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE; return 0; } static void sysfs_fs_context_free(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; if (kfc->ns_tag) kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag); kernfs_free_fs_context(fc); kfree(kfc); } static const struct fs_context_operations sysfs_fs_context_ops = { .free = sysfs_fs_context_free, .get_tree = sysfs_get_tree, }; static int sysfs_init_fs_context(struct fs_context *fc) { struct kernfs_fs_context *kfc; struct net *netns; if (!(fc->sb_flags & SB_KERNMOUNT)) { if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return -EPERM; } kfc = kzalloc(sizeof(struct kernfs_fs_context), GFP_KERNEL); if (!kfc) return -ENOMEM; kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); kfc->root = sysfs_root; kfc->magic = SYSFS_MAGIC; fc->fs_private = kfc; fc->ops = &sysfs_fs_context_ops; if (netns) { put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(netns->user_ns); } fc->global = true; return 0; } static void sysfs_kill_sb(struct super_block *sb) { void *ns = (void *)kernfs_super_ns(sb); kernfs_kill_sb(sb); kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); } static struct file_system_type sysfs_fs_type = { .name = "sysfs", .init_fs_context = sysfs_init_fs_context, .kill_sb = sysfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; int __init sysfs_init(void) { int err; sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, NULL); if (IS_ERR(sysfs_root)) return PTR_ERR(sysfs_root); sysfs_root_kn = kernfs_root_to_node(sysfs_root); err = register_filesystem(&sysfs_fs_type); if (err) { kernfs_destroy_root(sysfs_root); return err; } return 0; } |
| 8216 1 1 1 1 1 1 1 1 1 1 1 1 145 147 146 1 1 147 146 146 148 147 148 147 148 205 208 186 208 208 12 205 208 208 208 207 207 1 208 1 1 1 211 259 259 204 146 157 160 1 158 156 158 210 209 212 210 1 3 197 189 210 209 4 15 158 148 14 160 206 209 209 4 4 4 4 3 3 3 3 3 3 3 2 3 3 3 3 3 3 157 157 157 5 156 157 153 14 153 4 13 157 154 4 157 157 157 129 88 156 140 205 204 157 139 205 206 155 140 157 157 206 1 203 206 3 2 3 3 3 3 3 3 3 3 3 3 3 3 148 146 148 148 147 1 8 15 8 148 148 148 1 1 1 1 1 3 1 3 3 3 3 3 1 3 3 3 3 202 202 180 24 6 6 147 144 4 143 142 141 5 5 24 24 23 1 3 179 180 178 179 178 1 180 1 181 181 179 179 178 178 178 179 1 181 180 49 128 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 */ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/set_memory.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <linux/io.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/memcontrol.h> #include <linux/llist.h> #include <linux/uio.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> #include <linux/overflow.h> #include <linux/pgtable.h> #include <linux/hugetlb.h> #include <linux/sched/mm.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> #include <linux/page_owner.h> #define CREATE_TRACE_POINTS #include <trace/events/vmalloc.h> #include "internal.h" #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { ioremap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC static bool __ro_after_init vmap_allow_huge = true; static int __init set_nohugevmalloc(char *str) { vmap_allow_huge = false; return 0; } early_param("nohugevmalloc", set_nohugevmalloc); #else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ static const bool vmap_allow_huge = false; #endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ bool is_vmalloc_addr(const void *x) { unsigned long addr = (unsigned long)kasan_reset_tag(x); return addr >= VMALLOC_START && addr < VMALLOC_END; } EXPORT_SYMBOL(is_vmalloc_addr); struct vfree_deferred { struct llist_head list; struct work_struct wq; }; static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); /*** Page table manipulation functions ***/ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pte_t *pte; u64 pfn; struct page *page; unsigned long size = PAGE_SIZE; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { if (!pte_none(ptep_get(pte))) { if (pfn_valid(pfn)) { page = pfn_to_page(pfn); dump_page(page, "remapping already mapped page"); } BUG(); } #ifdef CONFIG_HUGETLB_PAGE size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); if (size != PAGE_SIZE) { pte_t entry = pfn_pte(pfn, prot); entry = arch_make_huge_pte(entry, ilog2(size), 0); set_huge_pte_at(&init_mm, addr, pte, entry, size); pfn += PFN_DOWN(size); continue; } #endif set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte += PFN_DOWN(size), addr += size, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PMD_SHIFT) return 0; if (!arch_vmap_pmd_supported(prot)) return 0; if ((end - addr) != PMD_SIZE) return 0; if (!IS_ALIGNED(addr, PMD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PMD_SIZE)) return 0; if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) return 0; return pmd_set_huge(pmd, phys_addr, prot); } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PMD_MODIFIED; continue; } if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PUD_SHIFT) return 0; if (!arch_vmap_pud_supported(prot)) return 0; if ((end - addr) != PUD_SIZE) return 0; if (!IS_ALIGNED(addr, PUD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PUD_SIZE)) return 0; if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) return 0; return pud_set_huge(pud, phys_addr, prot); } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PUD_MODIFIED; continue; } if (vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pud++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < P4D_SHIFT) return 0; if (!arch_vmap_p4d_supported(prot)) return 0; if ((end - addr) != P4D_SIZE) return 0; if (!IS_ALIGNED(addr, P4D_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, P4D_SIZE)) return 0; if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) return 0; return p4d_set_huge(p4d, phys_addr, prot); } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_P4D_MODIFIED; continue; } if (vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); return 0; } static int vmap_range_noflush(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { pgd_t *pgd; unsigned long start; unsigned long next; int err; pgtbl_mod_mask mask = 0; might_sleep(); BUG_ON(addr >= end); start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, max_page_shift, &mask); if (err) break; } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return err; } int vmap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { int err; err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), ioremap_max_page_shift); flush_cache_vmap(addr, end); if (!err) err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, ioremap_max_page_shift); return err; } int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { struct vm_struct *area; area = find_vm_area((void *)addr); if (!area || !(area->flags & VM_IOREMAP)) { WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr); return -EINVAL; } if (addr != (unsigned long)area->addr || (void *)end != area->addr + get_vm_area_size(area)) { WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n", addr, end, (long)area->addr, (long)area->addr + get_vm_area_size(area)); return -ERANGE; } return vmap_page_range(addr, end, phys_addr, prot); } static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; pte = pte_offset_kernel(pmd, addr); do { pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; } static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); cleared = pmd_clear_huge(pmd); if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; if (cleared) continue; if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); cond_resched(); } while (pmd++, addr = next, addr != end); } static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); cleared = pud_clear_huge(pud); if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; if (cleared) continue; if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); p4d_clear_huge(p4d); if (p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /* * vunmap_range_noflush is similar to vunmap_range, but does not * flush caches or TLBs. * * The caller is responsible for calling flush_cache_vmap() before calling * this function, and flush_tlb_kernel_range after it has returned * successfully (and before the addresses are expected to cause a page fault * or be re-mapped for something else, if TLB flushes are being delayed or * coalesced). * * This is an internal function only. Do not use outside mm/. */ void __vunmap_range_noflush(unsigned long start, unsigned long end) { unsigned long next; pgd_t *pgd; unsigned long addr = start; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); } void vunmap_range_noflush(unsigned long start, unsigned long end) { kmsan_vunmap_range_noflush(start, end); __vunmap_range_noflush(start, end); } /** * vunmap_range - unmap kernel virtual addresses * @addr: start of the VM area to unmap * @end: end of the VM area to unmap (non-inclusive) * * Clears any present PTEs in the virtual address range, flushes TLBs and * caches. Any subsequent access to the address before it has been re-mapped * is a kernel bug. */ void vunmap_range(unsigned long addr, unsigned long end) { flush_cache_vunmap(addr, end); vunmap_range_noflush(addr, end); flush_tlb_kernel_range(addr, end); } static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pte_t *pte; /* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { struct page *page = pages[*nr]; if (WARN_ON(!pte_none(ptep_get(pte)))) return -EBUSY; if (WARN_ON(!page)) return -ENOMEM; if (WARN_ON(!pfn_valid(page_to_pfn(page)))) return -EINVAL; set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; } static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages) { unsigned long start = addr; pgd_t *pgd; unsigned long next; int err = 0; int nr = 0; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) return err; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return 0; } /* * vmap_pages_range_noflush is similar to vmap_pages_range, but does not * flush caches. * * The caller is responsible for calling flush_cache_vmap() after this * function returns successfully and before the addresses are accessed. * * This is an internal function only. Do not use outside mm/. */ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { unsigned int i, nr = (end - addr) >> PAGE_SHIFT; WARN_ON(page_shift < PAGE_SHIFT); if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || page_shift == PAGE_SHIFT) return vmap_small_pages_range_noflush(addr, end, prot, pages); for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { int err; err = vmap_range_noflush(addr, addr + (1UL << page_shift), page_to_phys(pages[i]), prot, page_shift); if (err) return err; addr += 1UL << page_shift; } return 0; } int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift); if (ret) return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } /** * vmap_pages_range - map pages to a kernel virtual address * @addr: start of the VM area to map * @end: end of the VM area to map (non-inclusive) * @prot: page protection flags to use * @pages: pages to map (always PAGE_SIZE pages) * @page_shift: maximum shift that the pages may be mapped with, @pages must * be aligned and contiguous up to at least this shift. * * RETURNS: * 0 on success, -errno on failure. */ static int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int err; err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift); flush_cache_vmap(addr, end); return err; } static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, unsigned long end) { might_sleep(); if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS)) return -EINVAL; if (WARN_ON_ONCE(area->flags & VM_NO_GUARD)) return -EINVAL; if (WARN_ON_ONCE(!(area->flags & VM_SPARSE))) return -EINVAL; if ((end - start) >> PAGE_SHIFT > totalram_pages()) return -E2BIG; if (start < (unsigned long)area->addr || (void *)end > area->addr + get_vm_area_size(area)) return -ERANGE; return 0; } /** * vm_area_map_pages - map pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area * @pages: pages to map (always PAGE_SIZE pages) */ int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages) { int err; err = check_sparse_vm_area(area, start, end); if (err) return err; return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT); } /** * vm_area_unmap_pages - unmap pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area */ void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end) { if (check_sparse_vm_area(area, start, end)) return; vunmap_range(start, end); } int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* * Walk a vmap address to the struct page it maps. Huge vmap mappings will * return the tail page that corresponds to the base page address, which * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (pgd_none(*pgd)) return NULL; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return NULL; /* XXX: no allowance for huge pgd */ if (WARN_ON_ONCE(pgd_bad(*pgd))) return NULL; p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; if (p4d_leaf(*p4d)) return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(p4d_bad(*p4d))) return NULL; pud = pud_offset(p4d, addr); if (pud_none(*pud)) return NULL; if (pud_leaf(*pud)) return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return NULL; if (pmd_leaf(*pmd)) return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; ptep = pte_offset_kernel(pmd, addr); pte = ptep_get(ptep); if (pte_present(pte)) page = pte_page(pte); return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ unsigned long vmalloc_to_pfn(const void *vmalloc_addr) { return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ #define DEBUG_AUGMENT_PROPAGATE_CHECK 0 #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 static DEFINE_SPINLOCK(free_vmap_area_lock); static bool vmap_initialized __read_mostly; /* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to * make things faster. Especially in "no edge" splitting of * free block. */ static struct kmem_cache *vmap_area_cachep; /* * This linked list is used in pair with free_vmap_area_root. * It gives O(1) access to prev/next to perform fast coalescing. */ static LIST_HEAD(free_vmap_area_list); /* * This augment red-black tree represents the free vmap space. * All vmap_area objects in this tree are sorted by va->va_start * address. It is used for allocation and merging when a vmap * object is released. * * Each vmap_area node contains a maximum available free block * of its sub-tree, right or left. Therefore it is possible to * find a lowest match of free area. */ static struct rb_root free_vmap_area_root = RB_ROOT; /* * Preload a CPU with one object for "no edge" split case. The * aim is to get rid of allocations from the atomic context, thus * to use more permissive allocation masks. */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); /* * This structure defines a single, solid model where a list and * rb-tree are part of one entity protected by the lock. Nodes are * sorted in ascending order, thus for O(1) access to left/right * neighbors a list is used as well as for sequential traversal. */ struct rb_list { struct rb_root root; struct list_head head; spinlock_t lock; }; /* * A fast size storage contains VAs up to 1M size. A pool consists * of linked between each other ready to go VAs of certain sizes. * An index in the pool-array corresponds to number of pages + 1. */ #define MAX_VA_SIZE_PAGES 256 struct vmap_pool { struct list_head head; unsigned long len; }; /* * An effective vmap-node logic. Users make use of nodes instead * of a global heap. It allows to balance an access and mitigate * contention. */ static struct vmap_node { /* Simple size segregated storage. */ struct vmap_pool pool[MAX_VA_SIZE_PAGES]; spinlock_t pool_lock; bool skip_populate; /* Bookkeeping data of this node. */ struct rb_list busy; struct rb_list lazy; /* * Ready-to-free areas. */ struct list_head purge_list; struct work_struct purge_work; unsigned long nr_purged; } single; /* * Initial setup consists of one single node, i.e. a balancing * is fully disabled. Later on, after vmap is initialized these * parameters are updated based on a system capacity. */ static struct vmap_node *vmap_nodes = &single; static __read_mostly unsigned int nr_vmap_nodes = 1; static __read_mostly unsigned int vmap_zone_size = 1; static inline unsigned int addr_to_node_id(unsigned long addr) { return (addr / vmap_zone_size) % nr_vmap_nodes; } static inline struct vmap_node * addr_to_node(unsigned long addr) { return &vmap_nodes[addr_to_node_id(addr)]; } static inline struct vmap_node * id_to_node(unsigned int id) { return &vmap_nodes[id % nr_vmap_nodes]; } /* * We use the value 0 to represent "no node", that is why * an encoded value will be the node-id incremented by 1. * It is always greater then 0. A valid node_id which can * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id * is not valid 0 is returned. */ static unsigned int encode_vn_id(unsigned int node_id) { /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return (node_id + 1) << BITS_PER_BYTE; /* Warn and no node encoded. */ WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); return 0; } /* * Returns an encoded node-id, the valid range is within * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is * returned if extracted data is wrong. */ static unsigned int decode_vn_id(unsigned int val) { unsigned int node_id = (val >> BITS_PER_BYTE) - 1; /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return node_id; /* If it was _not_ zero, warn. */ WARN_ONCE(node_id != UINT_MAX, "Decode wrong node id (%d)\n", node_id); return nr_vmap_nodes; } static bool is_vn_id_valid(unsigned int node_id) { if (node_id < nr_vmap_nodes) return true; return false; } static __always_inline unsigned long va_size(struct vmap_area *va) { return (va->va_end - va->va_start); } static __always_inline unsigned long get_subtree_max_size(struct rb_node *node) { struct vmap_area *va; va = rb_entry_safe(node, struct vmap_area, rb_node); return va ? va->subtree_max_size : 0; } RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void reclaim_and_purge_vmap_areas(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static void drain_vmap_area_work(struct work_struct *work); static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work); static atomic_long_t nr_vmalloc_pages; unsigned long vmalloc_nr_pages(void) { return atomic_long_read(&nr_vmalloc_pages); } static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr >= va->va_end) n = n->rb_right; else return va; } return NULL; } /* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area * __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) { struct vmap_area *va = NULL; struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end > addr) { va = tmp; if (tmp->va_start <= addr) break; n = n->rb_left; } else n = n->rb_right; } return va; } /* * Returns a node where a first VA, that satisfies addr < va_end, resides. * If success, a node is locked. A user is responsible to unlock it when a * VA is no longer needed to be accessed. * * Returns NULL if nothing found. */ static struct vmap_node * find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { unsigned long va_start_lowest; struct vmap_node *vn; int i; repeat: for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); if (*va) if (!va_start_lowest || (*va)->va_start < va_start_lowest) va_start_lowest = (*va)->va_start; spin_unlock(&vn->busy.lock); } /* * Check if found VA exists, it might have gone away. In this case we * repeat the search because a VA has been removed concurrently and we * need to proceed to the next one, which is a rare case. */ if (va_start_lowest) { vn = addr_to_node(va_start_lowest); spin_lock(&vn->busy.lock); *va = __find_vmap_area(va_start_lowest, &vn->busy.root); if (*va) return vn; spin_unlock(&vn->busy.lock); goto repeat; } return NULL; } /* * This function returns back addresses of parent node * and its left or right link for further processing. * * Otherwise NULL is returned. In that case all further * steps regarding inserting of conflicting overlap range * have to be declined and actually considered as a bug. */ static __always_inline struct rb_node ** find_va_links(struct vmap_area *va, struct rb_root *root, struct rb_node *from, struct rb_node **parent) { struct vmap_area *tmp_va; struct rb_node **link; if (root) { link = &root->rb_node; if (unlikely(!*link)) { *parent = NULL; return link; } } else { link = &from; } /* * Go to the bottom of the tree. When we hit the last point * we end up with parent rb_node and correct direction, i name * it link, where the new va->rb_node will be attached to. */ do { tmp_va = rb_entry(*link, struct vmap_area, rb_node); /* * During the traversal we also do some sanity check. * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ if (va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; else if (va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; else { WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); return NULL; } } while (*link); *parent = &tmp_va->rb_node; return link; } static __always_inline struct list_head * get_va_next_sibling(struct rb_node *parent, struct rb_node **link) { struct list_head *list; if (unlikely(!parent)) /* * The red-black tree where we try to find VA neighbors * before merging or inserting is empty, i.e. it means * there is no free vmap space. Normally it does not * happen but we handle this case anyway. */ return NULL; list = &rb_entry(parent, struct vmap_area, rb_node)->list; return (&parent->rb_right == link ? list->next : list); } static __always_inline void __link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head, bool augment) { /* * VA is still not in the list, but we can * identify its future previous list_head node. */ if (likely(parent)) { head = &rb_entry(parent, struct vmap_area, rb_node)->list; if (&parent->rb_right != link) head = head->prev; } /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, * to let __augment_tree_propagate_from() puts everything to * the correct order later on. */ rb_insert_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); va->subtree_max_size = 0; } else { rb_insert_color(&va->rb_node, root); } /* Address-sort this list */ list_add(&va->list, head); } static __always_inline void link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, false); } static __always_inline void link_va_augment(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, true); } static __always_inline void __unlink_va(struct vmap_area *va, struct rb_root *root, bool augment) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; if (augment) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); list_del_init(&va->list); RB_CLEAR_NODE(&va->rb_node); } static __always_inline void unlink_va(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, false); } static __always_inline void unlink_va_augment(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, true); } #if DEBUG_AUGMENT_PROPAGATE_CHECK /* * Gets called when remove the node and rotate. */ static __always_inline unsigned long compute_subtree_max_size(struct vmap_area *va) { return max3(va_size(va), get_subtree_max_size(va->rb_node.rb_left), get_subtree_max_size(va->rb_node.rb_right)); } static void augment_tree_propagate_check(void) { struct vmap_area *va; unsigned long computed_size; list_for_each_entry(va, &free_vmap_area_list, list) { computed_size = compute_subtree_max_size(va); if (computed_size != va->subtree_max_size) pr_emerg("tree is corrupted: %lu, %lu\n", va_size(va), va->subtree_max_size); } } #endif /* * This function populates subtree_max_size from bottom to upper * levels starting from VA point. The propagation must be done * when VA size is modified by changing its va_start/va_end. Or * in case of newly inserting of VA to the tree. * * It means that __augment_tree_propagate_from() must be called: * - After VA has been inserted to the tree(free path); * - After VA has been shrunk(allocation path); * - After VA has been increased(merging path). * * Please note that, it does not mean that upper parent nodes * and their subtree_max_size are recalculated all the time up * to the root node. * * 4--8 * /\ * / \ * / \ * 2--2 8--8 * * For example if we modify the node 4, shrinking it to 2, then * no any modification is required. If we shrink the node 2 to 1 * its subtree_max_size is updated only, and set to 1. If we shrink * the node 8 to 6, then its subtree_max_size is set to 6 and parent * node becomes 4--6. */ static __always_inline void augment_tree_propagate_from(struct vmap_area *va) { /* * Populate the tree from bottom towards the root until * the calculated maximum available size of checked node * is equal to its current one. */ free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); #if DEBUG_AUGMENT_PROPAGATE_CHECK augment_tree_propagate_check(); #endif } static void insert_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; link = find_va_links(va, root, NULL, &parent); if (link) link_va(va, root, parent, link, head); } static void insert_vmap_area_augment(struct vmap_area *va, struct rb_node *from, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; if (from) link = find_va_links(va, NULL, from, &parent); else link = find_va_links(va, root, NULL, &parent); if (link) { link_va_augment(va, root, parent, link, head); augment_tree_propagate_from(va); } } /* * Merge de-allocated chunk of VA memory with previous * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. * * Please note, it can return NULL in case of overlap * ranges, followed by WARN() report. Despite it is a * buggy behaviour, a system can be alive and keep * ongoing. */ static __always_inline struct vmap_area * __merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head, bool augment) { struct vmap_area *sibling; struct list_head *next; struct rb_node **link; struct rb_node *parent; bool merged = false; /* * Find a place in the tree where VA potentially will be * inserted, unless it is merged with its sibling/siblings. */ link = find_va_links(va, root, NULL, &parent); if (!link) return NULL; /* * Get next node of VA to check if merging can be done. */ next = get_va_next_sibling(parent, link); if (unlikely(next == NULL)) goto insert; /* * start end * | | * |<------VA------>|<-----Next----->| * | | * start end */ if (next != head) { sibling = list_entry(next, struct vmap_area, list); if (sibling->va_start == va->va_end) { sibling->va_start = va->va_start; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } /* * start end * | | * |<-----Prev----->|<------VA------>| * | | * start end */ if (next->prev != head) { sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { /* * If both neighbors are coalesced, it is important * to unlink the "next" node first, followed by merging * with "previous" one. Otherwise the tree might not be * fully populated if a sibling's augmented value is * "normalized" because of rotation operations. */ if (merged) __unlink_va(va, root, augment); sibling->va_end = va->va_end; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } insert: if (!merged) __link_va(va, root, parent, link, head, augment); return va; } static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { return __merge_or_add_vmap_area(va, root, head, false); } static __always_inline struct vmap_area * merge_or_add_vmap_area_augment(struct vmap_area *va, struct rb_root *root, struct list_head *head) { va = __merge_or_add_vmap_area(va, root, head, true); if (va) augment_tree_propagate_from(va); return va; } static __always_inline bool is_within_this_va(struct vmap_area *va, unsigned long size, unsigned long align, unsigned long vstart) { unsigned long nva_start_addr; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Can be overflowed due to big size or alignment. */ if (nva_start_addr + size < nva_start_addr || nva_start_addr < vstart) return false; return (nva_start_addr + size <= va->va_end); } /* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing * parameters. Please note, with an alignment bigger than PAGE_SIZE, * a search length is adjusted to account for worst case alignment * overhead. */ static __always_inline struct vmap_area * find_vmap_lowest_match(struct rb_root *root, unsigned long size, unsigned long align, unsigned long vstart, bool adjust_search_size) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ node = root->rb_node; /* Adjust the search size for alignment overhead. */ length = adjust_search_size ? size + align - 1 : size; while (node) { va = rb_entry(node, struct vmap_area, rb_node); if (get_subtree_max_size(node->rb_left) >= length && vstart < va->va_start) { node = node->rb_left; } else { if (is_within_this_va(va, size, align, vstart)) return va; /* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is * equal or bigger to the requested search length. */ if (get_subtree_max_size(node->rb_right) >= length) { node = node->rb_right; continue; } /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen * due to "vstart" restriction or an alignment overhead * that is bigger then PAGE_SIZE. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va; if (get_subtree_max_size(node->rb_right) >= length && vstart <= va->va_start) { /* * Shift the vstart forward. Please note, we update it with * parent's start address adding "1" because we do not want * to enter same sub-tree after it has already been checked * and no suitable free block found there. */ vstart = va->va_start + 1; node = node->rb_right; break; } } } } return NULL; } #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK #include <linux/random.h> static struct vmap_area * find_vmap_lowest_linear_match(struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; list_for_each_entry(va, head, list) { if (!is_within_this_va(va, size, align, vstart)) continue; return va; } return NULL; } static void find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align) { struct vmap_area *va_1, *va_2; unsigned long vstart; unsigned int rnd; get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; va_1 = find_vmap_lowest_match(root, size, align, vstart, false); va_2 = find_vmap_lowest_linear_match(head, size, align, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", va_1, va_2, vstart); } #endif enum fit_type { NOTHING_FIT = 0, FL_FIT_TYPE = 1, /* full fit */ LE_FIT_TYPE = 2, /* left edge fit */ RE_FIT_TYPE = 3, /* right edge fit */ NE_FIT_TYPE = 4 /* no edge fit */ }; static __always_inline enum fit_type classify_va_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { enum fit_type type; /* Check if it is within VA. */ if (nva_start_addr < va->va_start || nva_start_addr + size > va->va_end) return NOTHING_FIT; /* Now classify. */ if (va->va_start == nva_start_addr) { if (va->va_end == nva_start_addr + size) type = FL_FIT_TYPE; else type = LE_FIT_TYPE; } else if (va->va_end == nva_start_addr + size) { type = RE_FIT_TYPE; } else { type = NE_FIT_TYPE; } return type; } static __always_inline int va_clip(struct rb_root *root, struct list_head *head, struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { struct vmap_area *lva = NULL; enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); if (type == FL_FIT_TYPE) { /* * No need to split VA, it fully fits. * * | | * V NVA V * |---------------| */ unlink_va_augment(va, root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* * Split left edge of fit VA. * * | | * V NVA V R * |-------|-------| */ va->va_start += size; } else if (type == RE_FIT_TYPE) { /* * Split right edge of fit VA. * * | | * L V NVA V * |-------|-------| */ va->va_end = nva_start_addr; } else if (type == NE_FIT_TYPE) { /* * Split no edge of fit VA. * * | | * L V NVA V R * |---|-------|---| */ lva = __this_cpu_xchg(ne_fit_preload_node, NULL); if (unlikely(!lva)) { /* * For percpu allocator we do not do any pre-allocation * and leave it as it is. The reason is it most likely * never ends up with NE_FIT_TYPE splitting. In case of * percpu allocations offsets and sizes are aligned to * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE * are its main fitting cases. * * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. * * Also we can hit this path in case of regular "vmap" * allocations, if "this" current CPU was not preloaded. * See the comment in alloc_vmap_area() why. If so, then * GFP_NOWAIT is used instead to get an extra object for * split purpose. That is rare and most time does not * occur. * * What happens if an allocation gets failed. Basically, * an "overflow" path is triggered to purge lazily freed * areas to free some memory, then, the "retry" path is * triggered to repeat one more time. See more details * in alloc_vmap_area() function. */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) return -1; } /* * Build the remainder. */ lva->va_start = va->va_start; lva->va_end = nva_start_addr; /* * Shrink this VA to remaining size. */ va->va_start = nva_start_addr + size; } else { return -1; } if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, root, head); } return 0; } static unsigned long va_alloc(struct vmap_area *va, struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; int ret; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) return vend; /* Update the free vmap_area. */ ret = va_clip(root, head, va, nva_start_addr, size); if (WARN_ON_ONCE(ret)) return vend; return nva_start_addr; } /* * Returns a start address of the newly allocated area, if success. * Otherwise a vend is returned that indicates failure. */ static __always_inline unsigned long __alloc_vmap_area(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { bool adjust_search_size = true; unsigned long nva_start_addr; struct vmap_area *va; /* * Do not adjust when: * a) align <= PAGE_SIZE, because it does not make any sense. * All blocks(their start addresses) are at least PAGE_SIZE * aligned anyway; * b) a short range where a requested size corresponds to exactly * specified [vstart:vend] interval and an alignment > PAGE_SIZE. * With adjusted search length an allocation would not succeed. */ if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size)) adjust_search_size = false; va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) return vend; nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); if (nva_start_addr == vend) return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK find_vmap_lowest_match_check(root, head, size, align); #endif return nva_start_addr; } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { struct vmap_node *vn = addr_to_node(va->va_start); /* * Remove from the busy tree/list. */ spin_lock(&vn->busy.lock); unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); /* * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static inline void preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) { struct vmap_area *va = NULL, *tmp; /* * Preload this CPU with one extra vmap_area object. It is used * when fit type of free area is NE_FIT_TYPE. It guarantees that * a CPU that does an allocation is preloaded. * * We do it in non-atomic context, thus it allows us to use more * permissive allocation masks to be more stable under low memory * condition and high memory pressure. */ if (!this_cpu_read(ne_fit_preload_node)) va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); spin_lock(lock); tmp = NULL; if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) kmem_cache_free(vmap_area_cachep, va); } static struct vmap_pool * size_to_va_pool(struct vmap_node *vn, unsigned long size) { unsigned int idx = (size - 1) / PAGE_SIZE; if (idx < MAX_VA_SIZE_PAGES) return &vn->pool[idx]; return NULL; } static bool node_pool_add_va(struct vmap_node *n, struct vmap_area *va) { struct vmap_pool *vp; vp = size_to_va_pool(n, va_size(va)); if (!vp) return false; spin_lock(&n->pool_lock); list_add(&va->list, &vp->head); WRITE_ONCE(vp->len, vp->len + 1); spin_unlock(&n->pool_lock); return true; } static struct vmap_area * node_pool_del_va(struct vmap_node *vn, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { struct vmap_area *va = NULL; struct vmap_pool *vp; int err = 0; vp = size_to_va_pool(vn, size); if (!vp || list_empty(&vp->head)) return NULL; spin_lock(&vn->pool_lock); if (!list_empty(&vp->head)) { va = list_first_entry(&vp->head, struct vmap_area, list); if (IS_ALIGNED(va->va_start, align)) { /* * Do some sanity check and emit a warning * if one of below checks detects an error. */ err |= (va_size(va) != size); err |= (va->va_start < vstart); err |= (va->va_end > vend); if (!WARN_ON_ONCE(err)) { list_del_init(&va->list); WRITE_ONCE(vp->len, vp->len - 1); } else { va = NULL; } } else { list_move_tail(&va->list, &vp->head); va = NULL; } } spin_unlock(&vn->pool_lock); return va; } static struct vmap_area * node_alloc(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, unsigned long *addr, unsigned int *vn_id) { struct vmap_area *va; *vn_id = 0; *addr = vend; /* * Fallback to a global heap if not vmalloc or there * is only one node. */ if (vstart != VMALLOC_START || vend != VMALLOC_END || nr_vmap_nodes == 1) return NULL; *vn_id = raw_smp_processor_id() % nr_vmap_nodes; va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); *vn_id = encode_vn_id(*vn_id); if (va) *addr = va->va_start; return va; } static inline void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->vm = vm; } /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask, unsigned long va_flags, struct vm_struct *vm) { struct vmap_node *vn; struct vmap_area *va; unsigned long freed; unsigned long addr; unsigned int vn_id; int purged = 0; int ret; if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align))) return ERR_PTR(-EINVAL); if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); might_sleep(); /* * If a VA is obtained from a global heap(if it fails here) * it is anyway marked with this "vn_id" so it is returned * to this pool's node later. Such way gives a possibility * to populate pools based on users demand. * * On success a ready to go VA is returned. */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { gfp_mask = gfp_mask & GFP_RECLAIM_MASK; va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); /* * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); } retry: if (addr == vend) { preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); } trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ if (unlikely(addr == vend)) goto overflow; va->va_start = addr; va->va_end = addr + size; va->vm = NULL; va->flags = (va_flags | vn_id); if (vm) { vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; va->vm = vm; } vn = addr_to_node(va->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); spin_unlock(&vn->busy.lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); ret = kasan_populate_vmalloc(addr, size); if (ret) { free_vmap_area(va); return ERR_PTR(ret); } return va; overflow: if (!purged) { reclaim_and_purge_vmap_areas(); purged = 1; goto retry; } freed = 0; blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); if (freed > 0) { purged = 0; goto retry; } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n", size, vstart, vend); kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } int register_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); int unregister_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* * Serialize vmap purging. There is no actual critical section protected * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); static cpumask_t purge_nodes; static void reclaim_list_global(struct list_head *head) { struct vmap_area *va, *n; if (list_empty(head)) return; spin_lock(&free_vmap_area_lock); list_for_each_entry_safe(va, n, head, list) merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static void decay_va_pool_node(struct vmap_node *vn, bool full_decay) { struct vmap_area *va, *nva; struct list_head decay_list; struct rb_root decay_root; unsigned long n_decay; int i; decay_root = RB_ROOT; INIT_LIST_HEAD(&decay_list); for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { struct list_head tmp_list; if (list_empty(&vn->pool[i].head)) continue; INIT_LIST_HEAD(&tmp_list); /* Detach the pool, so no-one can access it. */ spin_lock(&vn->pool_lock); list_replace_init(&vn->pool[i].head, &tmp_list); spin_unlock(&vn->pool_lock); if (full_decay) WRITE_ONCE(vn->pool[i].len, 0); /* Decay a pool by ~25% out of left objects. */ n_decay = vn->pool[i].len >> 2; list_for_each_entry_safe(va, nva, &tmp_list, list) { list_del_init(&va->list); merge_or_add_vmap_area(va, &decay_root, &decay_list); if (!full_decay) { WRITE_ONCE(vn->pool[i].len, vn->pool[i].len - 1); if (!--n_decay) break; } } /* * Attach the pool back if it has been partly decayed. * Please note, it is supposed that nobody(other contexts) * can populate the pool therefore a simple list replace * operation takes place here. */ if (!full_decay && !list_empty(&tmp_list)) { spin_lock(&vn->pool_lock); list_replace_init(&tmp_list, &vn->pool[i].head); spin_unlock(&vn->pool_lock); } } reclaim_list_global(&decay_list); } static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); struct vmap_area *va, *n_va; LIST_HEAD(local_list); vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; unsigned long orig_start = va->va_start; unsigned long orig_end = va->va_end; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); if (is_vmalloc_or_module_addr((void *)orig_start)) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); atomic_long_sub(nr, &vmap_lazy_nr); vn->nr_purged++; if (is_vn_id_valid(vn_id) && !vn->skip_populate) if (node_pool_add_va(vn, va)) continue; /* Go back to global. */ list_add(&va->list, &local_list); } reclaim_list_global(&local_list); } /* * Purges all lazily-freed vmap areas. */ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, bool full_pool_decay) { unsigned long nr_purged_areas = 0; unsigned int nr_purge_helpers; unsigned int nr_purge_nodes; struct vmap_node *vn; int i; lockdep_assert_held(&vmap_purge_lock); /* * Use cpumask to mark which node has to be processed. */ purge_nodes = CPU_MASK_NONE; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; INIT_LIST_HEAD(&vn->purge_list); vn->skip_populate = full_pool_decay; decay_va_pool_node(vn, full_pool_decay); if (RB_EMPTY_ROOT(&vn->lazy.root)) continue; spin_lock(&vn->lazy.lock); WRITE_ONCE(vn->lazy.root.rb_node, NULL); list_replace_init(&vn->lazy.head, &vn->purge_list); spin_unlock(&vn->lazy.lock); start = min(start, list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start); end = max(end, list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end); cpumask_set_cpu(i, &purge_nodes); } nr_purge_nodes = cpumask_weight(&purge_nodes); if (nr_purge_nodes > 0) { flush_tlb_kernel_range(start, end); /* One extra worker is per a lazy_max_pages() full set minus one. */ nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages(); nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1; for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (nr_purge_helpers > 0) { INIT_WORK(&vn->purge_work, purge_vmap_node); if (cpumask_test_cpu(i, cpu_online_mask)) schedule_work_on(i, &vn->purge_work); else schedule_work(&vn->purge_work); nr_purge_helpers--; } else { vn->purge_work.func = NULL; purge_vmap_node(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (vn->purge_work.func) { flush_work(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } } trace_purge_vmap_area_lazy(start, end, nr_purged_areas); return nr_purged_areas > 0; } /* * Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list. */ static void reclaim_and_purge_vmap_areas(void) { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); __purge_vmap_area_lazy(ULONG_MAX, 0, true); mutex_unlock(&vmap_purge_lock); } static void drain_vmap_area_work(struct work_struct *work) { mutex_lock(&vmap_purge_lock); __purge_vmap_area_lazy(ULONG_MAX, 0, false); mutex_unlock(&vmap_purge_lock); } /* * Free a vmap area, caller ensuring that the area has been unmapped, * unlinked and flush_cache_vunmap had been called for the correct * range previously. */ static void free_vmap_area_noflush(struct vmap_area *va) { unsigned long nr_lazy_max = lazy_max_pages(); unsigned long va_start = va->va_start; unsigned int vn_id = decode_vn_id(va->flags); struct vmap_node *vn; unsigned long nr_lazy; if (WARN_ON_ONCE(!list_empty(&va->list))) return; nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); /* * If it was request by a certain node we would like to * return it to that node, i.e. its pool for later reuse. */ vn = is_vn_id_valid(vn_id) ? id_to_node(vn_id):addr_to_node(va->va_start); spin_lock(&vn->lazy.lock); insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head); spin_unlock(&vn->lazy.lock); trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max); /* After this point, we may free va at any time */ if (unlikely(nr_lazy > nr_lazy_max)) schedule_work(&drain_vmap_work); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); } struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; if (unlikely(!vmap_initialized)) return NULL; /* * An addr_to_node_id(addr) converts an address to a node index * where a VA is located. If VA spans several zones and passed * addr is not the same as va->va_start, what is not common, we * may need to scan extra nodes. See an example: * * <----va----> * -|-----|-----|-----|-----|- * 1 2 0 1 * * VA resides in node 1 whereas it spans 1, 2 an 0. If passed * addr is within 2 or 0 nodes we should do extra work. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + 1) % nr_vmap_nodes) != j); return NULL; } static struct vmap_area *find_unlink_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; /* * Check the comment in the find_vmap_area() about the loop. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); if (va) unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + 1) % nr_vmap_nodes) != j); return NULL; } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS \ VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) /* * Purge threshold to prevent overeager purging of fragmented blocks for * regular operations: Purge if vb->free is less than 1/4 of the capacity. */ #define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4) #define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ #define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ #define VMAP_FLAGS_MASK 0x3 struct vmap_block_queue { spinlock_t lock; struct list_head free; /* * An xarray requires an extra memory dynamically to * be allocated. If it is an issue, we can use rb-tree * instead. */ struct xarray vmap_blocks; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS); unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * In order to fast access to any "vmap_block" associated with a * specific address, we use a hash. * * A per-cpu vmap_block_queue is used in both ways, to serialize * an access to free block chains among CPUs(alloc path) and it * also acts as a vmap_block hash(alloc/free paths). It means we * overload it, since we already have the per-cpu array which is * used as a hash table. When used as a hash a 'cpu' passed to * per_cpu() is not actually a CPU but rather a hash index. * * A hash function is addr_to_vb_xa() which hashes any address * to a specific index(in a hash) it belongs to. This then uses a * per_cpu() macro to access an array with generated index. * * An example: * * CPU_1 CPU_2 CPU_0 * | | | * V V V * 0 10 20 30 40 50 60 * |------|------|------|------|------|------|...<vmap address space> * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 * * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; * * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; * * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. * * This technique almost always avoids lock contention on insert/remove, * however xarray spinlocks protect against any contention that remains. */ static struct xarray * addr_to_vb_xa(unsigned long addr) { int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids; /* * Please note, nr_cpu_ids points on a highest set * possible bit, i.e. we never invoke cpumask_next() * if an index points on it which is nr_cpu_ids - 1. */ if (!cpu_possible(index)) index = cpumask_next(index, cpu_possible_mask); return &per_cpu(vmap_block_queue, index).vmap_blocks; } /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) { unsigned long addr; addr = va_start + (pages_off << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); return (void *)addr; } /** * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this * block. Of course pages number can't exceed VMAP_BBMAP_BITS * @order: how many 2^order pages should be occupied in newly allocated block * @gfp_mask: flags for the page level allocator * * Return: virtual address in a newly allocated block or ERR_PTR(-errno) */ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; struct xarray *xa; unsigned long vb_idx; int node, err; void *vaddr; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask, VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; /* At least something should be left free */ BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); bitmap_zero(vb->used_map, VMAP_BBMAP_BITS); vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } /* * list_add_tail_rcu could happened in another core * rather than vb->cpu due to task migration, which * is safe as list_add_tail_rcu will ensure the list's * integrity together with list_for_each_rcu from read * side. */ vb->cpu = raw_smp_processor_id(); vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); return vaddr; } static void free_vmap_block(struct vmap_block *vb) { struct vmap_node *vn; struct vmap_block *tmp; struct xarray *xa; xa = addr_to_vb_xa(vb->va->va_start); tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); vn = addr_to_node(vb->va->va_start); spin_lock(&vn->busy.lock); unlink_va(vb->va, &vn->busy.root); spin_unlock(&vn->busy.lock); free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); } static bool purge_fragmented_block(struct vmap_block *vb, struct list_head *purge_list, bool force_purge) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); if (vb->free + vb->dirty != VMAP_BBMAP_BITS || vb->dirty == VMAP_BBMAP_BITS) return false; /* Don't overeagerly purge usable blocks unless requested */ if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD)) return false; /* prevent further allocs after releasing lock */ WRITE_ONCE(vb->free, 0); /* prevent purging it again */ WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS); vb->dirty_min = 0; vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); list_add_tail(&vb->purge, purge_list); return true; } static void free_purged_blocks(struct list_head *purge_list) { struct vmap_block *vb, *n_vb; list_for_each_entry_safe(vb, n_vb, purge_list, purge) { list_del(&vb->purge); free_vmap_block(vb); } } static void purge_fragmented_blocks(int cpu) { LIST_HEAD(purge); struct vmap_block *vb; struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long free = READ_ONCE(vb->free); unsigned long dirty = READ_ONCE(vb->dirty); if (free + dirty != VMAP_BBMAP_BITS || dirty == VMAP_BBMAP_BITS) continue; spin_lock(&vb->lock); purge_fragmented_block(vb, &purge, true); spin_unlock(&vb->lock); } rcu_read_unlock(); free_purged_blocks(&purge); } static void purge_fragmented_blocks_allcpus(void) { int cpu; for_each_possible_cpu(cpu) purge_fragmented_blocks(cpu); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; void *vaddr = NULL; unsigned int order; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); if (WARN_ON(size == 0)) { /* * Allocating 0 bytes isn't what caller wants since * get_order(0) returns funny result. Just warn and terminate * early. */ return ERR_PTR(-EINVAL); } order = get_order(size); rcu_read_lock(); vbq = raw_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; if (READ_ONCE(vb->free) < (1UL << order)) continue; spin_lock(&vb->lock); if (vb->free < (1UL << order)) { spin_unlock(&vb->lock); continue; } pages_off = VMAP_BBMAP_BITS - vb->free; vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); WRITE_ONCE(vb->free, vb->free - (1UL << order)); bitmap_set(vb->used_map, pages_off, (1UL << order)); if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } rcu_read_unlock(); /* Allocate new block if nothing was found */ if (!vaddr) vaddr = new_vmap_block(order, gfp_mask); return vaddr; } static void vb_free(unsigned long addr, unsigned long size) { unsigned long offset; unsigned int order; struct vmap_block *vb; struct xarray *xa; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); flush_cache_vunmap(addr, addr + size); order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; xa = addr_to_vb_xa(addr); vb = xa_load(xa, addr_to_vb_idx(addr)); spin_lock(&vb->lock); bitmap_clear(vb->used_map, offset, (1UL << order)); spin_unlock(&vb->lock); vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); spin_lock(&vb->lock); /* Expand the not yet TLB flushed dirty range */ vb->dirty_min = min(vb->dirty_min, offset); vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order)); if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { LIST_HEAD(purge_list); int cpu; if (unlikely(!vmap_initialized)) return; mutex_lock(&vmap_purge_lock); for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; unsigned long idx; rcu_read_lock(); xa_for_each(&vbq->vmap_blocks, idx, vb) { spin_lock(&vb->lock); /* * Try to purge a fragmented block first. If it's * not purgeable, check whether there is dirty * space to be flushed. */ if (!purge_fragmented_block(vb, &purge_list, false) && vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; s = va_start + (vb->dirty_min << PAGE_SHIFT); e = va_start + (vb->dirty_max << PAGE_SHIFT); start = min(s, start); end = max(e, end); /* Prevent that this is flushed again */ vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; flush = 1; } spin_unlock(&vb->lock); } rcu_read_unlock(); } free_purged_blocks(&purge_list); if (!__purge_vmap_area_lazy(start, end, false) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { unsigned long start = ULONG_MAX, end = 0; int flush = 0; _vm_unmap_aliases(start, end, flush); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr = (unsigned long)kasan_reset_tag(mem); struct vmap_area *va; might_sleep(); BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); kasan_poison_vmalloc(mem, size); if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(addr, size); return; } va = find_unlink_vmap_area(addr); if (WARN_ON_ONCE(!va)) return; debug_check_no_locks_freed((void *)va->va_start, (va->va_end - va->va_start)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life * objects with vm_map_ram(), it could consume lots of address space through * fragmentation (especially on a 32bit machine). You could see failures in * the end. Please use this function for short-lived objects. * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL, VMAP_RAM, NULL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } if (vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, PAGE_SHIFT) < 0) { vm_unmap_ram(mem, count); return NULL; } /* * Mark the pages as accessible, now that they are mapped. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL); return mem; } EXPORT_SYMBOL(vm_map_ram); static struct vm_struct *vmlist __initdata; static inline unsigned int vm_area_page_order(struct vm_struct *vm) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return vm->page_order; #else return 0; #endif } static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC vm->page_order = order; #else BUG_ON(order != 0); #endif } /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add * * This function is used to add fixed kernel vm area to vmlist before * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags * should contain proper values and the other fields should be zero. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_add_early(struct vm_struct *vm) { struct vm_struct *tmp, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) { BUG_ON(tmp->addr < vm->addr + vm->size); break; } else BUG_ON(tmp->addr + tmp->size > vm->addr); } vm->next = *p; *p = vm; } /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { unsigned long addr = ALIGN(VMALLOC_START, align); struct vm_struct *cur, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { if ((unsigned long)cur->addr - addr >= vm->size) break; addr = ALIGN((unsigned long)cur->addr + cur->size, align); } BUG_ON(addr > VMALLOC_END - vm->size); vm->addr = (void *)addr; vm->next = *p; *p = vm; kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. * Pair with smp_rmb() in show_numa_info(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); size = ALIGN(size, 1ul << shift); if (unlikely(!size)) return NULL; if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; area->flags = flags; area->caller = caller; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { kfree(area); return NULL; } /* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. * For VM_ALLOC mappings, the pages are marked as accessible after * getting mapped in __vmalloc_node_range(). * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, KASAN_VMALLOC_PROT_NORMAL); return area; } struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * find_vm_area - find a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and return it. * It is up to the caller to do all required locking to keep the returned * pointer valid. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (!va) return NULL; return va->vm; } /** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; struct vm_struct *vm; might_sleep(); if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", addr)) return NULL; va = find_unlink_vmap_area((unsigned long)addr); if (!va || !va->vm) return NULL; vm = va->vm; debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm)); debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm)); kasan_free_module_shadow(vm); kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm)); free_unmap_vmap_area(va); return vm; } static inline void set_area_direct_map(const struct vm_struct *area, int (*set_direct_map)(struct page *page)) { int i; /* HUGE_VMALLOC passes small pages to set_direct_map */ for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i])) set_direct_map(area->pages[i]); } /* * Flush the vm mapping and reset the direct map. */ static void vm_reset_perms(struct vm_struct *area) { unsigned long start = ULONG_MAX, end = 0; unsigned int page_order = vm_area_page_order(area); int flush_dmap = 0; int i; /* * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map. */ for (i = 0; i < area->nr_pages; i += 1U << page_order) { unsigned long addr = (unsigned long)page_address(area->pages[i]); if (addr) { unsigned long page_size; page_size = PAGE_SIZE << page_order; start = min(addr, start); end = max(addr + page_size, end); flush_dmap = 1; } } /* * Set direct map to something invalid so that it won't be cached if * there are any accesses after the TLB flush, then flush the TLB and * reset the direct map permissions to the default. */ set_area_direct_map(area, set_direct_map_invalid_noflush); _vm_unmap_aliases(start, end, flush_dmap); set_area_direct_map(area, set_direct_map_default_noflush); } static void delayed_vfree_work(struct work_struct *w) { struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); struct llist_node *t, *llnode; llist_for_each_safe(llnode, t, llist_del_all(&p->list)) vfree(llnode); } /** * vfree_atomic - release memory allocated by vmalloc() * @addr: memory base address * * This one is just like vfree() but can be called in any atomic context * except NMIs. */ void vfree_atomic(const void *addr) { struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); BUG_ON(in_nmi()); kmemleak_free(addr); /* * Use raw_cpu_ptr() because this can be called from preemptible * context. Preemption is absolutely fine here, because the llist_add() * implementation is lockless, so it works even if we are adding to * another cpu's list. schedule_work() should be fine with this too. */ if (addr && llist_add((struct llist_node *)addr, &p->list)) schedule_work(&p->wq); } /** * vfree - Release memory allocated by vmalloc() * @addr: Memory base address * * Free the virtually continuous memory area starting at @addr, as obtained * from one of the vmalloc() family of APIs. This will usually also free the * physical memory underlying the virtual allocation, but that memory is * reference counted, so it will not be freed until the last user goes away. * * If @addr is NULL, no operation is performed. * * Context: * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-dependent would be a really bad idea). */ void vfree(const void *addr) { struct vm_struct *vm; int i; if (unlikely(in_interrupt())) { vfree_atomic(addr); return; } BUG_ON(in_nmi()); kmemleak_free(addr); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr); return; } if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) vm_reset_perms(vm); for (i = 0; i < vm->nr_pages; i++) { struct page *page = vm->pages[i]; BUG_ON(!page); mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations */ __free_page(page); cond_resched(); } atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context. */ void vunmap(const void *addr) { struct vm_struct *vm; BUG_ON(in_interrupt()); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n", addr); return; } kfree(vm); } EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual space. * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself * (which must be kmalloc or vmalloc memory) and one reference per pages in it * are transferred from the caller to vmap(), and will be freed / dropped when * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; unsigned long addr; unsigned long size; /* In bytes */ might_sleep(); if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS)) return NULL; /* * Your top guard is someone else's bottom guard. Not having a top * guard compromises someone else's mappings too. */ if (WARN_ON_ONCE(flags & VM_NO_GUARD)) flags &= ~VM_NO_GUARD; if (count > totalram_pages()) return NULL; size = (unsigned long)count << PAGE_SHIFT; area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL; addr = (unsigned long)area->addr; if (vmap_pages_range(addr, addr + size, pgprot_nx(prot), pages, PAGE_SHIFT) < 0) { vunmap(area->addr); return NULL; } if (flags & VM_MAP_PUT_PAGES) { area->pages = pages; area->nr_pages = count; } return area->addr; } EXPORT_SYMBOL(vmap); #ifdef CONFIG_VMAP_PFN struct vmap_pfn_data { unsigned long *pfns; pgprot_t prot; unsigned int idx; }; static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) { struct vmap_pfn_data *data = private; unsigned long pfn = data->pfns[data->idx]; pte_t ptent; if (WARN_ON_ONCE(pfn_valid(pfn))) return -EINVAL; ptent = pte_mkspecial(pfn_pte(pfn, data->prot)); set_pte_at(&init_mm, addr, pte, ptent); data->idx++; return 0; } /** * vmap_pfn - map an array of PFNs into virtually contiguous space * @pfns: array of PFNs * @count: number of pages to map * @prot: page protection for the mapping * * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns * the start address of the mapping. */ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) { struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; struct vm_struct *area; area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, __builtin_return_address(0)); if (!area) return NULL; if (apply_to_page_range(&init_mm, (unsigned long)area->addr, count * PAGE_SIZE, vmap_pfn_apply, &data)) { free_vm_area(area); return NULL; } flush_cache_vmap((unsigned long)area->addr, (unsigned long)area->addr + count * PAGE_SIZE); return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ static inline unsigned int vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; gfp_t alloc_gfp = gfp; bool nofail = gfp & __GFP_NOFAIL; struct page *page; int i; /* * For order-0 pages we make use of bulk allocator, if * the page array is partly or not at all populated due * to fails, fallback to a single page allocator that is * more permissive. */ if (!order) { /* bulk allocator doesn't support nofail req. officially */ gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL; while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; /* * A maximum allowed request is hard-coded and is 100 * pages per call. That is done in order to prevent a * long preemption off scenario in the bulk-allocator * so the range is [1:100]. */ nr_pages_request = min(100U, nr_pages - nr_allocated); /* memory allocation should consider mempolicy, we can't * wrongly use nearest node when nid == NUMA_NO_NODE, * otherwise memory may be allocated in only one node, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp, nr_pages_request, pages + nr_allocated); else nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid, nr_pages_request, pages + nr_allocated); nr_allocated += nr; cond_resched(); /* * If zero or pages were obtained partly, * fallback to a single page allocator. */ if (nr != nr_pages_request) break; } } else if (gfp & __GFP_NOFAIL) { /* * Higher order nofail allocations are really expensive and * potentially dangerous (pre-mature OOM, disruptive reclaim * and compaction etc. */ alloc_gfp &= ~__GFP_NOFAIL; } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { if (!nofail && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) page = alloc_pages_noprof(alloc_gfp, order); else page = alloc_pages_node_noprof(nid, alloc_gfp, order); if (unlikely(!page)) break; /* * Higher order allocations must be able to be treated as * indepdenent small pages by callers (as they can with * small-page vmallocs). Some drivers do their own refcounting * on vmalloc_to_page() pages, some use page->mapping, * page->lru, etc. */ if (order) split_page(page, order); /* * Careful, we allocate and map page-order pages, but * tracking is done per PAGE_SIZE page so as to keep the * vm_struct APIs independent of the physical/mapped size. */ for (i = 0; i < (1U << order); i++) pages[nr_allocated + i] = page + i; cond_resched(); nr_allocated += 1U << order; } return nr_allocated; } static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; bool nofail = gfp_mask & __GFP_NOFAIL; unsigned long addr = (unsigned long)area->addr; unsigned long size = get_vm_area_size(area); unsigned long array_size; unsigned int nr_small_pages = size >> PAGE_SHIFT; unsigned int page_order; unsigned int flags; int ret; array_size = (unsigned long)nr_small_pages * sizeof(struct page *); if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node, area->caller); } else { area->pages = kmalloc_node_noprof(array_size, nested_gfp, node); } if (!area->pages) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocated page array size %lu", nr_small_pages * PAGE_SIZE, array_size); free_vm_area(area); return NULL; } set_vm_area_page_order(area, page_shift - PAGE_SHIFT); page_order = vm_area_page_order(area); area->nr_pages = vm_area_alloc_pages(gfp_mask | __GFP_NOWARN, node, page_order, nr_small_pages, area->pages); atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) { int i; for (i = 0; i < area->nr_pages; i++) mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); } /* * If not enough pages were obtained to accomplish an * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { /* * vm_area_alloc_pages() can fail due to insufficient memory but * also:- * * - a pending fatal signal * - insufficient huge page-order pages * * Since we always retry allocations at order-0 in the huge page * case a warning for either is spurious. */ if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocate pages", area->nr_pages * PAGE_SIZE); goto fail; } /* * page tables allocations ignore external gfp mask, enforce it * by the scope API */ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) flags = memalloc_nofs_save(); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) flags = memalloc_noio_save(); do { ret = vmap_pages_range(addr, addr + size, prot, area->pages, page_shift); if (nofail && (ret < 0)) schedule_timeout_uninterruptible(1); } while (nofail && (ret < 0)); if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) memalloc_nofs_restore(flags); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) memalloc_noio_restore(flags); if (ret < 0) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to map pages", area->nr_pages * PAGE_SIZE); goto fail; } return area->addr; fail: vfree(area->addr); return NULL; } /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @start: vm area range start * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Please note that the full set of gfp * flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all * supported. * Zone modifiers are not supported. From the reclaim modifiers * __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported) * and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and * __GFP_RETRY_MAYFAIL are not supported). * * __GFP_NOWARN can be used to suppress failures messages. * * Map them into contiguous kernel virtual space, using a pagetable * protection of @prot. * * Return: the address of the area or %NULL on failure */ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { struct vm_struct *area; void *ret; kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; unsigned long real_size = size; unsigned long real_align = align; unsigned int shift = PAGE_SHIFT; if (WARN_ON_ONCE(!size)) return NULL; if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, exceeds total pages", real_size); return NULL; } if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { unsigned long size_per_node; /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in * their allocations due to apply_to_page_range not * supporting them. */ size_per_node = size; if (node == NUMA_NO_NODE) size_per_node /= num_online_nodes(); if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE) shift = PMD_SHIFT; else shift = arch_vmap_pte_supported_shift(size_per_node); align = max(real_align, 1UL << shift); size = ALIGN(real_size, 1UL << shift); } again: area = __get_vm_area_node(real_size, align, shift, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) { bool nofail = gfp_mask & __GFP_NOFAIL; warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, vm_struct allocation failed%s", real_size, (nofail) ? ". Retrying." : ""); if (nofail) { schedule_timeout_uninterruptible(1); goto again; } goto fail; } /* * Prepare arguments for __vmalloc_area_node() and * kasan_unpoison_vmalloc(). */ if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) { if (kasan_hw_tags_enabled()) { /* * Modify protection bits to allow tagging. * This must be done before mapping. */ prot = arch_vmap_pgprot_tagged(prot); /* * Skip page_alloc poisoning and zeroing for physical * pages backing VM_ALLOC mapping. Memory is instead * poisoned and zeroed by kasan_unpoison_vmalloc(). */ gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO; } /* Take note that the mapping is PAGE_KERNEL. */ kasan_flags |= KASAN_VMALLOC_PROT_NORMAL; } /* Allocate physical pages and map them into vmalloc space. */ ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!ret) goto fail; /* * Mark the pages as accessible, now that they are mapped. * The condition for setting KASAN_VMALLOC_INIT should complement the * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check * to make sure that memory is initialized under the same conditions. * Tag-based KASAN modes only assign tags to normal non-executable * allocations, see __kasan_unpoison_vmalloc(). */ kasan_flags |= KASAN_VMALLOC_VM_ALLOC; if (!want_init_on_free() && want_init_on_alloc(gfp_mask) && (gfp_mask & __GFP_SKIP_ZERO)) kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ area->addr = kasan_unpoison_vmalloc(area->addr, real_size, kasan_flags); /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. * Now, it is fully initialized, so remove this flag here. */ clear_vm_uninitialized_flag(area); size = PAGE_ALIGN(size); if (!(vm_flags & VM_DEFER_KMEMLEAK)) kmemleak_vmalloc(area, size, gfp_mask); return area->addr; fail: if (shift > PAGE_SHIFT) { shift = PAGE_SHIFT; align = real_align; size = real_size; goto again; } return NULL; } /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted * with mm people. * * Return: pointer to the allocated memory or %NULL on error */ void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* * This is only for performance analysis of vmalloc and stress purpose. * It is required by vmalloc test module, therefore do not use it other * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc_noprof); /** * vmalloc - allocate virtually contiguous memory * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_noprof); /** * vmalloc_huge - allocate virtually contiguous memory, allow huge pages * @size: allocation size * @gfp_mask: flags for the page level allocator * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * If @size is greater than or equal to PMD_SIZE, allow using * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(vmalloc_huge_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_user_noprof); /** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_node_noprof); #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else /* * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_user_noprof); /* * Atomically zero bytes in the iterator. * * Returns the number of zeroed bytes. */ static size_t zero_iter(struct iov_iter *iter, size_t count) { size_t remains = count; while (remains > 0) { size_t num, copied; num = min_t(size_t, remains, PAGE_SIZE); copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter); remains -= copied; if (copied < num) break; } return count - remains; } /* * small helper routine, copy contents to iter from addr. * If the page is not present, fill zero. * * Returns the number of copied bytes. */ static size_t aligned_vread_iter(struct iov_iter *iter, const char *addr, size_t count) { size_t remains = count; struct page *page; while (remains > 0) { unsigned long offset, length; size_t copied = 0; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > remains) length = remains; page = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need lock. But * adding lock here means that we need to add overhead of * vmalloc()/vfree() calls for this _debug_ interface, rarely * used. Instead of that, we'll use an local mapping via * copy_page_to_iter_nofault() and accept a small overhead in * this access function. */ if (page) copied = copy_page_to_iter_nofault(page, offset, length, iter); else copied = zero_iter(iter, length); addr += copied; remains -= copied; if (copied != length) break; } return count - remains; } /* * Read from a vm_map_ram region of memory. * * Returns the number of copied bytes. */ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, size_t count, unsigned long flags) { char *start; struct vmap_block *vb; struct xarray *xa; unsigned long offset; unsigned int rs, re; size_t remains, n; /* * If it's area created by vm_map_ram() interface directly, but * not further subdividing and delegating management to vmap_block, * handle it here. */ if (!(flags & VMAP_BLOCK)) return aligned_vread_iter(iter, addr, count); remains = count; /* * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions. */ xa = addr_to_vb_xa((unsigned long) addr); vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); if (!vb) goto finished_zero; spin_lock(&vb->lock); if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) { spin_unlock(&vb->lock); goto finished_zero; } for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) { size_t copied; if (remains == 0) goto finished; start = vmap_block_vaddr(vb->va->va_start, rs); if (addr < start) { size_t to_zero = min_t(size_t, start - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } /*it could start reading from the middle of used region*/ offset = offset_in_page(addr); n = ((re - rs + 1) << PAGE_SHIFT) - offset; if (n > remains) n = remains; copied = aligned_vread_iter(iter, start + offset, n); addr += copied; remains -= copied; if (copied != n) goto finished; } spin_unlock(&vb->lock); finished_zero: /* zero-fill the left dirty or free regions */ return count - remains + zero_iter(iter, remains); finished: /* We couldn't copy/zero everything */ spin_unlock(&vb->lock); return count - remains; } /** * vread_iter() - read vmalloc area in a safe way to an iterator. * @iter: the iterator to which data should be written. * @addr: vm address. * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range * of [addr...addr+count) includes some valid address, data is copied to * proper area of @buf. If there are memory holes, they'll be zero-filled. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; char *vaddr; size_t n, size, flags, remains; unsigned long next; addr = kasan_reset_tag(addr); /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; remains = count; vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va); if (!vn) goto finished_zero; /* no intersects with alive vmap_area */ if ((unsigned long)addr + remains <= va->va_start) goto finished_zero; do { size_t copied; if (remains == 0) goto finished; vm = va->vm; flags = va->flags & VMAP_FLAGS_MASK; /* * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need * be set together with VMAP_RAM. */ WARN_ON(flags == VMAP_BLOCK); if (!vm && !flags) goto next_va; if (vm && (vm->flags & VM_UNINITIALIZED)) goto next_va; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); vaddr = (char *) va->va_start; size = vm ? get_vm_area_size(vm) : va_size(va); if (addr >= vaddr + size) goto next_va; if (addr < vaddr) { size_t to_zero = min_t(size_t, vaddr - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } n = vaddr + size - addr; if (n > remains) n = remains; if (flags & VMAP_RAM) copied = vmap_ram_vread_iter(iter, addr, n, flags); else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE)))) copied = aligned_vread_iter(iter, addr, n); else /* IOREMAP | SPARSE area is treated as memory hole */ copied = zero_iter(iter, n); addr += copied; remains -= copied; if (copied != n) goto finished; next_va: next = va->va_end; spin_unlock(&vn->busy.lock); } while ((vn = find_vmap_area_exceed_addr_lock(next, &va))); finished_zero: if (vn) spin_unlock(&vn->busy.lock); /* zero-fill memory holes */ return count - remains + zero_iter(iter, remains); finished: /* Nothing remains, or We couldn't copy/zero everything. */ if (vn) spin_unlock(&vn->busy.lock); return count - remains; } /** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure * * This function checks that @kaddr is a valid vmalloc'ed area, * and that it is big enough to cover the range starting at * @uaddr in @vma. Will return failure if that criteria isn't * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size) { struct vm_struct *area; unsigned long off; unsigned long end_index; if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) return -EINVAL; size = PAGE_ALIGN(size); if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) return -EINVAL; if (check_add_overflow(size, off, &end_index) || end_index > get_vm_area_size(area)) return -EINVAL; kaddr += off; do { struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; kaddr += PAGE_SIZE; size -= PAGE_SIZE; } while (size > 0); vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); return 0; } /** * remap_vmalloc_range - map vmalloc pages to userspace * @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map * * Returns: 0 for success, -Exxx on failure * * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP static struct vmap_area *node_to_va(struct rb_node *n) { return rb_entry_safe(n, struct vmap_area, rb_node); } /** * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to * @addr: target address * * Returns: vmap_area if it is found. If there is no such area * the first highest(reverse order) vmap_area is returned * i.e. va->va_start < addr && va->va_end < addr or NULL * if there are no any areas before @addr. */ static struct vmap_area * pvm_find_va_enclose_addr(unsigned long addr) { struct vmap_area *va, *tmp; struct rb_node *n; n = free_vmap_area_root.rb_node; va = NULL; while (n) { tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_start <= addr) { va = tmp; if (tmp->va_end >= addr) break; n = n->rb_right; } else { n = n->rb_left; } } return va; } /** * pvm_determine_end_from_reverse - find the highest aligned address * of free block below VMALLOC_END * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. * @align: alignment for required highest address * * Returns: determined end address within vmap_area */ static unsigned long pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align) { unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); unsigned long addr; if (likely(*va)) { list_for_each_entry_from_reverse((*va), &free_vmap_area_list, list) { addr = min((*va)->va_end & ~(align - 1), vmalloc_end); if ((*va)->va_start < addr) return addr; } } return 0; } /** * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator * @offsets: array containing offset of each area * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to * be scattered pretty far, distance between two areas easily going up * to gigabytes. To avoid interacting with regular vmallocs, these * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans free blocks from the end looking * for matching base. While scanning, if any of the areas do not fit the * base address is pulled down to fit the area. Scanning is repeated till * all the areas fit and then all necessary data structures are inserted * and the result is returned. */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { start = offsets[area]; end = start + sizes[area]; /* is everything aligned properly? */ BUG_ON(!IS_ALIGNED(offsets[area], align)); BUG_ON(!IS_ALIGNED(sizes[area], align)); /* detect the area with the highest address */ if (start > offsets[last_area]) last_area = area; for (area2 = area + 1; area2 < nr_vms; area2++) { unsigned long start2 = offsets[area2]; unsigned long end2 = start2 + sizes[area2]; BUG_ON(start2 < end && start < end2); } } last_end = offsets[last_area] + sizes[last_area]; if (vmalloc_end - vmalloc_start < last_end) { WARN_ON(true); return NULL; } vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL); vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL); if (!vas || !vms) goto err_free2; for (area = 0; area < nr_vms; area++) { vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL); vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free; } retry: spin_lock(&free_vmap_area_lock); /* start scanning - we scan from the top, begin with the last area */ area = term_area = last_area; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(vmalloc_end); base = pvm_determine_end_from_reverse(&va, align) - end; while (true) { /* * base might have underflowed, add last_end before * comparing. */ if (base + last_end < vmalloc_start + last_end) goto overflow; /* * Fitting base has not been found. */ if (va == NULL) goto overflow; /* * If required width exceeds current VA block, move * base downwards and then recheck. */ if (base + end > va->va_end) { base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * If this VA does not fit, move base downwards and recheck. */ if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * This area fits, move on to the previous one. If * the previous one is the terminal one, we're done. */ area = (area + nr_vms - 1) % nr_vms; if (area == term_area) break; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(base + end); } /* we've found a fitting base, insert all va's */ for (area = 0; area < nr_vms; area++) { int ret; start = base + offsets[area]; size = sizes[area]; va = pvm_find_va_enclose_addr(start); if (WARN_ON_ONCE(va == NULL)) /* It is a BUG(), but trigger recovery instead. */ goto recovery; ret = va_clip(&free_vmap_area_root, &free_vmap_area_list, va, start, size); if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; /* Allocated area. */ va = vas[area]; va->va_start = start; va->va_end = start + size; } spin_unlock(&free_vmap_area_lock); /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) goto err_free_shadow; } /* insert all vm's */ for (area = 0; area < nr_vms; area++) { struct vmap_node *vn = addr_to_node(vas[area]->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); spin_unlock(&vn->busy.lock); } /* * Mark allocated areas as accessible. Do it now as a best-effort * approach, as they can be mapped outside of vmalloc code. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ for (area = 0; area < nr_vms; area++) vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; recovery: /* * Remove previously allocated areas. There is no * need in removing these areas from the busy tree, * because they are inserted only on the final step * and when pcpu_get_vm_areas() is success. */ while (area--) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); vas[area] = NULL; } overflow: spin_unlock(&free_vmap_area_lock); if (!purged) { reclaim_and_purge_vmap_areas(); purged = true; /* Before "retry", check if we recover. */ for (area = 0; area < nr_vms; area++) { if (vas[area]) continue; vas[area] = kmem_cache_zalloc( vmap_area_cachep, GFP_KERNEL); if (!vas[area]) goto err_free; } goto retry; } err_free: for (area = 0; area < nr_vms; area++) { if (vas[area]) kmem_cache_free(vmap_area_cachep, vas[area]); kfree(vms[area]); } err_free2: kfree(vas); kfree(vms); return NULL; err_free_shadow: spin_lock(&free_vmap_area_lock); /* * We release all the vmalloc shadows, even the ones for regions that * hadn't been successfully added. This relies on kasan_release_vmalloc * being able to tolerate this case. */ for (area = 0; area < nr_vms; area++) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); vas[area] = NULL; kfree(vms[area]); } spin_unlock(&free_vmap_area_lock); kfree(vas); kfree(vms); return NULL; } /** * pcpu_free_vm_areas - free vmalloc areas for percpu allocator * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() * @nr_vms: the number of allocated areas * * Free vm_structs and the array allocated by pcpu_get_vm_areas(). */ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { int i; for (i = 0; i < nr_vms; i++) free_vm_area(vms[i]); kfree(vms); } #endif /* CONFIG_SMP */ #ifdef CONFIG_PRINTK bool vmalloc_dump_obj(void *object) { const void *caller; struct vm_struct *vm; struct vmap_area *va; struct vmap_node *vn; unsigned long addr; unsigned int nr_pages; addr = PAGE_ALIGN((unsigned long) object); vn = addr_to_node(addr); if (!spin_trylock(&vn->busy.lock)) return false; va = __find_vmap_area(addr, &vn->busy.root); if (!va || !va->vm) { spin_unlock(&vn->busy.lock); return false; } vm = va->vm; addr = (unsigned long) vm->addr; caller = vm->caller; nr_pages = vm->nr_pages; spin_unlock(&vn->busy.lock); pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", nr_pages, addr, caller); return true; } #endif #ifdef CONFIG_PROC_FS static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { unsigned int nr, *counters = m->private; unsigned int step = 1U << vm_area_page_order(v); if (!counters) return; if (v->flags & VM_UNINITIALIZED) return; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr += step) counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } } static void show_purge_info(struct seq_file *m) { struct vmap_node *vn; struct vmap_area *va; int i; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->lazy.lock); list_for_each_entry(va, &vn->lazy.head, list) { seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); } spin_unlock(&vn->lazy.lock); } } static int vmalloc_info_show(struct seq_file *m, void *p) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; int i; for (i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); list_for_each_entry(va, &vn->busy.head, list) { if (!va->vm) { if (va->flags & VMAP_RAM) seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); continue; } v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); if (v->caller) seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%pa", &v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); if (v->flags & VM_SPARSE) seq_puts(m, " sparse"); if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) seq_puts(m, " user"); if (v->flags & VM_DMA_COHERENT) seq_puts(m, " dma-coherent"); if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); } /* * As a final step, dump "unpurged" areas. */ show_purge_info(m); return 0; } static int __init proc_vmalloc_init(void) { void *priv_data = NULL; if (IS_ENABLED(CONFIG_NUMA)) priv_data = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); proc_create_single_data("vmallocinfo", 0400, NULL, vmalloc_info_show, priv_data); return 0; } module_init(proc_vmalloc_init); #endif static void __init vmap_init_free_space(void) { unsigned long vmap_start = 1; const unsigned long vmap_end = ULONG_MAX; struct vmap_area *free; struct vm_struct *busy; /* * B F B B B F * -|-----|.....|-----|-----|-----|.....|- * | The KVA space | * |<--------------------------------->| */ for (busy = vmlist; busy; busy = busy->next) { if ((unsigned long) busy->addr - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = (unsigned long) busy->addr; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } vmap_start = (unsigned long) busy->addr + busy->size; } if (vmap_end - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = vmap_end; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } } static void vmap_init_nodes(void) { struct vmap_node *vn; int i, n; #if BITS_PER_LONG == 64 /* * A high threshold of max nodes is fixed and bound to 128, * thus a scale factor is 1 for systems where number of cores * are less or equal to specified threshold. * * As for NUMA-aware notes. For bigger systems, for example * NUMA with multi-sockets, where we can end-up with thousands * of cores in total, a "sub-numa-clustering" should be added. * * In this case a NUMA domain is considered as a single entity * with dedicated sub-nodes in it which describe one group or * set of cores. Therefore a per-domain purging is supposed to * be added as well as a per-domain balancing. */ n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); if (n > 1) { vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN); if (vn) { /* Node partition is 16 pages. */ vmap_zone_size = (1 << 4) * PAGE_SIZE; nr_vmap_nodes = n; vmap_nodes = vn; } else { pr_err("Failed to allocate an array. Disable a node layer\n"); } } #endif for (n = 0; n < nr_vmap_nodes; n++) { vn = &vmap_nodes[n]; vn->busy.root = RB_ROOT; INIT_LIST_HEAD(&vn->busy.head); spin_lock_init(&vn->busy.lock); vn->lazy.root = RB_ROOT; INIT_LIST_HEAD(&vn->lazy.head); spin_lock_init(&vn->lazy.lock); for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { INIT_LIST_HEAD(&vn->pool[i].head); WRITE_ONCE(vn->pool[i].len, 0); } spin_lock_init(&vn->pool_lock); } } static unsigned long vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; struct vmap_node *vn; int i, j; for (count = 0, i = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i]; for (j = 0; j < MAX_VA_SIZE_PAGES; j++) count += READ_ONCE(vn->pool[j].len); } return count ? count : SHRINK_EMPTY; } static unsigned long vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { int i; for (i = 0; i < nr_vmap_nodes; i++) decay_va_pool_node(&vmap_nodes[i], true); return SHRINK_STOP; } void __init vmalloc_init(void) { struct shrinker *vmap_node_shrinker; struct vmap_area *va; struct vmap_node *vn; struct vm_struct *tmp; int i; /* * Create the cache for vmap_area objects. */ vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); for_each_possible_cpu(i) { struct vmap_block_queue *vbq; struct vfree_deferred *p; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); p = &per_cpu(vfree_deferred, i); init_llist_head(&p->list); INIT_WORK(&p->wq, delayed_vfree_work); xa_init(&vbq->vmap_blocks); } /* * Setup nodes before importing vmlist. */ vmap_init_nodes(); /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (WARN_ON_ONCE(!va)) continue; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; va->vm = tmp; vn = addr_to_node(va->va_start); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); } /* * Now we can initialize a free vmap space. */ vmap_init_free_space(); vmap_initialized = true; vmap_node_shrinker = shrinker_alloc(0, "vmap-node"); if (!vmap_node_shrinker) { pr_err("Failed to allocate vmap-node shrinker!\n"); return; } vmap_node_shrinker->count_objects = vmap_node_shrink_count; vmap_node_shrinker->scan_objects = vmap_node_shrink_scan; shrinker_register(vmap_node_shrinker); } |
| 1821 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif #define PERF_GUEST_ACTIVE 0x01 #define PERF_GUEST_USER 0x02 struct perf_guest_info_callbacks { unsigned int (*state)(void); unsigned long (*get_ip)(void); unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <linux/rhashtable-types.h> #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> #include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * hw_perf_event::flag values * * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ #define PERF_EVENT_FLAG_ARCH 0x000fffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; struct perf_event_pmu_context; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x0001 #define PERF_PMU_CAP_NO_NMI 0x0002 #define PERF_PMU_CAP_AUX_NO_SG 0x0004 #define PERF_PMU_CAP_EXTENDED_REGS 0x0008 #define PERF_PMU_CAP_EXCLUSIVE 0x0010 #define PERF_PMU_CAP_ITRACE 0x0020 #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 struct perf_output_handle; #define PMU_NULL_DEV ((void *)(~0UL)) /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; struct device *parent; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_pmu_context __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to 0 (see * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_pmu_context *prev_epc, struct perf_event_pmu_context *next_epc); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Skip programming this PMU on the given CPU. Typically needed for * big.LITTLE things. */ bool (*filter) (struct pmu *pmu, int cpu); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 struct bpf_prog; struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; /* * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex * as such iteration must hold either lock. However, since ctx->lock is an IRQ * safe lock, and is only held by the CPU doing the modification, having IRQs * disabled is sufficient since it will hold-off the IPIs. */ #ifdef CONFIG_PROVE_LOCKING #define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) #else #define lockdep_assert_event_ctx(event) #endif #define for_each_sibling_event(sibling, event) \ lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. * Whereas event->pmu_ctx->pmu may point to other pmu when group of * different pmu events is created. */ struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event * is added. This pmu_ctx can be of other pmu for sw event when that * sw event is part of a group which also contains non-sw events. */ struct perf_event_pmu_context *pmu_ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; struct rcuwait pending_work_wait; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; struct bpf_prog *prog; u64 bpf_cookie; #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; /* * Certain events gets forwarded to another pmu internally by over- * writing kernel copy of event->attr.type without user being aware * of it. event->orig_type contains original 'type' requested by * user. */ __u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; /* * ,-----------------------[1:n]------------------------. * V V * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event * | | * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed * (similar to perf_event_context). Locking is as if it were a member of * perf_event_context; specifically: * * modification, both: ctx->mutex && ctx->lock * reading, either: ctx->mutex || ctx->lock * * There is one exception to this; namely put_pmu_ctx() isn't always called * with ctx->mutex held; this means that as long as we can guarantee the epc * has events the above rules hold. * * Specificially, sys_perf_event_open()'s group_leader case depends on * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. * * perf_event holds a refcount on perf_event_context * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; struct perf_event_context *ctx; struct list_head pmu_ctx_entry; struct list_head pinned_active; struct list_head flexible_active; /* Used to avoid freeing per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; unsigned int nr_cgroups; unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; void *task_ctx_data; /* pmu specific data */ /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to * events not necessary to be active due to scheduling constraints, * such as cgroups. */ int rotate_necessary; }; static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) { return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); } struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head pmu_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; int nr_events; int nr_user; int is_active; int nr_task_data; int nr_stat; int nr_freq; int rotate_disable; refcount_t refcount; /* event <-> ctx */ struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif struct rcu_head rcu_head; /* * Sum (event->pending_work + event->pending_work) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_pending; }; struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; struct list_head sched_cb_entry; int sched_cb_usage; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; }; /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int online; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; #endif /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern struct perf_event_context *perf_cpu_task_ctx(void); extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child, u64 clone_flags); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); static inline bool branch_sample_no_flags(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; } static inline bool branch_sample_no_cycles(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; } static inline bool branch_sample_type(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; } static inline bool branch_sample_hw_index(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; } static inline bool branch_sample_priv(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; } static inline bool branch_sample_counters(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS; } static inline bool branch_sample_call_stack(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } struct perf_sample_data { /* * Fields set by perf_sample_data_init() unconditionally, * group so as to minimize the cachelines touched. */ u64 sample_flags; u64 period; u64 dyn_size; /* * Fields commonly set by __perf_event_header__init_id(), * group so as to minimize the cachelines touched. */ u64 type; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; struct { u32 cpu; u32 reserved; } cpu_entry; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 ip; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 stream_id; u64 cgroup; u64 addr; u64 phys_addr; u64 data_page_size; u64 code_page_size; u64 aux_size; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA) |\ PERF_MEM_S(LVLNUM, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; data->dyn_size = 0; if (addr) { data->addr = addr; data->sample_flags |= PERF_SAMPLE_ADDR; } } static inline void perf_sample_save_callchain(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs) { int size = 1; data->callchain = perf_callchain(event, regs); size += data->callchain->nr; data->dyn_size += size * sizeof(u64); data->sample_flags |= PERF_SAMPLE_CALLCHAIN; } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; do { sum += frag->size; if (perf_raw_frag_last(frag)) break; frag = frag->next; } while (1); size = round_up(sum + sizeof(u32), sizeof(u64)); raw->size = size - sizeof(u32); frag->pad = raw->size - sum; data->raw = raw; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_RAW; } static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, u64 *brs_cntr) { int size = sizeof(u64); /* nr */ if (branch_sample_hw_index(event)) size += sizeof(u64); size += brs->nr * sizeof(struct perf_branch_entry); /* * The extension space for counters is appended after the * struct perf_branch_stack. It is used to store the occurrences * of events of each branch. */ if (brs_cntr) size += brs->nr * sizeof(u64); data->br_stack = brs; data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } static inline u32 perf_sample_data_size(struct perf_sample_data *data, struct perf_event *event) { u32 size = sizeof(struct perf_event_header); size += event->header_size + event->id_header_size; size += data->dyn_size; return size; } /* * Clear all bitfields in the perf_branch_entry. * The to and from fields are not cleared because they are * systematically modified by caller. */ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) { br->mispred = 0; br->predicted = 0; br->in_tx = 0; br->abort = 0; br->cycles = 0; br->type = 0; br->spec = PERF_BR_SPEC_NA; br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern void perf_prepare_header(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { perf_overflow_handler_t overflow_handler = event->overflow_handler; if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } extern struct static_key_false perf_sched_events; static __always_inline bool __perf_sw_enabled(int swevt) { return static_key_false(&perf_swevent_enabled[swevt]); } static inline void perf_event_task_migrate(struct task_struct *task) { if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); #ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); #endif if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); #ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); static inline unsigned int perf_guest_state(void) { return static_call(__perf_guest_state)(); } static inline unsigned long perf_guest_get_ip(void) { return static_call(__perf_guest_get_ip)(); } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return static_call(__perf_guest_handle_intel_pt_intr)(); } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); #else static inline unsigned int perf_guest_state(void) { return 0; } static inline unsigned long perf_guest_get_ip(void) { return 0; } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } #endif /* CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) { /* Only the parent has fasync state */ if (event->parent) event = event->parent; return &event->fasync; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr) #define PMU_FORMAT_ATTR_SHOW(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ #define PMU_FORMAT_ATTR(_name, _format) \ PMU_FORMAT_ATTR_SHOW(_name, _format) \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); /* * Snapshot branch stack on software events. * * Branch stack can be very useful in understanding software events. For * example, when a long function, e.g. sys_perf_event_open, returns an * errno, it is not obvious why the function failed. Branch stack could * provide very helpful information in this type of scenarios. * * On software event, it is necessary to stop the hardware branch recorder * fast. Otherwise, the hardware register/buffer will be flushed with * entries of the triggering event. Therefore, static call is used to * stop the hardware recorder. */ /* * cnt is the number of entries allocated for entries. * Return number of entries copied to . */ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); #ifndef PERF_NEEDS_LOPWR_CB static inline void perf_lopwr_cb(bool mode) { } #endif #endif /* _LINUX_PERF_EVENT_H */ |
| 3 3 3 2 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 4 4 4 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 3 3 3 3 3 3 3 2 3 3 3 3 3 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Multicast support for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c */ /* Changes: * * yoshfuji : fix format of router-alert option * YOSHIFUJI Hideaki @USAGI: * Fixed source address for MLD message based on * <draft-ietf-magma-mld-source-05.txt>. * YOSHIFUJI Hideaki @USAGI: * - Ignore Queries for invalid addresses. * - MLD for link-local addresses. * David L Stevens <dlstevens@us.ibm.com>: * - MLDv2 support */ #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/jiffies.h> #include <linux/net.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/route.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/workqueue.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/inet_common.h> #include <net/ip6_checksum.h> /* Ensure that we have struct in6_addr aligned on 32bit word. */ static int __mld2_query_bugs[] __attribute__((__unused__)) = { BUILD_BUG_ON_ZERO(offsetof(struct mld2_query, mld2q_srcs) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_report, mld2r_grec) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct workqueue_struct *mld_wq; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); static void mld_mca_work(struct work_struct *work); static void mld_ifc_event(struct inet6_dev *idev); static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ #define MLD_QI_DEFAULT (125 * HZ) /* RFC3810, 9.3. Query Response Interval */ #define MLD_QRI_DEFAULT (10 * HZ) /* RFC3810, 8.1 Query Version Distinctions */ #define MLD_V1_QUERY_LEN 24 #define MLD_V2_QUERY_LEN_MIN 28 #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; /* * socket join on multicast group */ #define mc_dereference(e, idev) \ rcu_dereference_protected(e, lockdep_is_held(&(idev)->mc_lock)) #define sock_dereference(e, sk) \ rcu_dereference_protected(e, lockdep_sock_is_held(sk)) #define for_each_pmc_socklock(np, sk, pmc) \ for (pmc = sock_dereference((np)->ipv6_mc_list, sk); \ pmc; \ pmc = sock_dereference(pmc->next, sk)) #define for_each_pmc_rcu(np, pmc) \ for (pmc = rcu_dereference((np)->ipv6_mc_list); \ pmc; \ pmc = rcu_dereference(pmc->next)) #define for_each_psf_mclock(mc, psf) \ for (psf = mc_dereference((mc)->mca_sources, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_psf_rcu(mc, psf) \ for (psf = rcu_dereference((mc)->mca_sources); \ psf; \ psf = rcu_dereference(psf->sf_next)) #define for_each_psf_tomb(mc, psf) \ for (psf = mc_dereference((mc)->mca_tomb, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_mc_mclock(idev, mc) \ for (mc = mc_dereference((idev)->mc_list, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) #define for_each_mc_rcu(idev, mc) \ for (mc = rcu_dereference((idev)->mc_list); \ mc; \ mc = rcu_dereference(mc->next)) #define for_each_mc_tomb(idev, mc) \ for (mc = mc_dereference((idev)->mc_tomb, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) static int unsolicited_report_interval(struct inet6_dev *idev) { int iv; if (mld_in_v1_mode(idev)) iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int err; ASSERT_RTNL(); if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for_each_pmc_socklock(np, sk, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) return -EADDRINUSE; } mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); if (!mc_lst) return -ENOMEM; mc_lst->next = NULL; mc_lst->addr = *addr; if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else dev = __dev_get_by_index(net, ifindex); if (!dev) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = mode; RCU_INIT_POINTER(mc_lst->sflist, NULL); /* * now add/increase the group membership on the device */ err = __ipv6_dev_mc_inc(dev, addr, mode); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_sock_mc_join); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { return __ipv6_sock_mc_join(sk, ifindex, addr, mode); } /* * socket leave on multicast group */ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for (lnk = &np->ipv6_mc_list; (mc_lst = sock_dereference(*lnk, sk)) != NULL; lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } return -EADDRNOTAVAIL; } EXPORT_SYMBOL(ipv6_sock_mc_drop); static struct inet6_dev *ip6_mc_find_dev_rtnl(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; struct inet6_dev *idev = NULL; if (ifindex == 0) { struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else { dev = __dev_get_by_index(net, ifindex); } if (!dev) return NULL; idev = __in6_dev_get(dev); if (!idev) return NULL; if (idev->dead) return NULL; return idev; } void __ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); ASSERT_RTNL(); while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); } } void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!rcu_access_pointer(np->ipv6_mc_list)) return; rtnl_lock(); lock_sock(sk); __ipv6_sock_mc_close(sk); release_sock(sk); rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr) { struct in6_addr *source, *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; struct net *net = sock_net(sk); int i, j, rv; int leavegroup = 0; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; idev = ip6_mc_find_dev_rtnl(net, group, pgsr->gsr_interface); if (!idev) return -ENODEV; err = -EADDRNOTAVAIL; mutex_lock(&idev->mc_lock); for_each_pmc_socklock(inet6, sk, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (rcu_access_pointer(pmc->sflist)) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip6_mc_add_src(idev, group, omode, 0, NULL, 0); ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = sock_dereference(pmc->sflist, sk); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= sysctl_mld_max_msf) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip6_sf_socklist *newpsl; int count = IP6_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP6_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) /* There is an error in the address. */ goto done; } for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; psl->sl_count++; err = 0; /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: mutex_unlock(&idev->mc_lock); if (leavegroup) err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list) { const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, err; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; if (gsf->gf_fmode != MCAST_INCLUDE && gsf->gf_fmode != MCAST_EXCLUDE) return -EINVAL; idev = ip6_mc_find_dev_rtnl(net, group, gsf->gf_interface); if (!idev) return -ENODEV; err = 0; if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (gsf->gf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, gsf->gf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc; for (i = 0; i < newpsl->sl_count; ++i, ++list) { struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)list; newpsl->sl_addr[i] = psin6->sin6_addr; } mutex_lock(&idev->mc_lock); err = ip6_mc_add_src(idev, group, gsf->gf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { mutex_unlock(&idev->mc_lock); sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } mutex_unlock(&idev->mc_lock); } else { newpsl = NULL; mutex_lock(&idev->mc_lock); ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); } mutex_lock(&idev->mc_lock); psl = sock_dereference(pmc->sflist, sk); if (psl) { ip6_mc_del_src(idev, group, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); mutex_unlock(&idev->mc_lock); kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: if (leavegroup) err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; } int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { struct ipv6_pinfo *inet6 = inet6_sk(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; int i, count, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; /* changes to the ipv6_mc_list require the socket lock and * rtnl lock. We have the socket lock, so reading the list is safe. */ for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; psin6 = (struct sockaddr_in6 *)&ss; memset(&ss, 0, sizeof(ss)); psin6->sin6_family = AF_INET6; psin6->sin6_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr) { const struct ipv6_pinfo *np = inet6_sk(sk); const struct ipv6_mc_socklist *mc; const struct ip6_sf_socklist *psl; bool rv = true; rcu_read_lock(); for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { rcu_read_unlock(); return inet6_test_bit(MC6_ALL, sk); } psl = rcu_dereference(mc->sflist); if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; } else { int i; for (i = 0; i < psl->sl_count; i++) { if (ipv6_addr_equal(&psl->sl_addr[i], src_addr)) break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) rv = false; } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } /* else v2 */ /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we * should not send filter-mode change record as the mode * should be from IN() to IN(A). */ if (mc->mca_sfmode == MCAST_EXCLUDE) mc->mca_crcount = mc->idev->mc_qrv; mld_ifc_event(mc->idev); } /* called with mc_lock */ static void igmp6_group_dropped(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) return; if (!mc->idev->dead) igmp6_leave_group(mc); if (cancel_delayed_work(&mc->mca_work)) refcount_dec(&mc->mca_refcnt); } /* * deleted ifmcaddr6 manipulation * called with mc_lock */ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc; /* this is an "ifmcaddr6" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); if (!pmc) return; pmc->idev = im->idev; in6_dev_hold(idev); pmc->mca_addr = im->mca_addr; pmc->mca_crcount = idev->mc_qrv; pmc->mca_sfmode = im->mca_sfmode; if (pmc->mca_sfmode == MCAST_INCLUDE) { struct ip6_sf_list *psf; rcu_assign_pointer(pmc->mca_tomb, mc_dereference(im->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_sources, mc_dereference(im->mca_sources, idev)); RCU_INIT_POINTER(im->mca_tomb, NULL); RCU_INIT_POINTER(im->mca_sources, NULL); for_each_psf_mclock(pmc, psf) psf->sf_crcount = pmc->mca_crcount; } rcu_assign_pointer(pmc->next, idev->mc_tomb); rcu_assign_pointer(idev->mc_tomb, pmc); } /* called with mc_lock */ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ip6_sf_list *psf, *sources, *tomb; struct in6_addr *pmca = &im->mca_addr; struct ifmcaddr6 *pmc, *pmc_prev; pmc_prev = NULL; for_each_mc_tomb(idev, pmc) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc->next); else rcu_assign_pointer(idev->mc_tomb, pmc->next); } if (pmc) { im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { tomb = rcu_replace_pointer(im->mca_tomb, mc_dereference(pmc->mca_tomb, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_tomb, tomb); sources = rcu_replace_pointer(im->mca_sources, mc_dereference(pmc->mca_sources, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_sources, sources); for_each_psf_mclock(im, psf) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); ip6_mc_clear_src(pmc); kfree_rcu(pmc, rcu); } } /* called with mc_lock */ static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; pmc = mc_dereference(idev->mc_tomb, idev); RCU_INIT_POINTER(idev->mc_tomb, NULL); for (; pmc; pmc = nextpmc) { nextpmc = mc_dereference(pmc->next, idev); ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } /* clear dead sources, too */ for_each_mc_mclock(idev, pmc) { struct ip6_sf_list *psf, *psf_next; psf = mc_dereference(pmc->mca_tomb, idev); RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (; psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); kfree_rcu(psf, rcu); } } } static void mld_clear_query(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_query_lock); } static void mld_clear_report(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_report_lock); } static void mca_get(struct ifmcaddr6 *mc) { refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree_rcu(mc, rcu); } } /* called with mc_lock */ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return NULL; INIT_DELAYED_WORK(&mc->mca_work, mld_mca_work); mc->mca_addr = *addr; mc->idev = idev; /* reference taken by caller */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; refcount_set(&mc->mca_refcnt, 1); mc->mca_sfmode = mode; mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) mc->mca_flags |= MAF_NOREPORT; return mc; } /* * device multicast group inc (add if not found) */ static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; struct inet6_dev *idev; ASSERT_RTNL(); /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (!idev) return -EINVAL; if (idev->dead) { in6_dev_put(idev); return -ENODEV; } mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return 0; } } mc = mca_alloc(idev, addr, mode); if (!mc) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENOMEM; } rcu_assign_pointer(mc->next, idev->mc_list); rcu_assign_pointer(idev->mc_list, mc); mca_get(mc); mld_del_delrec(idev, mc); igmp6_group_added(mc); mutex_unlock(&idev->mc_lock); ma_put(mc); return 0; } int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del */ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, __rcu **map; ASSERT_RTNL(); mutex_lock(&idev->mc_lock); for (map = &idev->mc_list; (ma = mc_dereference(*map, idev)); map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { if (--ma->mca_users == 0) { *map = ma->next; igmp6_group_dropped(ma); ip6_mc_clear_src(ma); mutex_unlock(&idev->mc_lock); ma_put(ma); return 0; } mutex_unlock(&idev->mc_lock); return 0; } } mutex_unlock(&idev->mc_lock); return -ENOENT; } int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; int err; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) err = -ENODEV; else err = __ipv6_dev_mc_dec(idev, addr); return err; } EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; bool rv = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { for_each_mc_rcu(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, group)) break; } if (mc) { if (src_addr && !ipv6_addr_any(src_addr)) { struct ip6_sf_list *psf; for_each_psf_rcu(mc, psf) { if (ipv6_addr_equal(&psf->sf_addr, src_addr)) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != mc->mca_sfcount[MCAST_EXCLUDE]; else rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0; } else rv = true; /* don't filter unspecified source */ } } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void mld_gq_start_work(struct inet6_dev *idev) { unsigned long tv = get_random_u32_below(idev->mc_maxdelay); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_gq_stop_work(struct inet6_dev *idev) { idev->mc_gq_running = 0; if (cancel_delayed_work(&idev->mc_gq_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_ifc_stop_work(struct inet6_dev *idev) { idev->mc_ifc_count = 0; if (cancel_delayed_work(&idev->mc_ifc_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); } static void mld_dad_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work(&idev->mc_dad_work)) __in6_dev_put(idev); } static void mld_query_stop_work(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); if (cancel_delayed_work(&idev->mc_query_work)) __in6_dev_put(idev); spin_unlock_bh(&idev->mc_query_lock); } static void mld_report_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work_sync(&idev->mc_report_work)) __in6_dev_put(idev); } /* * IGMP handling (alias multicast ICMPv6 messages) * called with mc_lock */ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) { unsigned long delay = resptime; /* Do not start work for these addresses */ if (ipv6_addr_is_ll_all_nodes(&ma->mca_addr) || IPV6_ADDR_MC_SCOPE(&ma->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (delay >= resptime) delay = get_random_u32_below(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } /* mark EXCLUDE-mode sources * called with mc_lock */ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { scount++; break; } } } pmc->mca_flags &= ~MAF_GSQUERY; if (scount == nsrcs) /* all sources excluded */ return false; return true; } /* called with mc_lock */ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; if (pmc->mca_sfmode == MCAST_EXCLUDE) return mld_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } } } if (!scount) { pmc->mca_flags &= ~MAF_GSQUERY; return false; } pmc->mca_flags |= MAF_GSQUERY; return true; } static int mld_force_mld_version(const struct inet6_dev *idev) { const struct net *net = dev_net(idev->dev); int all_force; all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 2; } static bool mld_in_v1_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 1; } static bool mld_in_v1_mode(const struct inet6_dev *idev) { if (mld_in_v2_mode_only(idev)) return false; if (mld_in_v1_mode_only(idev)) return true; if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) return true; return false; } static void mld_set_v1_mode(struct inet6_dev *idev) { /* RFC3810, relevant sections: * - 9.1. Robustness Variable * - 9.2. Query Interval * - 9.3. Query Response Interval * - 9.12. Older Version Querier Present Timeout */ unsigned long switchback; switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; idev->mc_v1_seen = jiffies + switchback; } static void mld_update_qrv(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.8. QRV (Querier's Robustness Variable) * - 9.1. Robustness Variable */ /* The value of the Robustness Variable MUST NOT be zero, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", idev->mc_qrv, min_qrv); idev->mc_qrv = min_qrv; } } static void mld_update_qi(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.9. QQIC (Querier's Query Interval Code) * - 9.2. Query Interval * - 9.12. Older Version Querier Present Timeout * (the [Query Interval] in the last Query received) */ unsigned long mc_qqi; if (mlh2->mld2q_qqic < 128) { mc_qqi = mlh2->mld2q_qqic; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); mc_qqi = (mc_man | 0x10) << (mc_exp + 3); } idev->mc_qi = mc_qqi * HZ; } static void mld_update_qri(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.3. Maximum Response Code * - 9.3. Query Response Interval */ idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); } static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, unsigned long *max_delay, bool v1_query) { unsigned long mldv1_md; /* Ignore v1 queries */ if (mld_in_v2_mode_only(idev)) return -EINVAL; mldv1_md = ntohs(mld->mld_maxdelay); /* When in MLDv1 fallback and a MLDv2 router start-up being * unaware of current MLDv1 operation, the MRC == MRD mapping * only works when the exponential algorithm is not being * used (as MLDv1 is unaware of such things). * * According to the RFC author, the MLDv2 implementations * he's aware of all use a MRC < 32768 on start up queries. * * Thus, should we *ever* encounter something else larger * than that, just assume the maximum possible within our * reach. */ if (!v1_query) mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT); *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); /* MLDv1 router present: we need to go into v1 mode *only* * when an MLDv1 query is received as per section 9.12. of * RFC3810! And we know from RFC2710 section 3.7 that MLDv1 * queries MUST be of exactly 24 octets. */ if (v1_query) mld_set_v1_mode(idev); /* cancel MLDv2 report work */ mld_gq_stop_work(idev); /* cancel the interface change work */ mld_ifc_stop_work(idev); /* clear deleted report items */ mld_clear_delrec(idev); return 0; } static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, unsigned long *max_delay) { *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); mld_update_qrv(idev, mld); mld_update_qi(idev, mld); mld_update_qri(idev, mld); idev->mc_maxdelay = *max_delay; return; } /* called with rcu_read_lock() */ void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_query_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); out: kfree_skb(skb); } static void __mld_query_work(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int group_type; int mark = 0; int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) goto kfree_skb; /* compute payload length excluding extension headers */ len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); len -= skb_network_header_len(skb); /* RFC3810 6.2 * Upon reception of an MLD message that contains a Query, the node * checks if the source address of the message is a valid link-local * address, if the Hop Limit is set to 1, and if the Router Alert * option is present in the Hop-By-Hop Options header of the IPv6 * packet. If any of these checks fails, the packet is dropped. */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || ipv6_hdr(skb)->hop_limit != 1 || !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && !(group_type&IPV6_ADDR_MULTICAST)) goto out; if (len < MLD_V1_QUERY_LEN) { goto out; } else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) { err = mld_process_v1(idev, mld, &max_delay, len == MLD_V1_QUERY_LEN); if (err < 0) goto out; } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); if (!pskb_may_pull(skb, srcs_offset)) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mld_process_v2(idev, mlh2, &max_delay); if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) goto out; /* no sources allowed */ mld_gq_start_work(idev); goto out; } /* mark sources to include, if group & source-specific */ if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } } else { goto out; } if (group_type == IPV6_ADDR_ANY) { for_each_mc_mclock(idev, ma) { igmp6_group_queried(ma, max_delay); } } else { for_each_mc_mclock(idev, ma) { if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; if (ma->mca_flags & MAF_TIMER_RUNNING) { /* gsquery <- gsquery && mark */ if (!mark) ma->mca_flags &= ~MAF_GSQUERY; } else { /* gsquery <- mark */ if (mark) ma->mca_flags |= MAF_GSQUERY; else ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); break; } } out: in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_query_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_query_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_query_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_query_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0)) return; in6_dev_put(idev); } /* called with rcu_read_lock() */ void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_report_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); out: kfree_skb(skb); } static void __mld_report_work(struct sk_buff *skb) { struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ if (skb->pkt_type == PACKET_LOOPBACK) goto kfree_skb; /* send our report if the MC router may not have heard this report */ if (skb->pkt_type != PACKET_MULTICAST && skb->pkt_type != PACKET_BROADCAST) goto kfree_skb; if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); if (addr_type != IPV6_ADDR_ANY && !(addr_type&IPV6_ADDR_LINKLOCAL)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; /* * Cancel the work for this group */ for_each_mc_mclock(idev, ma) { if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { if (cancel_delayed_work(&ma->mca_work)) refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER | MAF_TIMER_RUNNING); break; } } in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_report_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_report_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_report_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_report_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0)) return; in6_dev_put(idev); } static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return false; if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { if (pmc->mca_sfmode == MCAST_INCLUDE) return true; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return false; } static int mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { struct ip6_sf_list *psf; int scount = 0; for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, int proto, int len) { struct ipv6hdr *hdr; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reset_network_header(skb); skb_put(skb, sizeof(struct ipv6hdr)); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, 0, 0); hdr->payload_len = htons(len); hdr->nexthdr = proto; hdr->hop_limit = READ_ONCE(inet6_sk(sk)->hop_limit); hdr->saddr = *saddr; hdr->daddr = *daddr; } static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct net *net = dev_net(dev); const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; int err; sk = net->ipv6.igmp_sk; /* we assume size > sizeof(ra) here * Also try to not allocate high-order pages for big MTU */ size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = sock_alloc_send_skb(sk, size, 1, &err); if (!skb) return NULL; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_type = ICMPV6_MLD2_REPORT; pmr->mld2r_resv1 = 0; pmr->mld2r_cksum = 0; pmr->mld2r_resv2 = 0; pmr->mld2r_ngrec = 0; return skb; } static void mld_sendpack(struct sk_buff *skb) { struct ipv6hdr *pip6 = ipv6_hdr(skb); struct mld2_report *pmr = (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); int err; struct flowi6 fl6; struct dst_entry *dst; rcu_read_lock(); idev = __in6_dev_get(skb->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; } skb_dst_set(skb, dst); if (err) goto err_out; err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) { return sizeof(struct mld2_grec) + 16 * mld_scount(pmc,type,gdel,sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, struct mld2_grec **ppgr, unsigned int mtu) { struct mld2_report *pmr; struct mld2_grec *pgr; if (!skb) { skb = mld_newpack(pmc->idev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) /* called with mc_lock */ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted, int crsend) { struct ip6_sf_list *psf, *psf_prev, *psf_next; int scount, stotal, first, isquery, truncate; struct ip6_sf_list __rcu **psf_list; struct inet6_dev *idev = pmc->idev; struct net_device *dev = idev->dev; struct mld2_grec *pgr = NULL; struct mld2_report *pmr; unsigned int mtu; if (pmc->mca_flags & MAF_NOREPORT) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV6_MIN_MTU) return skb; isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; if (!rcu_access_pointer(*psf_list)) goto empty_source; pmr = skb ? (struct mld2_report *)skb_transport_header(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); } } first = 1; psf_prev = NULL; for (psf = mc_dereference(*psf_list, idev); psf; psf = psf_next) { struct in6_addr *psrc; psf_next = mc_dereference(psf->sf_next, idev); if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } /* Based on RFC3810 6.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->mca_sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->mca_crcount)) && (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(*psrc) + first*sizeof(struct mld2_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*psf_list, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) return skb; if (pmc->mca_crcount || isquery || crsend) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->mca_flags &= ~MAF_GSQUERY; /* clear query state */ return skb; } /* called with mc_lock */ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) { struct sk_buff *skb = NULL; int type; if (!pmc) { for_each_mc_mclock(idev, pmc) { if (pmc->mca_flags & MAF_NOREPORT) continue; if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } } else { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } if (skb) mld_sendpack(skb); } /* * remove zero-count source records from a source filter list * called with mc_lock */ static void mld_clear_zeros(struct ip6_sf_list __rcu **ppsf, struct inet6_dev *idev) { struct ip6_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = mc_dereference(*ppsf, idev); psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); if (psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*ppsf, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); } else { psf_prev = psf; } } } /* called with mc_lock */ static void mld_send_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; /* deleted MCA's */ pmc_prev = NULL; for (pmc = mc_dereference(idev->mc_tomb, idev); pmc; pmc = pmc_next) { pmc_next = mc_dereference(pmc->next, idev); if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0, 0); skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0, 0); } pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb, idev); mld_clear_zeros(&pmc->mca_sources, idev); } } if (pmc->mca_crcount == 0 && !rcu_access_pointer(pmc->mca_tomb) && !rcu_access_pointer(pmc->mca_sources)) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc_next); else rcu_assign_pointer(idev->mc_tomb, pmc_next); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } else pmc_prev = pmc; } /* change recs */ for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_ALLOW_NEW_SOURCES; } else { type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); pmc->mca_crcount--; } } if (!skb) return; (void) mld_sendpack(skb); } static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct flowi6 fl6; struct dst_entry *dst; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; else snd_addr = addr; len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (!skb) { rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); skb_put_data(skb, ra, sizeof(ra)); hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); rcu_read_lock(); idev = __in6_dev_get(skb->dev); icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; } skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } /* called with mc_lock */ static void mld_send_initial_cr(struct inet6_dev *idev) { struct sk_buff *skb; struct ifmcaddr6 *pmc; int type; if (mld_in_v1_mode(idev)) return; skb = NULL; for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); } if (skb) mld_sendpack(skb); } void ipv6_mc_dad_complete(struct inet6_dev *idev) { mutex_lock(&idev->mc_lock); idev->mc_dad_count = idev->mc_qrv; if (idev->mc_dad_count) { mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); } static void mld_dad_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_dad_work); mutex_lock(&idev->mc_lock); mld_send_initial_cr(idev); if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } /* called with mc_lock */ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { struct inet6_dev *idev = pmc->idev; /* no more filters for this source */ if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(pmc->mca_sources, mc_dereference(psf->sf_next, idev)); if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; rcu_assign_pointer(psf->sf_next, mc_dereference(pmc->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_tomb, psf); rv = 1; } else { kfree_rcu(psf, rcu); } } return rv; } /* called with mc_lock */ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int changerec = 0; int i, err; if (!idev) return -ENODEV; for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); if (!delta) { if (!pmc->mca_sfcount[sfmode]) return -EINVAL; pmc->mca_sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->mca_sfmode == MCAST_EXCLUDE && pmc->mca_sfcount[MCAST_EXCLUDE] == 0 && pmc->mca_sfcount[MCAST_INCLUDE]) { struct ip6_sf_list *psf; /* filter mode change */ pmc->mca_sfmode = MCAST_INCLUDE; pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(pmc->idev); } else if (sf_setstate(pmc) || changerec) { mld_ifc_event(pmc->idev); } return err; } /* * Add multicast single-source filter to the interface list * called with mc_lock */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_KERNEL); if (!psf) return -ENOBUFS; psf->sf_addr = *psfsrc; if (psf_prev) { rcu_assign_pointer(psf_prev->sf_next, psf); } else { rcu_assign_pointer(pmc->mca_sources, psf); } } psf->sf_count[sfmode]++; return 0; } /* called with mc_lock */ static void sf_markstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } } } /* called with mc_lock */ static int sf_setstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; rv = 0; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip6_sf_list *prev = NULL; for_each_psf_tomb(pmc, dpsf) { if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; prev = dpsf; } if (dpsf) { if (prev) rcu_assign_pointer(prev->sf_next, mc_dereference(dpsf->sf_next, pmc->idev)); else rcu_assign_pointer(pmc->mca_tomb, mc_dereference(dpsf->sf_next, pmc->idev)); kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for_each_psf_tomb(pmc, dpsf) if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_KERNEL); if (!dpsf) continue; *dpsf = *psf; rcu_assign_pointer(dpsf->sf_next, mc_dereference(pmc->mca_tomb, pmc->idev)); rcu_assign_pointer(pmc->mca_tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; } } return rv; } /* * Add multicast source filter list to the interface list * called with mc_lock */ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int isexclude; int i, err; if (!idev) return -ENODEV; for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); isexclude = pmc->mca_sfmode == MCAST_EXCLUDE; if (!delta) pmc->mca_sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->mca_sfcount[sfmode]--; for (j = 0; j < i; j++) ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; /* filter mode change */ if (pmc->mca_sfcount[MCAST_EXCLUDE]) pmc->mca_sfmode = MCAST_EXCLUDE; else if (pmc->mca_sfcount[MCAST_INCLUDE]) pmc->mca_sfmode = MCAST_INCLUDE; /* else no filters; keep old mode for reports */ pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(idev); } else if (sf_setstate(pmc)) { mld_ifc_event(idev); } return err; } /* called with mc_lock */ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *nextpsf; for (psf = mc_dereference(pmc->mca_tomb, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (psf = mc_dereference(pmc->mca_sources, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_sources, NULL); pmc->mca_sfmode = MCAST_EXCLUDE; pmc->mca_sfcount[MCAST_INCLUDE] = 0; pmc->mca_sfcount[MCAST_EXCLUDE] = 1; } /* called with mc_lock */ static void igmp6_join_group(struct ifmcaddr6 *ma) { unsigned long delay; if (ma->mca_flags & MAF_NOREPORT) return; igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; } static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev) { struct ip6_sf_socklist *psl; int err; psl = sock_dereference(iml->sflist, sk); if (idev) mutex_lock(&idev->mc_lock); if (!psl) { /* any-source empty exclude case */ err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); } else { err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, psl->sl_count, psl->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } if (idev) mutex_unlock(&idev->mc_lock); return err; } /* called with mc_lock */ static void igmp6_leave_group(struct ifmcaddr6 *ma) { if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) { igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); } } else { mld_add_delrec(ma->idev, ma); mld_ifc_event(ma->idev); } } static void mld_gq_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_gq_work); mutex_lock(&idev->mc_lock); mld_send_report(idev, NULL); idev->mc_gq_running = 0; mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_ifc_work); mutex_lock(&idev->mc_lock); mld_send_cr(idev); if (idev->mc_ifc_count) { idev->mc_ifc_count--; if (idev->mc_ifc_count) mld_ifc_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_event(struct inet6_dev *idev) { if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_work(idev, 1); } static void mld_mca_work(struct work_struct *work) { struct ifmcaddr6 *ma = container_of(to_delayed_work(work), struct ifmcaddr6, mca_work); mutex_lock(&ma->idev->mc_lock); if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); ma->mca_flags |= MAF_LAST_REPORTER; ma->mca_flags &= ~MAF_TIMER_RUNNING; mutex_unlock(&ma->idev->mc_lock); ma_put(ma); } /* Device changing type */ void ipv6_mc_unmap(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); } void ipv6_mc_remap(struct inet6_dev *idev) { ipv6_mc_up(idev); } /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) { struct ifmcaddr6 *i; mutex_lock(&idev->mc_lock); /* Withdraw multicast list */ for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ mld_query_stop_work(idev); mld_report_stop_work(idev); mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); mutex_unlock(&idev->mc_lock); mld_dad_stop_work(idev); } static void ipv6_mc_reset(struct inet6_dev *idev) { idev->mc_qrv = sysctl_mld_qrv; idev->mc_qi = MLD_QI_DEFAULT; idev->mc_qri = MLD_QRI_DEFAULT; idev->mc_v1_seen = 0; idev->mc_maxdelay = unsolicited_report_interval(idev); } /* Device going up */ void ipv6_mc_up(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ ipv6_mc_reset(idev); mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) { mld_del_delrec(idev, i); igmp6_group_added(i); } mutex_unlock(&idev->mc_lock); } /* IPv6 device initialization. */ void ipv6_mc_init_dev(struct inet6_dev *idev) { idev->mc_gq_running = 0; INIT_DELAYED_WORK(&idev->mc_gq_work, mld_gq_work); RCU_INIT_POINTER(idev->mc_tomb, NULL); idev->mc_ifc_count = 0; INIT_DELAYED_WORK(&idev->mc_ifc_work, mld_ifc_work); INIT_DELAYED_WORK(&idev->mc_dad_work, mld_dad_work); INIT_DELAYED_WORK(&idev->mc_query_work, mld_query_work); INIT_DELAYED_WORK(&idev->mc_report_work, mld_report_work); skb_queue_head_init(&idev->mc_query_queue); skb_queue_head_init(&idev->mc_report_queue); spin_lock_init(&idev->mc_query_lock); spin_lock_init(&idev->mc_report_lock); mutex_init(&idev->mc_lock); ipv6_mc_reset(idev); } /* * Device is about to be destroyed: clean up. */ void ipv6_mc_destroy_dev(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Deactivate works */ ipv6_mc_down(idev); mutex_lock(&idev->mc_lock); mld_clear_delrec(idev); mutex_unlock(&idev->mc_lock); mld_clear_query(idev); mld_clear_report(idev); /* Delete all-nodes address. */ /* We cannot call ipv6_dev_mc_dec() directly, our caller in * addrconf.c has NULL'd out dev->ip6_ptr so in6_dev_get() will * fail. */ __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allnodes); if (idev->cnf.forwarding) __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allrouters); mutex_lock(&idev->mc_lock); while ((i = mc_dereference(idev->mc_list, idev))) { rcu_assign_pointer(idev->mc_list, mc_dereference(i->next, idev)); ip6_mc_clear_src(i); ma_put(i); } mutex_unlock(&idev->mc_lock); } static void ipv6_mc_rejoin_groups(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; ASSERT_RTNL(); mutex_lock(&idev->mc_lock); if (mld_in_v1_mode(idev)) { for_each_mc_mclock(idev, pmc) igmp6_join_group(pmc); } else { mld_send_report(idev, NULL); } mutex_unlock(&idev->mc_lock); } static int ipv6_mc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); switch (event) { case NETDEV_RESEND_IGMP: if (idev) ipv6_mc_rejoin_groups(idev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp6_netdev_notifier = { .notifier_call = ipv6_mc_netdev_event, }; #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; #define igmp6_mc_seq_private(seq) ((struct igmp6_mc_iter_state *)(seq)->private) static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) { struct ifmcaddr6 *im = NULL; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->mc_list); if (im) { state->idev = idev; break; } } return im; } static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr6 *im) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); im = rcu_dereference(im->next); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; im = rcu_dereference(state->idev->mc_list); } return im; } static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ifmcaddr6 *im = igmp6_mc_get_first(seq); if (im) while (pos && (im = igmp6_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) { struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags & MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_work.timer.expires - jiffies) : 0); return 0; } static const struct seq_operations igmp6_mc_seq_ops = { .start = igmp6_mc_seq_start, .next = igmp6_mc_seq_next, .stop = igmp6_mc_seq_stop, .show = igmp6_mc_seq_show, }; struct igmp6_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; struct ifmcaddr6 *im; }; #define igmp6_mcf_seq_private(seq) ((struct igmp6_mcf_iter_state *)(seq)->private) static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) { struct ip6_sf_list *psf = NULL; struct ifmcaddr6 *im = NULL; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { psf = rcu_dereference(im->mca_sources); if (likely(psf)) { state->im = im; state->idev = idev; break; } } } return psf; } static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_sf_list *psf) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); psf = rcu_dereference(psf->sf_next); while (!psf) { state->im = rcu_dereference(state->im->next); while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } psf = rcu_dereference(state->im->mca_sources); } out: return psf; } static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_sf_list *psf = igmp6_mcf_get_first(seq); if (psf) while (pos && (psf = igmp6_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp6_mcf_get_first(seq); else psf = igmp6_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im)) state->im = NULL; if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) { struct ip6_sf_list *psf = (struct ip6_sf_list *)v; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device Multicast Address Source Address INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, &state->im->mca_addr, &psf->sf_addr, psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp6_mcf_seq_ops = { .start = igmp6_mcf_seq_start, .next = igmp6_mcf_seq_next, .stop = igmp6_mcf_seq_stop, .show = igmp6_mcf_seq_show, }; static int __net_init igmp6_proc_init(struct net *net) { int err; err = -ENOMEM; if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops, sizeof(struct igmp6_mc_iter_state))) goto out; if (!proc_create_net("mcfilter6", 0444, net->proc_net, &igmp6_mcf_seq_ops, sizeof(struct igmp6_mcf_iter_state))) goto out_proc_net_igmp6; err = 0; out: return err; out_proc_net_igmp6: remove_proc_entry("igmp6", net->proc_net); goto out; } static void __net_exit igmp6_proc_exit(struct net *net) { remove_proc_entry("mcfilter6", net->proc_net); remove_proc_entry("igmp6", net->proc_net); } #else static inline int igmp6_proc_init(struct net *net) { return 0; } static inline void igmp6_proc_exit(struct net *net) { } #endif static int __net_init igmp6_net_init(struct net *net) { int err; err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); goto out; } inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; net->ipv6.igmp_sk->sk_allocation = GFP_KERNEL; err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", err); goto out_sock_create; } err = igmp6_proc_init(net); if (err) goto out_sock_create_autojoin; return 0; out_sock_create_autojoin: inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); out: return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, }; int __init igmp6_init(void) { int err; err = register_pernet_subsys(&igmp6_net_ops); if (err) return err; mld_wq = create_workqueue("mld"); if (!mld_wq) { unregister_pernet_subsys(&igmp6_net_ops); return -ENOMEM; } return err; } int __init igmp6_late_init(void) { return register_netdevice_notifier(&igmp6_netdev_notifier); } void igmp6_cleanup(void) { unregister_pernet_subsys(&igmp6_net_ops); destroy_workqueue(mld_wq); } void igmp6_late_cleanup(void) { unregister_netdevice_notifier(&igmp6_netdev_notifier); } |
| 150 150 29 150 150 150 150 150 1 1 150 1 1 149 150 150 44 29 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/rmap.h> #include <linux/hugetlb.h> #include <linux/swap.h> #include <linux/swapops.h> #include "internal.h" static inline bool not_found(struct page_vma_mapped_walk *pvmw) { page_vma_mapped_walk_done(pvmw); return false; } static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) { pte_t ptent; if (pvmw->flags & PVMW_SYNC) { /* Use the stricter lookup */ pvmw->pte = pte_offset_map_lock(pvmw->vma->vm_mm, pvmw->pmd, pvmw->address, &pvmw->ptl); *ptlp = pvmw->ptl; return !!pvmw->pte; } /* * It is important to return the ptl corresponding to pte, * in case *pvmw->pmd changes underneath us; so we need to * return it even when choosing not to lock, in case caller * proceeds to loop over next ptes, and finds a match later. * Though, in most cases, page lock already protects this. */ pvmw->pte = pte_offset_map_nolock(pvmw->vma->vm_mm, pvmw->pmd, pvmw->address, ptlp); if (!pvmw->pte) return false; ptent = ptep_get(pvmw->pte); if (pvmw->flags & PVMW_MIGRATION) { if (!is_swap_pte(ptent)) return false; } else if (is_swap_pte(ptent)) { swp_entry_t entry; /* * Handle un-addressable ZONE_DEVICE memory. * * We get here when we are trying to unmap a private * device page from the process address space. Such * page is not CPU accessible and thus is mapped as * a special swap entry, nonetheless it still does * count as a valid regular mapping for the page * (and is accounted as such in page maps count). * * So handle this special case as if it was a normal * page mapping ie lock CPU page table and return true. * * For more details on device private memory see HMM * (include/linux/hmm.h or mm/hmm.c). */ entry = pte_to_swp_entry(ptent); if (!is_device_private_entry(entry) && !is_device_exclusive_entry(entry)) return false; } else if (!pte_present(ptent)) { return false; } pvmw->ptl = *ptlp; spin_lock(pvmw->ptl); return true; } /** * check_pte - check if [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) is * mapped at the @pvmw->pte * @pvmw: page_vma_mapped_walk struct, includes a pair pte and pfn range * for checking * * page_vma_mapped_walk() found a place where pfn range is *potentially* * mapped. check_pte() has to validate this. * * pvmw->pte may point to empty PTE, swap PTE or PTE pointing to * arbitrary page. * * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration * entry that points to [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) * * If PVMW_MIGRATION flag is not set, returns true if pvmw->pte points to * [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) * * Otherwise, return false. * */ static bool check_pte(struct page_vma_mapped_walk *pvmw) { unsigned long pfn; pte_t ptent = ptep_get(pvmw->pte); if (pvmw->flags & PVMW_MIGRATION) { swp_entry_t entry; if (!is_swap_pte(ptent)) return false; entry = pte_to_swp_entry(ptent); if (!is_migration_entry(entry) && !is_device_exclusive_entry(entry)) return false; pfn = swp_offset_pfn(entry); } else if (is_swap_pte(ptent)) { swp_entry_t entry; /* Handle un-addressable ZONE_DEVICE memory */ entry = pte_to_swp_entry(ptent); if (!is_device_private_entry(entry) && !is_device_exclusive_entry(entry)) return false; pfn = swp_offset_pfn(entry); } else { if (!pte_present(ptent)) return false; pfn = pte_pfn(ptent); } return (pfn - pvmw->pfn) < pvmw->nr_pages; } /* Returns true if the two ranges overlap. Careful to not overflow. */ static bool check_pmd(unsigned long pfn, struct page_vma_mapped_walk *pvmw) { if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn) return false; if (pfn > pvmw->pfn + pvmw->nr_pages - 1) return false; return true; } static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) { pvmw->address = (pvmw->address + size) & ~(size - 1); if (!pvmw->address) pvmw->address = ULONG_MAX; } /** * page_vma_mapped_walk - check if @pvmw->pfn is mapped in @pvmw->vma at * @pvmw->address * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags * must be set. pmd, pte and ptl must be NULL. * * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is * adjusted if needed (for PTE-mapped THPs). * * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in * a loop to find all PTEs that map the THP. * * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry * regardless of which page table level the page is mapped at. @pvmw->pmd is * NULL. * * Returns false if there are no more page table entries for the page in * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped. * * If you need to stop the walk before page_vma_mapped_walk() returned false, * use page_vma_mapped_walk_done(). It will do the housekeeping. */ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long end; spinlock_t *ptl; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t pmde; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { struct hstate *hstate = hstate_vma(vma); unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); /* * All callers that get here will already hold the * i_mmap_rwsem. Therefore, no additional locks need to be * taken before calling hugetlb_walk(). */ pvmw->pte = hugetlb_walk(vma, pvmw->address, size); if (!pvmw->pte) return false; pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte); if (!check_pte(pvmw)) return not_found(pvmw); return true; } end = vma_address_end(pvmw); if (pvmw->pte) goto next_pte; restart: do { pgd = pgd_offset(mm, pvmw->address); if (!pgd_present(*pgd)) { step_forward(pvmw, PGDIR_SIZE); continue; } p4d = p4d_offset(pgd, pvmw->address); if (!p4d_present(*p4d)) { step_forward(pvmw, P4D_SIZE); continue; } pud = pud_offset(p4d, pvmw->address); if (!pud_present(*pud)) { step_forward(pvmw, PUD_SIZE); continue; } pvmw->pmd = pmd_offset(pud, pvmw->address); /* * Make sure the pmd value isn't cached in a register by the * compiler and used as a stale value after we've observed a * subsequent update. */ pmde = pmdp_get_lockless(pvmw->pmd); if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde) || (pmd_present(pmde) && pmd_devmap(pmde))) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); pmde = *pvmw->pmd; if (!pmd_present(pmde)) { swp_entry_t entry; if (!thp_migration_supported() || !(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); entry = pmd_to_swp_entry(pmde); if (!is_migration_entry(entry) || !check_pmd(swp_offset_pfn(entry), pvmw)) return not_found(pvmw); return true; } if (likely(pmd_trans_huge(pmde) || pmd_devmap(pmde))) { if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); if (!check_pmd(pmd_pfn(pmde), pvmw)) return not_found(pvmw); return true; } /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } else if (!pmd_present(pmde)) { /* * If PVMW_SYNC, take and drop THP pmd lock so that we * cannot return prematurely, while zap_huge_pmd() has * cleared *pmd but not decremented compound_mapcount(). */ if ((pvmw->flags & PVMW_SYNC) && thp_vma_suitable_order(vma, pvmw->address, PMD_ORDER) && (pvmw->nr_pages >= HPAGE_PMD_NR)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); spin_unlock(ptl); } step_forward(pvmw, PMD_SIZE); continue; } if (!map_pte(pvmw, &ptl)) { if (!pvmw->pte) goto restart; goto next_pte; } this_pte: if (check_pte(pvmw)) return true; next_pte: do { pvmw->address += PAGE_SIZE; if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } pte_unmap(pvmw->pte); pvmw->pte = NULL; goto restart; } pvmw->pte++; } while (pte_none(ptep_get(pvmw->pte))); if (!pvmw->ptl) { pvmw->ptl = ptl; spin_lock(pvmw->ptl); } goto this_pte; } while (pvmw->address < end); return false; } #ifdef CONFIG_MEMORY_FAILURE /** * page_mapped_in_vma - check whether a page is really mapped in a VMA * @page: the page to test * @vma: the VMA to test * * Return: The address the page is mapped at if the page is in the range * covered by the VMA and present in the page table. If the page is * outside the VMA or not present, returns -EFAULT. * Only valid for normal file or anonymous VMAs. */ unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) { struct folio *folio = page_folio(page); pgoff_t pgoff = folio->index + folio_page_idx(folio, page); struct page_vma_mapped_walk pvmw = { .pfn = page_to_pfn(page), .nr_pages = 1, .vma = vma, .flags = PVMW_SYNC, }; pvmw.address = vma_address(vma, pgoff, 1); if (pvmw.address == -EFAULT) goto out; if (!page_vma_mapped_walk(&pvmw)) return -EFAULT; page_vma_mapped_walk_done(&pvmw); out: return pvmw.address; } #endif |
| 3 3 2 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 * Phillip Lougher <phillip@squashfs.org.uk> * * xz_wrapper.c */ #include <linux/mutex.h> #include <linux/bio.h> #include <linux/slab.h> #include <linux/xz.h> #include <linux/bitops.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" #include "page_actor.h" struct squashfs_xz { struct xz_dec *state; struct xz_buf buf; }; struct disk_comp_opts { __le32 dictionary_size; __le32 flags; }; struct comp_opts { int dict_size; }; static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk, void *buff, int len) { struct disk_comp_opts *comp_opts = buff; struct comp_opts *opts; int err = 0, n; opts = kmalloc(sizeof(*opts), GFP_KERNEL); if (opts == NULL) { err = -ENOMEM; goto out2; } if (comp_opts) { /* check compressor options are the expected length */ if (len < sizeof(*comp_opts)) { err = -EIO; goto out; } opts->dict_size = le32_to_cpu(comp_opts->dictionary_size); /* the dictionary size should be 2^n or 2^n+2^(n+1) */ n = ffs(opts->dict_size) - 1; if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) + (1 << (n + 1))) { err = -EIO; goto out; } } else /* use defaults */ opts->dict_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); return opts; out: kfree(opts); out2: return ERR_PTR(err); } static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff) { struct comp_opts *comp_opts = buff; struct squashfs_xz *stream; int err; stream = kmalloc(sizeof(*stream), GFP_KERNEL); if (stream == NULL) { err = -ENOMEM; goto failed; } stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size); if (stream->state == NULL) { kfree(stream); err = -ENOMEM; goto failed; } return stream; failed: ERROR("Failed to initialise xz decompressor\n"); return ERR_PTR(err); } static void squashfs_xz_free(void *strm) { struct squashfs_xz *stream = strm; if (stream) { xz_dec_end(stream->state); kfree(stream); } } static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, struct bio *bio, int offset, int length, struct squashfs_page_actor *output) { struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); int total = 0, error = 0; struct squashfs_xz *stream = strm; xz_dec_reset(stream->state); stream->buf.in_pos = 0; stream->buf.in_size = 0; stream->buf.out_pos = 0; stream->buf.out_size = PAGE_SIZE; stream->buf.out = squashfs_first_page(output); if (IS_ERR(stream->buf.out)) { error = PTR_ERR(stream->buf.out); goto finish; } for (;;) { enum xz_ret xz_err; if (stream->buf.in_pos == stream->buf.in_size) { const void *data; int avail; if (!bio_next_segment(bio, &iter_all)) { /* XZ_STREAM_END must be reached. */ error = -EIO; break; } avail = min(length, ((int)bvec->bv_len) - offset); data = bvec_virt(bvec); length -= avail; stream->buf.in = data + offset; stream->buf.in_size = avail; stream->buf.in_pos = 0; offset = 0; } if (stream->buf.out_pos == stream->buf.out_size) { stream->buf.out = squashfs_next_page(output); if (IS_ERR(stream->buf.out)) { error = PTR_ERR(stream->buf.out); break; } else if (stream->buf.out != NULL) { stream->buf.out_pos = 0; total += PAGE_SIZE; } } xz_err = xz_dec_run(stream->state, &stream->buf); if (xz_err == XZ_STREAM_END) break; if (xz_err != XZ_OK) { error = -EIO; break; } } finish: squashfs_finish_page(output); return error ? error : total + stream->buf.out_pos; } const struct squashfs_decompressor squashfs_xz_comp_ops = { .init = squashfs_xz_init, .comp_opts = squashfs_xz_comp_opts, .free = squashfs_xz_free, .decompress = squashfs_xz_uncompress, .id = XZ_COMPRESSION, .name = "xz", .alloc_buffer = 1, .supported = 1 }; |
| 5 13 14 7 6 14 3 3 7 16 16 7 7 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 | // SPDX-License-Identifier: GPL-2.0 /* * Ldisc rw semaphore * * The ldisc semaphore is semantically a rw_semaphore but which enforces * an alternate policy, namely: * 1) Supports lock wait timeouts * 2) Write waiter has priority * 3) Downgrading is not supported * * Implementation notes: * 1) Upper half of semaphore count is a wait count (differs from rwsem * in that rwsem normalizes the upper half to the wait bias) * 2) Lacks overflow checking * * The generic counting was copied and modified from include/asm-generic/rwsem.h * by Paul Mackerras <paulus@samba.org>. * * The scheduling policy was copied and modified from lib/rwsem.c * Written by David Howells (dhowells@redhat.com). * * This implementation incorporates the write lock stealing work of * Michel Lespinasse <walken@google.com>. * * Copyright (C) 2013 Peter Hurley <peter@hurleysoftware.com> */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/tty.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task.h> #if BITS_PER_LONG == 64 # define LDSEM_ACTIVE_MASK 0xffffffffL #else # define LDSEM_ACTIVE_MASK 0x0000ffffL #endif #define LDSEM_UNLOCKED 0L #define LDSEM_ACTIVE_BIAS 1L #define LDSEM_WAIT_BIAS (-LDSEM_ACTIVE_MASK-1) #define LDSEM_READ_BIAS LDSEM_ACTIVE_BIAS #define LDSEM_WRITE_BIAS (LDSEM_WAIT_BIAS + LDSEM_ACTIVE_BIAS) struct ldsem_waiter { struct list_head list; struct task_struct *task; }; /* * Initialize an ldsem: */ void __init_ldsem(struct ld_semaphore *sem, const char *name, struct lock_class_key *key) { #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Make sure we are not reinitializing a held semaphore: */ debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map(&sem->dep_map, name, key, 0); #endif atomic_long_set(&sem->count, LDSEM_UNLOCKED); sem->wait_readers = 0; raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->read_wait); INIT_LIST_HEAD(&sem->write_wait); } static void __ldsem_wake_readers(struct ld_semaphore *sem) { struct ldsem_waiter *waiter, *next; struct task_struct *tsk; long adjust, count; /* * Try to grant read locks to all readers on the read wait list. * Note the 'active part' of the count is incremented by * the number of readers before waking any processes up. */ adjust = sem->wait_readers * (LDSEM_ACTIVE_BIAS - LDSEM_WAIT_BIAS); count = atomic_long_add_return(adjust, &sem->count); do { if (count > 0) break; if (atomic_long_try_cmpxchg(&sem->count, &count, count - adjust)) return; } while (1); list_for_each_entry_safe(waiter, next, &sem->read_wait, list) { tsk = waiter->task; smp_store_release(&waiter->task, NULL); wake_up_process(tsk); put_task_struct(tsk); } INIT_LIST_HEAD(&sem->read_wait); sem->wait_readers = 0; } static inline int writer_trylock(struct ld_semaphore *sem) { /* * Only wake this writer if the active part of the count can be * transitioned from 0 -> 1 */ long count = atomic_long_add_return(LDSEM_ACTIVE_BIAS, &sem->count); do { if ((count & LDSEM_ACTIVE_MASK) == LDSEM_ACTIVE_BIAS) return 1; if (atomic_long_try_cmpxchg(&sem->count, &count, count - LDSEM_ACTIVE_BIAS)) return 0; } while (1); } static void __ldsem_wake_writer(struct ld_semaphore *sem) { struct ldsem_waiter *waiter; waiter = list_entry(sem->write_wait.next, struct ldsem_waiter, list); wake_up_process(waiter->task); } /* * handle the lock release when processes blocked on it that can now run * - if we come here from up_xxxx(), then: * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed) * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so) * - the spinlock must be held by the caller * - woken process blocks are discarded from the list after having task zeroed */ static void __ldsem_wake(struct ld_semaphore *sem) { if (!list_empty(&sem->write_wait)) __ldsem_wake_writer(sem); else if (!list_empty(&sem->read_wait)) __ldsem_wake_readers(sem); } static void ldsem_wake(struct ld_semaphore *sem) { unsigned long flags; raw_spin_lock_irqsave(&sem->wait_lock, flags); __ldsem_wake(sem); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); } /* * wait for the read lock to be granted */ static struct ld_semaphore __sched * down_read_failed(struct ld_semaphore *sem, long count, long timeout) { struct ldsem_waiter waiter; long adjust = -LDSEM_ACTIVE_BIAS + LDSEM_WAIT_BIAS; /* set up my own style of waitqueue */ raw_spin_lock_irq(&sem->wait_lock); /* * Try to reverse the lock attempt but if the count has changed * so that reversing fails, check if there are no waiters, * and early-out if not */ do { if (atomic_long_try_cmpxchg(&sem->count, &count, count + adjust)) { count += adjust; break; } if (count > 0) { raw_spin_unlock_irq(&sem->wait_lock); return sem; } } while (1); list_add_tail(&waiter.list, &sem->read_wait); sem->wait_readers++; waiter.task = current; get_task_struct(current); /* if there are no active locks, wake the new lock owner(s) */ if ((count & LDSEM_ACTIVE_MASK) == 0) __ldsem_wake(sem); raw_spin_unlock_irq(&sem->wait_lock); /* wait to be given the lock */ for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!smp_load_acquire(&waiter.task)) break; if (!timeout) break; timeout = schedule_timeout(timeout); } __set_current_state(TASK_RUNNING); if (!timeout) { /* * Lock timed out but check if this task was just * granted lock ownership - if so, pretend there * was no timeout; otherwise, cleanup lock wait. */ raw_spin_lock_irq(&sem->wait_lock); if (waiter.task) { atomic_long_add_return(-LDSEM_WAIT_BIAS, &sem->count); sem->wait_readers--; list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); put_task_struct(waiter.task); return NULL; } raw_spin_unlock_irq(&sem->wait_lock); } return sem; } /* * wait for the write lock to be granted */ static struct ld_semaphore __sched * down_write_failed(struct ld_semaphore *sem, long count, long timeout) { struct ldsem_waiter waiter; long adjust = -LDSEM_ACTIVE_BIAS; int locked = 0; /* set up my own style of waitqueue */ raw_spin_lock_irq(&sem->wait_lock); /* * Try to reverse the lock attempt but if the count has changed * so that reversing fails, check if the lock is now owned, * and early-out if so. */ do { if (atomic_long_try_cmpxchg(&sem->count, &count, count + adjust)) break; if ((count & LDSEM_ACTIVE_MASK) == LDSEM_ACTIVE_BIAS) { raw_spin_unlock_irq(&sem->wait_lock); return sem; } } while (1); list_add_tail(&waiter.list, &sem->write_wait); waiter.task = current; set_current_state(TASK_UNINTERRUPTIBLE); for (;;) { if (!timeout) break; raw_spin_unlock_irq(&sem->wait_lock); timeout = schedule_timeout(timeout); raw_spin_lock_irq(&sem->wait_lock); set_current_state(TASK_UNINTERRUPTIBLE); locked = writer_trylock(sem); if (locked) break; } if (!locked) atomic_long_add_return(-LDSEM_WAIT_BIAS, &sem->count); list_del(&waiter.list); /* * In case of timeout, wake up every reader who gave the right of way * to writer. Prevent separation readers into two groups: * one that helds semaphore and another that sleeps. * (in case of no contention with a writer) */ if (!locked && list_empty(&sem->write_wait)) __ldsem_wake_readers(sem); raw_spin_unlock_irq(&sem->wait_lock); __set_current_state(TASK_RUNNING); /* lock wait may have timed out */ if (!locked) return NULL; return sem; } static int __ldsem_down_read_nested(struct ld_semaphore *sem, int subclass, long timeout) { long count; rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_); count = atomic_long_add_return(LDSEM_READ_BIAS, &sem->count); if (count <= 0) { lock_contended(&sem->dep_map, _RET_IP_); if (!down_read_failed(sem, count, timeout)) { rwsem_release(&sem->dep_map, _RET_IP_); return 0; } } lock_acquired(&sem->dep_map, _RET_IP_); return 1; } static int __ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, long timeout) { long count; rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); count = atomic_long_add_return(LDSEM_WRITE_BIAS, &sem->count); if ((count & LDSEM_ACTIVE_MASK) != LDSEM_ACTIVE_BIAS) { lock_contended(&sem->dep_map, _RET_IP_); if (!down_write_failed(sem, count, timeout)) { rwsem_release(&sem->dep_map, _RET_IP_); return 0; } } lock_acquired(&sem->dep_map, _RET_IP_); return 1; } /* * lock for reading -- returns 1 if successful, 0 if timed out */ int __sched ldsem_down_read(struct ld_semaphore *sem, long timeout) { might_sleep(); return __ldsem_down_read_nested(sem, 0, timeout); } /* * trylock for reading -- returns 1 if successful, 0 if contention */ int ldsem_down_read_trylock(struct ld_semaphore *sem) { long count = atomic_long_read(&sem->count); while (count >= 0) { if (atomic_long_try_cmpxchg(&sem->count, &count, count + LDSEM_READ_BIAS)) { rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); lock_acquired(&sem->dep_map, _RET_IP_); return 1; } } return 0; } /* * lock for writing -- returns 1 if successful, 0 if timed out */ int __sched ldsem_down_write(struct ld_semaphore *sem, long timeout) { might_sleep(); return __ldsem_down_write_nested(sem, 0, timeout); } /* * trylock for writing -- returns 1 if successful, 0 if contention */ int ldsem_down_write_trylock(struct ld_semaphore *sem) { long count = atomic_long_read(&sem->count); while ((count & LDSEM_ACTIVE_MASK) == 0) { if (atomic_long_try_cmpxchg(&sem->count, &count, count + LDSEM_WRITE_BIAS)) { rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_); lock_acquired(&sem->dep_map, _RET_IP_); return 1; } } return 0; } /* * release a read lock */ void ldsem_up_read(struct ld_semaphore *sem) { long count; rwsem_release(&sem->dep_map, _RET_IP_); count = atomic_long_add_return(-LDSEM_READ_BIAS, &sem->count); if (count < 0 && (count & LDSEM_ACTIVE_MASK) == 0) ldsem_wake(sem); } /* * release a write lock */ void ldsem_up_write(struct ld_semaphore *sem) { long count; rwsem_release(&sem->dep_map, _RET_IP_); count = atomic_long_add_return(-LDSEM_WRITE_BIAS, &sem->count); if (count < 0) ldsem_wake(sem); } #ifdef CONFIG_DEBUG_LOCK_ALLOC int ldsem_down_read_nested(struct ld_semaphore *sem, int subclass, long timeout) { might_sleep(); return __ldsem_down_read_nested(sem, subclass, timeout); } int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, long timeout) { might_sleep(); return __ldsem_down_write_nested(sem, subclass, timeout); } #endif |
| 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Do sleep inside a spin-lock * Copyright (c) 1999 by Takashi Iwai <tiwai@suse.de> */ #include <linux/export.h> #include <sound/core.h> #include "seq_lock.h" /* wait until all locks are released */ void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line) { int warn_count = 5 * HZ; if (atomic_read(lockp) < 0) { pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line); return; } while (atomic_read(lockp) > 0) { if (warn_count-- == 0) pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line); schedule_timeout_uninterruptible(1); } } EXPORT_SYMBOL(snd_use_lock_sync_helper); |
| 1 5 5 5 5 1 4 5 5 5 5 5 5 42 43 5 1 8 2 5 1 1 6 5 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "tctx.h" #include "poll.h" #include "timeout.h" #include "waitid.h" #include "futex.h" #include "cancel.h" struct io_cancel { struct file *file; u64 addr; u32 flags; s32 fd; u8 opcode; }; #define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED | \ IORING_ASYNC_CANCEL_USERDATA | IORING_ASYNC_CANCEL_OP) /* * Returns true if the request matches the criteria outlined by 'cd'. */ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd) { bool match_user_data = cd->flags & IORING_ASYNC_CANCEL_USERDATA; if (req->ctx != cd->ctx) return false; if (!(cd->flags & (IORING_ASYNC_CANCEL_FD | IORING_ASYNC_CANCEL_OP))) match_user_data = true; if (cd->flags & IORING_ASYNC_CANCEL_ANY) goto check_seq; if (cd->flags & IORING_ASYNC_CANCEL_FD) { if (req->file != cd->file) return false; } if (cd->flags & IORING_ASYNC_CANCEL_OP) { if (req->opcode != cd->opcode) return false; } if (match_user_data && req->cqe.user_data != cd->data) return false; if (cd->flags & IORING_ASYNC_CANCEL_ALL) { check_seq: if (io_cancel_match_sequence(req, cd->seq)) return false; } return true; } static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_cancel_data *cd = data; return io_cancel_req_match(req, cd); } static int io_async_cancel_one(struct io_uring_task *tctx, struct io_cancel_data *cd) { enum io_wq_cancel cancel_ret; int ret = 0; bool all; if (!tctx || !tctx->io_wq) return -ENOENT; all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; break; case IO_WQ_CANCEL_RUNNING: ret = -EALREADY; break; case IO_WQ_CANCEL_NOTFOUND: ret = -ENOENT; break; } return ret; } int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned issue_flags) { struct io_ring_ctx *ctx = cd->ctx; int ret; WARN_ON_ONCE(!io_wq_current_is_worker() && tctx != current->io_uring); ret = io_async_cancel_one(tctx, cd); /* * Fall-through even for -EALREADY, as we may have poll armed * that need unarming. */ if (!ret) return 0; ret = io_poll_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; ret = io_waitid_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; ret = io_futex_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; spin_lock(&ctx->completion_lock); if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) ret = io_timeout_cancel(ctx, cd); spin_unlock(&ctx->completion_lock); return ret; } int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_cancel *cancel = io_kiocb_to_cmd(req, struct io_cancel); if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (sqe->off || sqe->splice_fd_in) return -EINVAL; cancel->addr = READ_ONCE(sqe->addr); cancel->flags = READ_ONCE(sqe->cancel_flags); if (cancel->flags & ~CANCEL_FLAGS) return -EINVAL; if (cancel->flags & IORING_ASYNC_CANCEL_FD) { if (cancel->flags & IORING_ASYNC_CANCEL_ANY) return -EINVAL; cancel->fd = READ_ONCE(sqe->fd); } if (cancel->flags & IORING_ASYNC_CANCEL_OP) { if (cancel->flags & IORING_ASYNC_CANCEL_ANY) return -EINVAL; cancel->opcode = READ_ONCE(sqe->len); } return 0; } static int __io_async_cancel(struct io_cancel_data *cd, struct io_uring_task *tctx, unsigned int issue_flags) { bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); struct io_ring_ctx *ctx = cd->ctx; struct io_tctx_node *node; int ret, nr = 0; do { ret = io_try_cancel(tctx, cd, issue_flags); if (ret == -ENOENT) break; if (!all) return ret; nr++; } while (1); /* slow path, try all io-wq's */ io_ring_submit_lock(ctx, issue_flags); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { ret = io_async_cancel_one(node->task->io_uring, cd); if (ret != -ENOENT) { if (!all) break; nr++; } } io_ring_submit_unlock(ctx, issue_flags); return all ? nr : ret; } int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_cancel *cancel = io_kiocb_to_cmd(req, struct io_cancel); struct io_cancel_data cd = { .ctx = req->ctx, .data = cancel->addr, .flags = cancel->flags, .opcode = cancel->opcode, .seq = atomic_inc_return(&req->ctx->cancel_seq), }; struct io_uring_task *tctx = req->task->io_uring; int ret; if (cd.flags & IORING_ASYNC_CANCEL_FD) { if (req->flags & REQ_F_FIXED_FILE || cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) { req->flags |= REQ_F_FIXED_FILE; req->file = io_file_get_fixed(req, cancel->fd, issue_flags); } else { req->file = io_file_get_normal(req, cancel->fd); } if (!req->file) { ret = -EBADF; goto done; } cd.file = req->file; } ret = __io_async_cancel(&cd, tctx, issue_flags); done: if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); return IOU_OK; } void init_hash_table(struct io_hash_table *table, unsigned size) { unsigned int i; for (i = 0; i < size; i++) { spin_lock_init(&table->hbs[i].lock); INIT_HLIST_HEAD(&table->hbs[i].list); } } static int __io_sync_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, int fd) { struct io_ring_ctx *ctx = cd->ctx; /* fixed must be grabbed every time since we drop the uring_lock */ if ((cd->flags & IORING_ASYNC_CANCEL_FD) && (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { if (unlikely(fd >= ctx->nr_user_files)) return -EBADF; fd = array_index_nospec(fd, ctx->nr_user_files); cd->file = io_file_from_index(&ctx->file_table, fd); if (!cd->file) return -EBADF; } return __io_async_cancel(cd, tctx, 0); } int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) __must_hold(&ctx->uring_lock) { struct io_cancel_data cd = { .ctx = ctx, .seq = atomic_inc_return(&ctx->cancel_seq), }; ktime_t timeout = KTIME_MAX; struct io_uring_sync_cancel_reg sc; struct file *file = NULL; DEFINE_WAIT(wait); int ret, i; if (copy_from_user(&sc, arg, sizeof(sc))) return -EFAULT; if (sc.flags & ~CANCEL_FLAGS) return -EINVAL; for (i = 0; i < ARRAY_SIZE(sc.pad); i++) if (sc.pad[i]) return -EINVAL; for (i = 0; i < ARRAY_SIZE(sc.pad2); i++) if (sc.pad2[i]) return -EINVAL; cd.data = sc.addr; cd.flags = sc.flags; cd.opcode = sc.opcode; /* we can grab a normal file descriptor upfront */ if ((cd.flags & IORING_ASYNC_CANCEL_FD) && !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) { file = fget(sc.fd); if (!file) return -EBADF; cd.file = file; } ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); /* found something, done! */ if (ret != -EALREADY) goto out; if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) { struct timespec64 ts = { .tv_sec = sc.timeout.tv_sec, .tv_nsec = sc.timeout.tv_nsec }; timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } /* * Keep looking until we get -ENOENT. we'll get woken everytime * every time a request completes and will retry the cancelation. */ do { cd.seq = atomic_inc_return(&ctx->cancel_seq); prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE); ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); mutex_unlock(&ctx->uring_lock); if (ret != -EALREADY) break; ret = io_run_task_work_sig(ctx); if (ret < 0) break; ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); if (!ret) { ret = -ETIME; break; } mutex_lock(&ctx->uring_lock); } while (1); finish_wait(&ctx->cq_wait, &wait); mutex_lock(&ctx->uring_lock); if (ret == -ENOENT || ret > 0) ret = 0; out: if (file) fput(file); return ret; } |
| 335 285 284 617 617 207 607 88 125 611 16 531 285 567 285 287 26 264 4 1 287 260 29 5 615 214 610 89 149 614 33 548 306 569 618 32 32 10 22 32 32 586 521 135 506 586 126 282 570 103 10 67 67 67 6 67 67 6 67 16 61 41 34 19 10 236 239 2 148 111 151 151 123 123 108 108 32 80 108 105 4 4 1 1 84 20 2 104 1 3 8 4 4 15 1 1 10 3 12 14 14 1 13 13 12 1 10 2 12 1 1 35 4 3 3 4 44 44 44 44 44 1 41 41 19 1 5 12 1 1 1 9 1 2 6 50 50 2 2 47 39 9 27 27 1 26 16 9 1 24 24 1 2 65 65 68 36 60 8 68 68 68 64 68 8 68 68 60 8 67 60 8 37 31 67 1 49 19 37 30 58 8 66 6 1 57 3 3 58 58 58 3 24 2 50 6 46 65 66 66 66 58 8 66 107 108 73 69 49 2 19 32 50 2 19 32 50 50 50 15 15 5 10 30 18 13 305 38 274 125 126 126 250 250 141 126 250 91 91 91 257 258 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ #include <linux/iversion.h> #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_dir2.h" #include "xfs_attr.h" #include "xfs_bit.h" #include "xfs_trans_space.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_inode_item.h" #include "xfs_iunlink_item.h" #include "xfs_ialloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_filestream.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_symlink.h" #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_bmap_btree.h" #include "xfs_reflink.h" #include "xfs_ag.h" #include "xfs_log_priv.h" #include "xfs_health.h" #include "xfs_pnfs.h" #include "xfs_parent.h" #include "xfs_xattr.h" #include "xfs_inode_util.h" struct kmem_cache *xfs_inode_cache; /* * These two are wrapper routines around the xfs_ilock() routine used to * centralize some grungy code. They are used in places that wish to lock the * inode solely for reading the extents. The reason these places can't just * call xfs_ilock(ip, XFS_ILOCK_SHARED) is that the inode lock also guards to * bringing in of the extents from disk for a file in b-tree format. If the * inode is in b-tree format, then we need to lock the inode exclusively until * the extents are read in. Locking it exclusively all the time would limit * our parallelism unnecessarily, though. What we do instead is check to see * if the extents have been read in yet, and only lock the inode exclusively * if they have not. * * The functions return a value which should be given to the corresponding * xfs_iunlock() call. */ uint xfs_ilock_data_map_shared( struct xfs_inode *ip) { uint lock_mode = XFS_ILOCK_SHARED; if (xfs_need_iread_extents(&ip->i_df)) lock_mode = XFS_ILOCK_EXCL; xfs_ilock(ip, lock_mode); return lock_mode; } uint xfs_ilock_attr_map_shared( struct xfs_inode *ip) { uint lock_mode = XFS_ILOCK_SHARED; if (xfs_inode_has_attr_fork(ip) && xfs_need_iread_extents(&ip->i_af)) lock_mode = XFS_ILOCK_EXCL; xfs_ilock(ip, lock_mode); return lock_mode; } /* * You can't set both SHARED and EXCL for the same lock, * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_MMAPLOCK_SHARED, * XFS_MMAPLOCK_EXCL, XFS_ILOCK_SHARED, XFS_ILOCK_EXCL are valid values * to set in lock_flags. */ static inline void xfs_lock_flags_assert( uint lock_flags) { ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); ASSERT(lock_flags != 0); } /* * In addition to i_rwsem in the VFS inode, the xfs inode contains 2 * multi-reader locks: invalidate_lock and the i_lock. This routine allows * various combinations of the locks to be obtained. * * The 3 locks should always be ordered so that the IO lock is obtained first, * the mmap lock second and the ilock last in order to prevent deadlock. * * Basic locking order: * * i_rwsem -> invalidate_lock -> page_lock -> i_ilock * * mmap_lock locking order: * * i_rwsem -> page lock -> mmap_lock * mmap_lock -> invalidate_lock -> page_lock * * The difference in mmap_lock locking order mean that we cannot hold the * invalidate_lock over syscall based read(2)/write(2) based IO. These IO paths * can fault in pages during copy in/out (for buffered IO) or require the * mmap_lock in get_user_pages() to map the user pages into the kernel address * space for direct IO. Similarly the i_rwsem cannot be taken inside a page * fault because page faults already hold the mmap_lock. * * Hence to serialise fully against both syscall and mmap based IO, we need to * take both the i_rwsem and the invalidate_lock. These locks should *only* be * both taken in places where we need to invalidate the page cache in a race * free manner (e.g. truncate, hole punch and other extent manipulation * functions). */ void xfs_ilock( xfs_inode_t *ip, uint lock_flags) { trace_xfs_ilock(ip, lock_flags, _RET_IP_); xfs_lock_flags_assert(lock_flags); if (lock_flags & XFS_IOLOCK_EXCL) { down_write_nested(&VFS_I(ip)->i_rwsem, XFS_IOLOCK_DEP(lock_flags)); } else if (lock_flags & XFS_IOLOCK_SHARED) { down_read_nested(&VFS_I(ip)->i_rwsem, XFS_IOLOCK_DEP(lock_flags)); } if (lock_flags & XFS_MMAPLOCK_EXCL) { down_write_nested(&VFS_I(ip)->i_mapping->invalidate_lock, XFS_MMAPLOCK_DEP(lock_flags)); } else if (lock_flags & XFS_MMAPLOCK_SHARED) { down_read_nested(&VFS_I(ip)->i_mapping->invalidate_lock, XFS_MMAPLOCK_DEP(lock_flags)); } if (lock_flags & XFS_ILOCK_EXCL) down_write_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); else if (lock_flags & XFS_ILOCK_SHARED) down_read_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); } /* * This is just like xfs_ilock(), except that the caller * is guaranteed not to sleep. It returns 1 if it gets * the requested locks and 0 otherwise. If the IO lock is * obtained but the inode lock cannot be, then the IO lock * is dropped before returning. * * ip -- the inode being locked * lock_flags -- this parameter indicates the inode's locks to be * to be locked. See the comment for xfs_ilock() for a list * of valid values. */ int xfs_ilock_nowait( xfs_inode_t *ip, uint lock_flags) { trace_xfs_ilock_nowait(ip, lock_flags, _RET_IP_); xfs_lock_flags_assert(lock_flags); if (lock_flags & XFS_IOLOCK_EXCL) { if (!down_write_trylock(&VFS_I(ip)->i_rwsem)) goto out; } else if (lock_flags & XFS_IOLOCK_SHARED) { if (!down_read_trylock(&VFS_I(ip)->i_rwsem)) goto out; } if (lock_flags & XFS_MMAPLOCK_EXCL) { if (!down_write_trylock(&VFS_I(ip)->i_mapping->invalidate_lock)) goto out_undo_iolock; } else if (lock_flags & XFS_MMAPLOCK_SHARED) { if (!down_read_trylock(&VFS_I(ip)->i_mapping->invalidate_lock)) goto out_undo_iolock; } if (lock_flags & XFS_ILOCK_EXCL) { if (!down_write_trylock(&ip->i_lock)) goto out_undo_mmaplock; } else if (lock_flags & XFS_ILOCK_SHARED) { if (!down_read_trylock(&ip->i_lock)) goto out_undo_mmaplock; } return 1; out_undo_mmaplock: if (lock_flags & XFS_MMAPLOCK_EXCL) up_write(&VFS_I(ip)->i_mapping->invalidate_lock); else if (lock_flags & XFS_MMAPLOCK_SHARED) up_read(&VFS_I(ip)->i_mapping->invalidate_lock); out_undo_iolock: if (lock_flags & XFS_IOLOCK_EXCL) up_write(&VFS_I(ip)->i_rwsem); else if (lock_flags & XFS_IOLOCK_SHARED) up_read(&VFS_I(ip)->i_rwsem); out: return 0; } /* * xfs_iunlock() is used to drop the inode locks acquired with * xfs_ilock() and xfs_ilock_nowait(). The caller must pass * in the flags given to xfs_ilock() or xfs_ilock_nowait() so * that we know which locks to drop. * * ip -- the inode being unlocked * lock_flags -- this parameter indicates the inode's locks to be * to be unlocked. See the comment for xfs_ilock() for a list * of valid values for this parameter. * */ void xfs_iunlock( xfs_inode_t *ip, uint lock_flags) { xfs_lock_flags_assert(lock_flags); if (lock_flags & XFS_IOLOCK_EXCL) up_write(&VFS_I(ip)->i_rwsem); else if (lock_flags & XFS_IOLOCK_SHARED) up_read(&VFS_I(ip)->i_rwsem); if (lock_flags & XFS_MMAPLOCK_EXCL) up_write(&VFS_I(ip)->i_mapping->invalidate_lock); else if (lock_flags & XFS_MMAPLOCK_SHARED) up_read(&VFS_I(ip)->i_mapping->invalidate_lock); if (lock_flags & XFS_ILOCK_EXCL) up_write(&ip->i_lock); else if (lock_flags & XFS_ILOCK_SHARED) up_read(&ip->i_lock); trace_xfs_iunlock(ip, lock_flags, _RET_IP_); } /* * give up write locks. the i/o lock cannot be held nested * if it is being demoted. */ void xfs_ilock_demote( xfs_inode_t *ip, uint lock_flags) { ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)); ASSERT((lock_flags & ~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0); if (lock_flags & XFS_ILOCK_EXCL) downgrade_write(&ip->i_lock); if (lock_flags & XFS_MMAPLOCK_EXCL) downgrade_write(&VFS_I(ip)->i_mapping->invalidate_lock); if (lock_flags & XFS_IOLOCK_EXCL) downgrade_write(&VFS_I(ip)->i_rwsem); trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_); } void xfs_assert_ilocked( struct xfs_inode *ip, uint lock_flags) { /* * Sometimes we assert the ILOCK is held exclusively, but we're in * a workqueue, so lockdep doesn't know we're the owner. */ if (lock_flags & XFS_ILOCK_SHARED) rwsem_assert_held(&ip->i_lock); else if (lock_flags & XFS_ILOCK_EXCL) rwsem_assert_held_write_nolockdep(&ip->i_lock); if (lock_flags & XFS_MMAPLOCK_SHARED) rwsem_assert_held(&VFS_I(ip)->i_mapping->invalidate_lock); else if (lock_flags & XFS_MMAPLOCK_EXCL) rwsem_assert_held_write(&VFS_I(ip)->i_mapping->invalidate_lock); if (lock_flags & XFS_IOLOCK_SHARED) rwsem_assert_held(&VFS_I(ip)->i_rwsem); else if (lock_flags & XFS_IOLOCK_EXCL) rwsem_assert_held_write(&VFS_I(ip)->i_rwsem); } /* * xfs_lockdep_subclass_ok() is only used in an ASSERT, so is only called when * DEBUG or XFS_WARN is set. And MAX_LOCKDEP_SUBCLASSES is then only defined * when CONFIG_LOCKDEP is set. Hence the complex define below to avoid build * errors and warnings. */ #if (defined(DEBUG) || defined(XFS_WARN)) && defined(CONFIG_LOCKDEP) static bool xfs_lockdep_subclass_ok( int subclass) { return subclass < MAX_LOCKDEP_SUBCLASSES; } #else #define xfs_lockdep_subclass_ok(subclass) (true) #endif /* * Bump the subclass so xfs_lock_inodes() acquires each lock with a different * value. This can be called for any type of inode lock combination, including * parent locking. Care must be taken to ensure we don't overrun the subclass * storage fields in the class mask we build. */ static inline uint xfs_lock_inumorder( uint lock_mode, uint subclass) { uint class = 0; ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP | XFS_ILOCK_RTSUM))); ASSERT(xfs_lockdep_subclass_ok(subclass)); if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { ASSERT(subclass <= XFS_IOLOCK_MAX_SUBCLASS); class += subclass << XFS_IOLOCK_SHIFT; } if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) { ASSERT(subclass <= XFS_MMAPLOCK_MAX_SUBCLASS); class += subclass << XFS_MMAPLOCK_SHIFT; } if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) { ASSERT(subclass <= XFS_ILOCK_MAX_SUBCLASS); class += subclass << XFS_ILOCK_SHIFT; } return (lock_mode & ~XFS_LOCK_SUBCLASS_MASK) | class; } /* * The following routine will lock n inodes in exclusive mode. We assume the * caller calls us with the inodes in i_ino order. * * We need to detect deadlock where an inode that we lock is in the AIL and we * start waiting for another inode that is locked by a thread in a long running * transaction (such as truncate). This can result in deadlock since the long * running trans might need to wait for the inode we just locked in order to * push the tail and free space in the log. * * xfs_lock_inodes() can only be used to lock one type of lock at a time - * the iolock, the mmaplock or the ilock, but not more than one at a time. If we * lock more than one at a time, lockdep will report false positives saying we * have violated locking orders. */ void xfs_lock_inodes( struct xfs_inode **ips, int inodes, uint lock_mode) { int attempts = 0; uint i; int j; bool try_lock; struct xfs_log_item *lp; /* * Currently supports between 2 and 5 inodes with exclusive locking. We * support an arbitrary depth of locking here, but absolute limits on * inodes depend on the type of locking and the limits placed by * lockdep annotations in xfs_lock_inumorder. These are all checked by * the asserts. */ ASSERT(ips && inodes >= 2 && inodes <= 5); ASSERT(lock_mode & (XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)); ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED | XFS_MMAPLOCK_SHARED | XFS_ILOCK_SHARED))); ASSERT(!(lock_mode & XFS_MMAPLOCK_EXCL) || inodes <= XFS_MMAPLOCK_MAX_SUBCLASS + 1); ASSERT(!(lock_mode & XFS_ILOCK_EXCL) || inodes <= XFS_ILOCK_MAX_SUBCLASS + 1); if (lock_mode & XFS_IOLOCK_EXCL) { ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL))); } else if (lock_mode & XFS_MMAPLOCK_EXCL) ASSERT(!(lock_mode & XFS_ILOCK_EXCL)); again: try_lock = false; i = 0; for (; i < inodes; i++) { ASSERT(ips[i]); if (i && (ips[i] == ips[i - 1])) /* Already locked */ continue; /* * If try_lock is not set yet, make sure all locked inodes are * not in the AIL. If any are, set try_lock to be used later. */ if (!try_lock) { for (j = (i - 1); j >= 0 && !try_lock; j--) { lp = &ips[j]->i_itemp->ili_item; if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) try_lock = true; } } /* * If any of the previous locks we have locked is in the AIL, * we must TRY to get the second and subsequent locks. If * we can't get any, we must release all we have * and try again. */ if (!try_lock) { xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i)); continue; } /* try_lock means we have an inode locked that is in the AIL. */ ASSERT(i != 0); if (xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) continue; /* * Unlock all previous guys and try again. xfs_iunlock will try * to push the tail if the inode is in the AIL. */ attempts++; for (j = i - 1; j >= 0; j--) { /* * Check to see if we've already unlocked this one. Not * the first one going back, and the inode ptr is the * same. */ if (j != (i - 1) && ips[j] == ips[j + 1]) continue; xfs_iunlock(ips[j], lock_mode); } if ((attempts % 5) == 0) { delay(1); /* Don't just spin the CPU */ } goto again; } } /* * xfs_lock_two_inodes() can only be used to lock ilock. The iolock and * mmaplock must be double-locked separately since we use i_rwsem and * invalidate_lock for that. We now support taking one lock EXCL and the * other SHARED. */ void xfs_lock_two_inodes( struct xfs_inode *ip0, uint ip0_mode, struct xfs_inode *ip1, uint ip1_mode) { int attempts = 0; struct xfs_log_item *lp; ASSERT(hweight32(ip0_mode) == 1); ASSERT(hweight32(ip1_mode) == 1); ASSERT(!(ip0_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))); ASSERT(!(ip1_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))); ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))); ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))); ASSERT(ip0->i_ino != ip1->i_ino); if (ip0->i_ino > ip1->i_ino) { swap(ip0, ip1); swap(ip0_mode, ip1_mode); } again: xfs_ilock(ip0, xfs_lock_inumorder(ip0_mode, 0)); /* * If the first lock we have locked is in the AIL, we must TRY to get * the second lock. If we can't get it, we must release the first one * and try again. */ lp = &ip0->i_itemp->ili_item; if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) { if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) { xfs_iunlock(ip0, ip0_mode); if ((++attempts % 5) == 0) delay(1); /* Don't just spin the CPU */ goto again; } } else { xfs_ilock(ip1, xfs_lock_inumorder(ip1_mode, 1)); } } /* * Lookups up an inode from "name". If ci_name is not NULL, then a CI match * is allowed, otherwise it has to be an exact match. If a CI match is found, * ci_name->name will point to a the actual name (caller must free) or * will be set to NULL if an exact match is found. */ int xfs_lookup( struct xfs_inode *dp, const struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name) { xfs_ino_t inum; int error; trace_xfs_lookup(dp, name); if (xfs_is_shutdown(dp->i_mount)) return -EIO; if (xfs_ifork_zapped(dp, XFS_DATA_FORK)) return -EIO; error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name); if (error) goto out_unlock; error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp); if (error) goto out_free_name; return 0; out_free_name: if (ci_name) kfree(ci_name->name); out_unlock: *ipp = NULL; return error; } /* * Initialise a newly allocated inode and return the in-core inode to the * caller locked exclusively. * * Caller is responsible for unlocking the inode manually upon return */ int xfs_icreate( struct xfs_trans *tp, xfs_ino_t ino, const struct xfs_icreate_args *args, struct xfs_inode **ipp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_inode *ip = NULL; int error; /* * Get the in-core inode with the lock held exclusively to prevent * others from looking at until we're done. */ error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE, XFS_ILOCK_EXCL, &ip); if (error) return error; ASSERT(ip != NULL); xfs_trans_ijoin(tp, ip, 0); xfs_inode_init(tp, args, ip); /* now that we have an i_mode we can setup the inode structure */ xfs_setup_inode(ip); *ipp = ip; return 0; } /* Return dquots for the ids that will be assigned to a new file. */ int xfs_icreate_dqalloc( const struct xfs_icreate_args *args, struct xfs_dquot **udqpp, struct xfs_dquot **gdqpp, struct xfs_dquot **pdqpp) { struct inode *dir = VFS_I(args->pip); kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; prid_t prid = 0; unsigned int flags = XFS_QMOPT_QUOTALL; if (args->idmap) { /* * The uid/gid computation code must match what the VFS uses to * assign i_[ug]id. INHERIT adjusts the gid computation for * setgid/grpid systems. */ uid = mapped_fsuid(args->idmap, i_user_ns(dir)); gid = mapped_fsgid(args->idmap, i_user_ns(dir)); prid = xfs_get_initial_prid(args->pip); flags |= XFS_QMOPT_INHERIT; } *udqpp = *gdqpp = *pdqpp = NULL; return xfs_qm_vop_dqalloc(args->pip, uid, gid, prid, flags, udqpp, gdqpp, pdqpp); } int xfs_create( const struct xfs_icreate_args *args, struct xfs_name *name, struct xfs_inode **ipp) { struct xfs_inode *dp = args->pip; struct xfs_dir_update du = { .dp = dp, .name = name, }; struct xfs_mount *mp = dp->i_mount; struct xfs_trans *tp = NULL; struct xfs_dquot *udqp; struct xfs_dquot *gdqp; struct xfs_dquot *pdqp; struct xfs_trans_res *tres; xfs_ino_t ino; bool unlock_dp_on_error = false; bool is_dir = S_ISDIR(args->mode); uint resblks; int error; trace_xfs_create(dp, name); if (xfs_is_shutdown(mp)) return -EIO; if (xfs_ifork_zapped(dp, XFS_DATA_FORK)) return -EIO; /* Make sure that we have allocated dquot(s) on disk. */ error = xfs_icreate_dqalloc(args, &udqp, &gdqp, &pdqp); if (error) return error; if (is_dir) { resblks = xfs_mkdir_space_res(mp, name->len); tres = &M_RES(mp)->tr_mkdir; } else { resblks = xfs_create_space_res(mp, name->len); tres = &M_RES(mp)->tr_create; } error = xfs_parent_start(mp, &du.ppargs); if (error) goto out_release_dquots; /* * Initially assume that the file does not exist and * reserve the resources for that case. If that is not * the case we'll drop the one we have and get a more * appropriate transaction later. */ error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, &tp); if (error == -ENOSPC) { /* flush outstanding delalloc blocks and retry */ xfs_flush_inodes(mp); error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, &tp); } if (error) goto out_parent; xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; /* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry * pointing to itself. */ error = xfs_dialloc(&tp, dp->i_ino, args->mode, &ino); if (!error) error = xfs_icreate(tp, ino, args, &du.ip); if (error) goto out_trans_cancel; /* * Now we join the directory inode to the transaction. We do not do it * earlier because xfs_dialloc might commit the previous transaction * (and release all the locks). An error from here on will result in * the transaction cancel unlocking dp so don't do it explicitly in the * error path. */ xfs_trans_ijoin(tp, dp, 0); error = xfs_dir_create_child(tp, resblks, &du); if (error) goto out_trans_cancel; /* * If this is a synchronous mount, make sure that the * create transaction goes to disk before returning to * the user. */ if (xfs_has_wsync(mp) || xfs_has_dirsync(mp)) xfs_trans_set_sync(tp); /* * Attach the dquot(s) to the inodes and modify them incore. * These ids of the inode couldn't have changed since the new * inode has been locked ever since it was created. */ xfs_qm_vop_create_dqattach(tp, du.ip, udqp, gdqp, pdqp); error = xfs_trans_commit(tp); if (error) goto out_release_inode; xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); *ipp = du.ip; xfs_iunlock(du.ip, XFS_ILOCK_EXCL); xfs_iunlock(dp, XFS_ILOCK_EXCL); xfs_parent_finish(mp, du.ppargs); return 0; out_trans_cancel: xfs_trans_cancel(tp); out_release_inode: /* * Wait until after the current transaction is aborted to finish the * setup of the inode and release the inode. This prevents recursive * transactions and deadlocks from xfs_inactive. */ if (du.ip) { xfs_iunlock(du.ip, XFS_ILOCK_EXCL); xfs_finish_inode_setup(du.ip); xfs_irele(du.ip); } out_parent: xfs_parent_finish(mp, du.ppargs); out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); if (unlock_dp_on_error) xfs_iunlock(dp, XFS_ILOCK_EXCL); return error; } int xfs_create_tmpfile( const struct xfs_icreate_args *args, struct xfs_inode **ipp) { struct xfs_inode *dp = args->pip; struct xfs_mount *mp = dp->i_mount; struct xfs_inode *ip = NULL; struct xfs_trans *tp = NULL; struct xfs_dquot *udqp; struct xfs_dquot *gdqp; struct xfs_dquot *pdqp; struct xfs_trans_res *tres; xfs_ino_t ino; uint resblks; int error; ASSERT(args->flags & XFS_ICREATE_TMPFILE); if (xfs_is_shutdown(mp)) return -EIO; /* Make sure that we have allocated dquot(s) on disk. */ error = xfs_icreate_dqalloc(args, &udqp, &gdqp, &pdqp); if (error) return error; resblks = XFS_IALLOC_SPACE_RES(mp); tres = &M_RES(mp)->tr_create_tmpfile; error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, &tp); if (error) goto out_release_dquots; error = xfs_dialloc(&tp, dp->i_ino, args->mode, &ino); if (!error) error = xfs_icreate(tp, ino, args, &ip); if (error) goto out_trans_cancel; if (xfs_has_wsync(mp)) xfs_trans_set_sync(tp); /* * Attach the dquot(s) to the inodes and modify them incore. * These ids of the inode couldn't have changed since the new * inode has been locked ever since it was created. */ xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp); error = xfs_iunlink(tp, ip); if (error) goto out_trans_cancel; error = xfs_trans_commit(tp); if (error) goto out_release_inode; xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); *ipp = ip; xfs_iunlock(ip, XFS_ILOCK_EXCL); return 0; out_trans_cancel: xfs_trans_cancel(tp); out_release_inode: /* * Wait until after the current transaction is aborted to finish the * setup of the inode and release the inode. This prevents recursive * transactions and deadlocks from xfs_inactive. */ if (ip) { xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_finish_inode_setup(ip); xfs_irele(ip); } out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); return error; } int xfs_link( struct xfs_inode *tdp, struct xfs_inode *sip, struct xfs_name *target_name) { struct xfs_dir_update du = { .dp = tdp, .name = target_name, .ip = sip, }; struct xfs_mount *mp = tdp->i_mount; struct xfs_trans *tp; int error, nospace_error = 0; int resblks; trace_xfs_link(tdp, target_name); ASSERT(!S_ISDIR(VFS_I(sip)->i_mode)); if (xfs_is_shutdown(mp)) return -EIO; if (xfs_ifork_zapped(tdp, XFS_DATA_FORK)) return -EIO; error = xfs_qm_dqattach(sip); if (error) goto std_return; error = xfs_qm_dqattach(tdp); if (error) goto std_return; error = xfs_parent_start(mp, &du.ppargs); if (error) goto std_return; resblks = xfs_link_space_res(mp, target_name->len); error = xfs_trans_alloc_dir(tdp, &M_RES(mp)->tr_link, sip, &resblks, &tp, &nospace_error); if (error) goto out_parent; /* * We don't allow reservationless or quotaless hardlinking when parent * pointers are enabled because we can't back out if the xattrs must * grow. */ if (du.ppargs && nospace_error) { error = nospace_error; goto error_return; } /* * If we are using project inheritance, we only allow hard link * creation in our tree when the project IDs are the same; else * the tree quota mechanism could be circumvented. */ if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) && tdp->i_projid != sip->i_projid)) { /* * Project quota setup skips special files which can * leave inodes in a PROJINHERIT directory without a * project ID set. We need to allow links to be made * to these "project-less" inodes because userspace * expects them to succeed after project ID setup, * but everything else should be rejected. */ if (!special_file(VFS_I(sip)->i_mode) || sip->i_projid != 0) { error = -EXDEV; goto error_return; } } error = xfs_dir_add_child(tp, resblks, &du); if (error) goto error_return; /* * If this is a synchronous mount, make sure that the * link transaction goes to disk before returning to * the user. */ if (xfs_has_wsync(mp) || xfs_has_dirsync(mp)) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); xfs_iunlock(tdp, XFS_ILOCK_EXCL); xfs_iunlock(sip, XFS_ILOCK_EXCL); xfs_parent_finish(mp, du.ppargs); return error; error_return: xfs_trans_cancel(tp); xfs_iunlock(tdp, XFS_ILOCK_EXCL); xfs_iunlock(sip, XFS_ILOCK_EXCL); out_parent: xfs_parent_finish(mp, du.ppargs); std_return: if (error == -ENOSPC && nospace_error) error = nospace_error; return error; } /* Clear the reflink flag and the cowblocks tag if possible. */ static void xfs_itruncate_clear_reflink_flags( struct xfs_inode *ip) { struct xfs_ifork *dfork; struct xfs_ifork *cfork; if (!xfs_is_reflink_inode(ip)) return; dfork = xfs_ifork_ptr(ip, XFS_DATA_FORK); cfork = xfs_ifork_ptr(ip, XFS_COW_FORK); if (dfork->if_bytes == 0 && cfork->if_bytes == 0) ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; if (cfork->if_bytes == 0) xfs_inode_clear_cowblocks_tag(ip); } /* * Free up the underlying blocks past new_size. The new size must be smaller * than the current size. This routine can be used both for the attribute and * data fork, and does not modify the inode size, which is left to the caller. * * The transaction passed to this routine must have made a permanent log * reservation of at least XFS_ITRUNCATE_LOG_RES. This routine may commit the * given transaction and start new ones, so make sure everything involved in * the transaction is tidy before calling here. Some transaction will be * returned to the caller to be committed. The incoming transaction must * already include the inode, and both inode locks must be held exclusively. * The inode must also be "held" within the transaction. On return the inode * will be "held" within the returned transaction. This routine does NOT * require any disk space to be reserved for it within the transaction. * * If we get an error, we must return with the inode locked and linked into the * current transaction. This keeps things simple for the higher level code, * because it always knows that the inode is locked and held in the transaction * that returns to it whether errors occur or not. We don't mark the inode * dirty on error so that transactions can be easily aborted if possible. */ int xfs_itruncate_extents_flags( struct xfs_trans **tpp, struct xfs_inode *ip, int whichfork, xfs_fsize_t new_size, int flags) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp = *tpp; xfs_fileoff_t first_unmap_block; int error = 0; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (atomic_read(&VFS_I(ip)->i_count)) xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); ASSERT(new_size <= XFS_ISIZE(ip)); ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(ip->i_itemp != NULL); ASSERT(ip->i_itemp->ili_lock_flags == 0); ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); trace_xfs_itruncate_extents_start(ip, new_size); flags |= xfs_bmapi_aflag(whichfork); /* * Since it is possible for space to become allocated beyond * the end of the file (in a crash where the space is allocated * but the inode size is not yet updated), simply remove any * blocks which show up between the new EOF and the maximum * possible file size. * * We have to free all the blocks to the bmbt maximum offset, even if * the page cache can't scale that far. */ first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size); if (!xfs_verify_fileoff(mp, first_unmap_block)) { WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF); return 0; } error = xfs_bunmapi_range(&tp, ip, flags, first_unmap_block, XFS_MAX_FILEOFF); if (error) goto out; if (whichfork == XFS_DATA_FORK) { /* Remove all pending CoW reservations. */ error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block, XFS_MAX_FILEOFF, true); if (error) goto out; xfs_itruncate_clear_reflink_flags(ip); } /* * Always re-log the inode so that our permanent transaction can keep * on rolling it forward in the log. */ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); trace_xfs_itruncate_extents_end(ip, new_size); out: *tpp = tp; return error; } int xfs_release( xfs_inode_t *ip) { xfs_mount_t *mp = ip->i_mount; int error = 0; if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0)) return 0; /* If this is a read-only mount, don't do this (would generate I/O) */ if (xfs_is_readonly(mp)) return 0; if (!xfs_is_shutdown(mp)) { int truncated; /* * If we previously truncated this file and removed old data * in the process, we want to initiate "early" writeout on * the last close. This is an attempt to combat the notorious * NULL files problem which is particularly noticeable from a * truncate down, buffered (re-)write (delalloc), followed by * a crash. What we are effectively doing here is * significantly reducing the time window where we'd otherwise * be exposed to that problem. */ truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED); if (truncated) { xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE); if (ip->i_delayed_blks > 0) { error = filemap_flush(VFS_I(ip)->i_mapping); if (error) return error; } } } if (VFS_I(ip)->i_nlink == 0) return 0; /* * If we can't get the iolock just skip truncating the blocks past EOF * because we could deadlock with the mmap_lock otherwise. We'll get * another chance to drop them once the last reference to the inode is * dropped, so we'll never leak blocks permanently. */ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) return 0; if (xfs_can_free_eofblocks(ip)) { /* * Check if the inode is being opened, written and closed * frequently and we have delayed allocation blocks outstanding * (e.g. streaming writes from the NFS server), truncating the * blocks past EOF will cause fragmentation to occur. * * In this case don't do the truncation, but we have to be * careful how we detect this case. Blocks beyond EOF show up as * i_delayed_blks even when the inode is clean, so we need to * truncate them away first before checking for a dirty release. * Hence on the first dirty close we will still remove the * speculative allocation, but after that we will leave it in * place. */ if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE)) goto out_unlock; error = xfs_free_eofblocks(ip); if (error) goto out_unlock; /* delalloc blocks after truncation means it really is dirty */ if (ip->i_delayed_blks) xfs_iflags_set(ip, XFS_IDIRTY_RELEASE); } out_unlock: xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } /* * Mark all the buffers attached to this directory stale. In theory we should * never be freeing a directory with any blocks at all, but this covers the * case where we've recovered a directory swap with a "temporary" directory * created by online repair and now need to dump it. */ STATIC void xfs_inactive_dir( struct xfs_inode *dp) { struct xfs_iext_cursor icur; struct xfs_bmbt_irec got; struct xfs_mount *mp = dp->i_mount; struct xfs_da_geometry *geo = mp->m_dir_geo; struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK); xfs_fileoff_t off; /* * Invalidate each directory block. All directory blocks are of * fsbcount length and alignment, so we only need to walk those same * offsets. We hold the only reference to this inode, so we must wait * for the buffer locks. */ for_each_xfs_iext(ifp, &icur, &got) { for (off = round_up(got.br_startoff, geo->fsbcount); off < got.br_startoff + got.br_blockcount; off += geo->fsbcount) { struct xfs_buf *bp = NULL; xfs_fsblock_t fsbno; int error; fsbno = (off - got.br_startoff) + got.br_startblock; error = xfs_buf_incore(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, fsbno), XFS_FSB_TO_BB(mp, geo->fsbcount), XBF_LIVESCAN, &bp); if (error) continue; xfs_buf_stale(bp); xfs_buf_relse(bp); } } } /* * xfs_inactive_truncate * * Called to perform a truncate when an inode becomes unlinked. */ STATIC int xfs_inactive_truncate( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { ASSERT(xfs_is_shutdown(mp)); return error; } xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); /* * Log the inode size first to prevent stale data exposure in the event * of a system crash before the truncate completes. See the related * comment in xfs_vn_setattr_size() for details. */ ip->i_disk_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0); if (error) goto error_trans_cancel; ASSERT(ip->i_df.if_nextents == 0); error = xfs_trans_commit(tp); if (error) goto error_unlock; xfs_iunlock(ip, XFS_ILOCK_EXCL); return 0; error_trans_cancel: xfs_trans_cancel(tp); error_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } /* * xfs_inactive_ifree() * * Perform the inode free when an inode is unlinked. */ STATIC int xfs_inactive_ifree( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error; /* * We try to use a per-AG reservation for any block needed by the finobt * tree, but as the finobt feature predates the per-AG reservation * support a degraded file system might not have enough space for the * reservation at mount time. In that case try to dip into the reserved * pool and pray. * * Send a warning if the reservation does happen to fail, as the inode * now remains allocated and sits on the unlinked list until the fs is * repaired. */ if (unlikely(mp->m_finobt_nores)) { error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp); } else { error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp); } if (error) { if (error == -ENOSPC) { xfs_warn_ratelimited(mp, "Failed to remove inode(s) from unlinked list. " "Please free space, unmount and run xfs_repair."); } else { ASSERT(xfs_is_shutdown(mp)); } return error; } /* * We do not hold the inode locked across the entire rolling transaction * here. We only need to hold it for the first transaction that * xfs_ifree() builds, which may mark the inode XFS_ISTALE if the * underlying cluster buffer is freed. Relogging an XFS_ISTALE inode * here breaks the relationship between cluster buffer invalidation and * stale inode invalidation on cluster buffer item journal commit * completion, and can result in leaving dirty stale inodes hanging * around in memory. * * We have no need for serialising this inode operation against other * operations - we freed the inode and hence reallocation is required * and that will serialise on reallocating the space the deferops need * to free. Hence we can unlock the inode on the first commit of * the transaction rather than roll it right through the deferops. This * avoids relogging the XFS_ISTALE inode. * * We check that xfs_ifree() hasn't grown an internal transaction roll * by asserting that the inode is still locked when it returns. */ xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); error = xfs_ifree(tp, ip); xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (error) { /* * If we fail to free the inode, shut down. The cancel * might do that, we need to make sure. Otherwise the * inode might be lost for a long time or forever. */ if (!xfs_is_shutdown(mp)) { xfs_notice(mp, "%s: xfs_ifree returned error %d", __func__, error); xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); } xfs_trans_cancel(tp); return error; } /* * Credit the quota account(s). The inode is gone. */ xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1); return xfs_trans_commit(tp); } /* * Returns true if we need to update the on-disk metadata before we can free * the memory used by this inode. Updates include freeing post-eof * preallocations; freeing COW staging extents; and marking the inode free in * the inobt if it is on the unlinked list. */ bool xfs_inode_needs_inactive( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *cow_ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); /* * If the inode is already free, then there can be nothing * to clean up here. */ if (VFS_I(ip)->i_mode == 0) return false; /* * If this is a read-only mount, don't do this (would generate I/O) * unless we're in log recovery and cleaning the iunlinked list. */ if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) return false; /* If the log isn't running, push inodes straight to reclaim. */ if (xfs_is_shutdown(mp) || xfs_has_norecovery(mp)) return false; /* Metadata inodes require explicit resource cleanup. */ if (xfs_is_metadata_inode(ip)) return false; /* Want to clean out the cow blocks if there are any. */ if (cow_ifp && cow_ifp->if_bytes > 0) return true; /* Unlinked files must be freed. */ if (VFS_I(ip)->i_nlink == 0) return true; /* * This file isn't being freed, so check if there are post-eof blocks * to free. * * Note: don't bother with iolock here since lockdep complains about * acquiring it in reclaim context. We have the only reference to the * inode at this point anyways. */ return xfs_can_free_eofblocks(ip); } /* * Save health status somewhere, if we're dumping an inode with uncorrected * errors and online repair isn't running. */ static inline void xfs_inactive_health( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; unsigned int sick; unsigned int checked; xfs_inode_measure_sickness(ip, &sick, &checked); if (!sick) return; trace_xfs_inode_unfixed_corruption(ip, sick); if (sick & XFS_SICK_INO_FORGET) return; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); if (!pag) { /* There had better still be a perag structure! */ ASSERT(0); return; } xfs_ag_mark_sick(pag, XFS_SICK_AG_INODES); xfs_perag_put(pag); } /* * xfs_inactive * * This is called when the vnode reference count for the vnode * goes to zero. If the file has been unlinked, then it must * now be truncated. Also, we clear all of the read-ahead state * kept for the inode here since the file is now closed. */ int xfs_inactive( xfs_inode_t *ip) { struct xfs_mount *mp; int error = 0; int truncate = 0; /* * If the inode is already free, then there can be nothing * to clean up here. */ if (VFS_I(ip)->i_mode == 0) { ASSERT(ip->i_df.if_broot_bytes == 0); goto out; } mp = ip->i_mount; ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY)); xfs_inactive_health(ip); /* * If this is a read-only mount, don't do this (would generate I/O) * unless we're in log recovery and cleaning the iunlinked list. */ if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) goto out; /* Metadata inodes require explicit resource cleanup. */ if (xfs_is_metadata_inode(ip)) goto out; /* Try to clean out the cow blocks if there are any. */ if (xfs_inode_has_cow_data(ip)) xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); if (VFS_I(ip)->i_nlink != 0) { /* * Note: don't bother with iolock here since lockdep complains * about acquiring it in reclaim context. We have the only * reference to the inode at this point anyways. */ if (xfs_can_free_eofblocks(ip)) error = xfs_free_eofblocks(ip); goto out; } if (S_ISREG(VFS_I(ip)->i_mode) && (ip->i_disk_size != 0 || XFS_ISIZE(ip) != 0 || ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0)) truncate = 1; if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { /* * If this inode is being inactivated during a quotacheck and * has not yet been scanned by quotacheck, we /must/ remove * the dquots from the inode before inactivation changes the * block and inode counts. Most probably this is a result of * reloading the incore iunlinked list to purge unrecovered * unlinked inodes. */ xfs_qm_dqdetach(ip); } else { error = xfs_qm_dqattach(ip); if (error) goto out; } if (S_ISDIR(VFS_I(ip)->i_mode) && ip->i_df.if_nextents > 0) { xfs_inactive_dir(ip); truncate = 1; } if (S_ISLNK(VFS_I(ip)->i_mode)) error = xfs_inactive_symlink(ip); else if (truncate) error = xfs_inactive_truncate(ip); if (error) goto out; /* * If there are attributes associated with the file then blow them away * now. The code calls a routine that recursively deconstructs the * attribute fork. If also blows away the in-core attribute fork. */ if (xfs_inode_has_attr_fork(ip)) { error = xfs_attr_inactive(ip); if (error) goto out; } ASSERT(ip->i_forkoff == 0); /* * Free the inode. */ error = xfs_inactive_ifree(ip); out: /* * We're done making metadata updates for this inode, so we can release * the attached dquots. */ xfs_qm_dqdetach(ip); return error; } /* * Find an inode on the unlinked list. This does not take references to the * inode as we have existence guarantees by holding the AGI buffer lock and that * only unlinked, referenced inodes can be on the unlinked inode list. If we * don't find the inode in cache, then let the caller handle the situation. */ struct xfs_inode * xfs_iunlink_lookup( struct xfs_perag *pag, xfs_agino_t agino) { struct xfs_inode *ip; rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, agino); if (!ip) { /* Caller can handle inode not being in memory. */ rcu_read_unlock(); return NULL; } /* * Inode in RCU freeing limbo should not happen. Warn about this and * let the caller handle the failure. */ if (WARN_ON_ONCE(!ip->i_ino)) { rcu_read_unlock(); return NULL; } ASSERT(!xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM)); rcu_read_unlock(); return ip; } /* * Load the inode @next_agino into the cache and set its prev_unlinked pointer * to @prev_agino. Caller must hold the AGI to synchronize with other changes * to the unlinked list. */ int xfs_iunlink_reload_next( struct xfs_trans *tp, struct xfs_buf *agibp, xfs_agino_t prev_agino, xfs_agino_t next_agino) { struct xfs_perag *pag = agibp->b_pag; struct xfs_mount *mp = pag->pag_mount; struct xfs_inode *next_ip = NULL; xfs_ino_t ino; int error; ASSERT(next_agino != NULLAGINO); #ifdef DEBUG rcu_read_lock(); next_ip = radix_tree_lookup(&pag->pag_ici_root, next_agino); ASSERT(next_ip == NULL); rcu_read_unlock(); #endif xfs_info_ratelimited(mp, "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating recovery.", next_agino, pag->pag_agno); /* * Use an untrusted lookup just to be cautious in case the AGI has been * corrupted and now points at a free inode. That shouldn't happen, * but we'd rather shut down now since we're already running in a weird * situation. */ ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino); error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip); if (error) { xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); return error; } /* If this is not an unlinked inode, something is very wrong. */ if (VFS_I(next_ip)->i_nlink != 0) { xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); error = -EFSCORRUPTED; goto rele; } next_ip->i_prev_unlinked = prev_agino; trace_xfs_iunlink_reload_next(next_ip); rele: ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE)); if (xfs_is_quotacheck_running(mp) && next_ip) xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED); xfs_irele(next_ip); return error; } /* * Look up the inode number specified and if it is not already marked XFS_ISTALE * mark it stale. We should only find clean inodes in this lookup that aren't * already stale. */ static void xfs_ifree_mark_inode_stale( struct xfs_perag *pag, struct xfs_inode *free_ip, xfs_ino_t inum) { struct xfs_mount *mp = pag->pag_mount; struct xfs_inode_log_item *iip; struct xfs_inode *ip; retry: rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum)); /* Inode not in memory, nothing to do */ if (!ip) { rcu_read_unlock(); return; } /* * because this is an RCU protected lookup, we could find a recently * freed or even reallocated inode during the lookup. We need to check * under the i_flags_lock for a valid inode here. Skip it if it is not * valid, the wrong inode or stale. */ spin_lock(&ip->i_flags_lock); if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) goto out_iflags_unlock; /* * Don't try to lock/unlock the current inode, but we _cannot_ skip the * other inodes that we did not find in the list attached to the buffer * and are not already marked stale. If we can't lock it, back off and * retry. */ if (ip != free_ip) { if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); delay(1); goto retry; } } ip->i_flags |= XFS_ISTALE; /* * If the inode is flushing, it is already attached to the buffer. All * we needed to do here is mark the inode stale so buffer IO completion * will remove it from the AIL. */ iip = ip->i_itemp; if (__xfs_iflags_test(ip, XFS_IFLUSHING)) { ASSERT(!list_empty(&iip->ili_item.li_bio_list)); ASSERT(iip->ili_last_fields); goto out_iunlock; } /* * Inodes not attached to the buffer can be released immediately. * Everything else has to go through xfs_iflush_abort() on journal * commit as the flock synchronises removal of the inode from the * cluster buffer against inode reclaim. */ if (!iip || list_empty(&iip->ili_item.li_bio_list)) goto out_iunlock; __xfs_iflags_set(ip, XFS_IFLUSHING); spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); /* we have a dirty inode in memory that has not yet been flushed. */ spin_lock(&iip->ili_lock); iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; iip->ili_fsync_fields = 0; spin_unlock(&iip->ili_lock); ASSERT(iip->ili_last_fields); if (ip != free_ip) xfs_iunlock(ip, XFS_ILOCK_EXCL); return; out_iunlock: if (ip != free_ip) xfs_iunlock(ip, XFS_ILOCK_EXCL); out_iflags_unlock: spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); } /* * A big issue when freeing the inode cluster is that we _cannot_ skip any * inodes that are in memory - they all must be marked stale and attached to * the cluster buffer. */ static int xfs_ifree_cluster( struct xfs_trans *tp, struct xfs_perag *pag, struct xfs_inode *free_ip, struct xfs_icluster *xic) { struct xfs_mount *mp = free_ip->i_mount; struct xfs_ino_geometry *igeo = M_IGEO(mp); struct xfs_buf *bp; xfs_daddr_t blkno; xfs_ino_t inum = xic->first_ino; int nbufs; int i, j; int ioffset; int error; nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster; for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) { /* * The allocation bitmap tells us which inodes of the chunk were * physically allocated. Skip the cluster if an inode falls into * a sparse region. */ ioffset = inum - xic->first_ino; if ((xic->alloc & XFS_INOBT_MASK(ioffset)) == 0) { ASSERT(ioffset % igeo->inodes_per_cluster == 0); continue; } blkno = XFS_AGB_TO_DADDR(mp, XFS_INO_TO_AGNO(mp, inum), XFS_INO_TO_AGBNO(mp, inum)); /* * We obtain and lock the backing buffer first in the process * here to ensure dirty inodes attached to the buffer remain in * the flushing state while we mark them stale. * * If we scan the in-memory inodes first, then buffer IO can * complete before we get a lock on it, and hence we may fail * to mark all the active inodes on the buffer stale. */ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, mp->m_bsize * igeo->blocks_per_cluster, XBF_UNMAPPED, &bp); if (error) return error; /* * This buffer may not have been correctly initialised as we * didn't read it from disk. That's not important because we are * only using to mark the buffer as stale in the log, and to * attach stale cached inodes on it. * * For the inode that triggered the cluster freeing, this * attachment may occur in xfs_inode_item_precommit() after we * have marked this buffer stale. If this buffer was not in * memory before xfs_ifree_cluster() started, it will not be * marked XBF_DONE and this will cause problems later in * xfs_inode_item_precommit() when we trip over a (stale, !done) * buffer to attached to the transaction. * * Hence we have to mark the buffer as XFS_DONE here. This is * safe because we are also marking the buffer as XBF_STALE and * XFS_BLI_STALE. That means it will never be dispatched for * IO and it won't be unlocked until the cluster freeing has * been committed to the journal and the buffer unpinned. If it * is written, we want to know about it, and we want it to * fail. We can acheive this by adding a write verifier to the * buffer. */ bp->b_flags |= XBF_DONE; bp->b_ops = &xfs_inode_buf_ops; /* * Now we need to set all the cached clean inodes as XFS_ISTALE, * too. This requires lookups, and will skip inodes that we've * already marked XFS_ISTALE. */ for (i = 0; i < igeo->inodes_per_cluster; i++) xfs_ifree_mark_inode_stale(pag, free_ip, inum + i); xfs_trans_stale_inode_buf(tp, bp); xfs_trans_binval(tp, bp); } return 0; } /* * This is called to return an inode to the inode free list. The inode should * already be truncated to 0 length and have no pages associated with it. This * routine also assumes that the inode is already a part of the transaction. * * The on-disk copy of the inode will have been added to the list of unlinked * inodes in the AGI. We need to remove the inode from that list atomically with * respect to freeing it here. */ int xfs_ifree( struct xfs_trans *tp, struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; struct xfs_icluster xic = { 0 }; struct xfs_inode_log_item *iip = ip->i_itemp; int error; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(VFS_I(ip)->i_nlink == 0); ASSERT(ip->i_df.if_nextents == 0); ASSERT(ip->i_disk_size == 0 || !S_ISREG(VFS_I(ip)->i_mode)); ASSERT(ip->i_nblocks == 0); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); error = xfs_inode_uninit(tp, pag, ip, &xic); if (error) goto out; if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) xfs_iflags_clear(ip, XFS_IPRESERVE_DM_FIELDS); /* Don't attempt to replay owner changes for a deleted inode */ spin_lock(&iip->ili_lock); iip->ili_fields &= ~(XFS_ILOG_AOWNER | XFS_ILOG_DOWNER); spin_unlock(&iip->ili_lock); if (xic.deleted) error = xfs_ifree_cluster(tp, pag, ip, &xic); out: xfs_perag_put(pag); return error; } /* * This is called to unpin an inode. The caller must have the inode locked * in at least shared mode so that the buffer cannot be subsequently pinned * once someone is waiting for it to be unpinned. */ static void xfs_iunpin( struct xfs_inode *ip) { xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); trace_xfs_inode_unpin_nowait(ip, _RET_IP_); /* Give the log a push to start the unpinning I/O */ xfs_log_force_seq(ip->i_mount, ip->i_itemp->ili_commit_seq, 0, NULL); } static void __xfs_iunpin_wait( struct xfs_inode *ip) { wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IPINNED_BIT); DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IPINNED_BIT); xfs_iunpin(ip); do { prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (xfs_ipincount(ip)) io_schedule(); } while (xfs_ipincount(ip)); finish_wait(wq, &wait.wq_entry); } void xfs_iunpin_wait( struct xfs_inode *ip) { if (xfs_ipincount(ip)) __xfs_iunpin_wait(ip); } /* * Removing an inode from the namespace involves removing the directory entry * and dropping the link count on the inode. Removing the directory entry can * result in locking an AGF (directory blocks were freed) and removing a link * count can result in placing the inode on an unlinked list which results in * locking an AGI. * * The big problem here is that we have an ordering constraint on AGF and AGI * locking - inode allocation locks the AGI, then can allocate a new extent for * new inodes, locking the AGF after the AGI. Similarly, freeing the inode * removes the inode from the unlinked list, requiring that we lock the AGI * first, and then freeing the inode can result in an inode chunk being freed * and hence freeing disk space requiring that we lock an AGF. * * Hence the ordering that is imposed by other parts of the code is AGI before * AGF. This means we cannot remove the directory entry before we drop the inode * reference count and put it on the unlinked list as this results in a lock * order of AGF then AGI, and this can deadlock against inode allocation and * freeing. Therefore we must drop the link counts before we remove the * directory entry. * * This is still safe from a transactional point of view - it is not until we * get to xfs_defer_finish() that we have the possibility of multiple * transactions in this operation. Hence as long as we remove the directory * entry and drop the link count in the first transaction of the remove * operation, there are no transactional constraints on the ordering here. */ int xfs_remove( struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip) { struct xfs_dir_update du = { .dp = dp, .name = name, .ip = ip, }; struct xfs_mount *mp = dp->i_mount; struct xfs_trans *tp = NULL; int is_dir = S_ISDIR(VFS_I(ip)->i_mode); int dontcare; int error = 0; uint resblks; trace_xfs_remove(dp, name); if (xfs_is_shutdown(mp)) return -EIO; if (xfs_ifork_zapped(dp, XFS_DATA_FORK)) return -EIO; error = xfs_qm_dqattach(dp); if (error) goto std_return; error = xfs_qm_dqattach(ip); if (error) goto std_return; error = xfs_parent_start(mp, &du.ppargs); if (error) goto std_return; /* * We try to get the real space reservation first, allowing for * directory btree deletion(s) implying possible bmap insert(s). If we * can't get the space reservation then we use 0 instead, and avoid the * bmap btree insert(s) in the directory code by, if the bmap insert * tries to happen, instead trimming the LAST block from the directory. * * Ignore EDQUOT and ENOSPC being returned via nospace_error because * the directory code can handle a reservationless update and we don't * want to prevent a user from trying to free space by deleting things. */ resblks = xfs_remove_space_res(mp, name->len); error = xfs_trans_alloc_dir(dp, &M_RES(mp)->tr_remove, ip, &resblks, &tp, &dontcare); if (error) { ASSERT(error != -ENOSPC); goto out_parent; } error = xfs_dir_remove_child(tp, resblks, &du); if (error) goto out_trans_cancel; /* * If this is a synchronous mount, make sure that the * remove transaction goes to disk before returning to * the user. */ if (xfs_has_wsync(mp) || xfs_has_dirsync(mp)) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) goto out_unlock; if (is_dir && xfs_inode_is_filestream(ip)) xfs_filestream_deassociate(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_iunlock(dp, XFS_ILOCK_EXCL); xfs_parent_finish(mp, du.ppargs); return 0; out_trans_cancel: xfs_trans_cancel(tp); out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_iunlock(dp, XFS_ILOCK_EXCL); out_parent: xfs_parent_finish(mp, du.ppargs); std_return: return error; } static inline void xfs_iunlock_rename( struct xfs_inode **i_tab, int num_inodes) { int i; for (i = num_inodes - 1; i >= 0; i--) { /* Skip duplicate inodes if src and target dps are the same */ if (!i_tab[i] || (i > 0 && i_tab[i] == i_tab[i - 1])) continue; xfs_iunlock(i_tab[i], XFS_ILOCK_EXCL); } } /* * Enter all inodes for a rename transaction into a sorted array. */ #define __XFS_SORT_INODES 5 STATIC void xfs_sort_for_rename( struct xfs_inode *dp1, /* in: old (source) directory inode */ struct xfs_inode *dp2, /* in: new (target) directory inode */ struct xfs_inode *ip1, /* in: inode of old entry */ struct xfs_inode *ip2, /* in: inode of new entry */ struct xfs_inode *wip, /* in: whiteout inode */ struct xfs_inode **i_tab,/* out: sorted array of inodes */ int *num_inodes) /* in/out: inodes in array */ { int i; ASSERT(*num_inodes == __XFS_SORT_INODES); memset(i_tab, 0, *num_inodes * sizeof(struct xfs_inode *)); /* * i_tab contains a list of pointers to inodes. We initialize * the table here & we'll sort it. We will then use it to * order the acquisition of the inode locks. * * Note that the table may contain duplicates. e.g., dp1 == dp2. */ i = 0; i_tab[i++] = dp1; i_tab[i++] = dp2; i_tab[i++] = ip1; if (ip2) i_tab[i++] = ip2; if (wip) i_tab[i++] = wip; *num_inodes = i; xfs_sort_inodes(i_tab, *num_inodes); } void xfs_sort_inodes( struct xfs_inode **i_tab, unsigned int num_inodes) { int i, j; ASSERT(num_inodes <= __XFS_SORT_INODES); /* * Sort the elements via bubble sort. (Remember, there are at * most 5 elements to sort, so this is adequate.) */ for (i = 0; i < num_inodes; i++) { for (j = 1; j < num_inodes; j++) { if (i_tab[j]->i_ino < i_tab[j-1]->i_ino) swap(i_tab[j], i_tab[j - 1]); } } } /* * xfs_rename_alloc_whiteout() * * Return a referenced, unlinked, unlocked inode that can be used as a * whiteout in a rename transaction. We use a tmpfile inode here so that if we * crash between allocating the inode and linking it into the rename transaction * recovery will free the inode and we won't leak it. */ static int xfs_rename_alloc_whiteout( struct mnt_idmap *idmap, struct xfs_name *src_name, struct xfs_inode *dp, struct xfs_inode **wip) { struct xfs_icreate_args args = { .idmap = idmap, .pip = dp, .mode = S_IFCHR | WHITEOUT_MODE, .flags = XFS_ICREATE_TMPFILE, }; struct xfs_inode *tmpfile; struct qstr name; int error; error = xfs_create_tmpfile(&args, &tmpfile); if (error) return error; name.name = src_name->name; name.len = src_name->len; error = xfs_inode_init_security(VFS_I(tmpfile), VFS_I(dp), &name); if (error) { xfs_finish_inode_setup(tmpfile); xfs_irele(tmpfile); return error; } /* * Prepare the tmpfile inode as if it were created through the VFS. * Complete the inode setup and flag it as linkable. nlink is already * zero, so we can skip the drop_nlink. */ xfs_setup_iops(tmpfile); xfs_finish_inode_setup(tmpfile); VFS_I(tmpfile)->i_state |= I_LINKABLE; *wip = tmpfile; return 0; } /* * xfs_rename */ int xfs_rename( struct mnt_idmap *idmap, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, struct xfs_inode *target_ip, unsigned int flags) { struct xfs_dir_update du_src = { .dp = src_dp, .name = src_name, .ip = src_ip, }; struct xfs_dir_update du_tgt = { .dp = target_dp, .name = target_name, .ip = target_ip, }; struct xfs_dir_update du_wip = { }; struct xfs_mount *mp = src_dp->i_mount; struct xfs_trans *tp; struct xfs_inode *inodes[__XFS_SORT_INODES]; int i; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); int spaceres; bool retried = false; int error, nospace_error = 0; trace_xfs_rename(src_dp, target_dp, src_name, target_name); if ((flags & RENAME_EXCHANGE) && !target_ip) return -EINVAL; /* * If we are doing a whiteout operation, allocate the whiteout inode * we will be placing at the target and ensure the type is set * appropriately. */ if (flags & RENAME_WHITEOUT) { error = xfs_rename_alloc_whiteout(idmap, src_name, target_dp, &du_wip.ip); if (error) return error; /* setup target dirent info as whiteout */ src_name->type = XFS_DIR3_FT_CHRDEV; } xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, du_wip.ip, inodes, &num_inodes); error = xfs_parent_start(mp, &du_src.ppargs); if (error) goto out_release_wip; if (du_wip.ip) { error = xfs_parent_start(mp, &du_wip.ppargs); if (error) goto out_src_ppargs; } if (target_ip) { error = xfs_parent_start(mp, &du_tgt.ppargs); if (error) goto out_wip_ppargs; } retry: nospace_error = 0; spaceres = xfs_rename_space_res(mp, src_name->len, target_ip != NULL, target_name->len, du_wip.ip != NULL); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, spaceres, 0, 0, &tp); if (error == -ENOSPC) { nospace_error = error; spaceres = 0; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, 0, 0, 0, &tp); } if (error) goto out_tgt_ppargs; /* * We don't allow reservationless renaming when parent pointers are * enabled because we can't back out if the xattrs must grow. */ if (du_src.ppargs && nospace_error) { error = nospace_error; xfs_trans_cancel(tp); goto out_tgt_ppargs; } /* * Attach the dquots to the inodes */ error = xfs_qm_vop_rename_dqattach(inodes); if (error) { xfs_trans_cancel(tp); goto out_tgt_ppargs; } /* * Lock all the participating inodes. Depending upon whether * the target_name exists in the target directory, and * whether the target directory is the same as the source * directory, we can lock from 2 to 5 inodes. */ xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL); /* * Join all the inodes to the transaction. */ xfs_trans_ijoin(tp, src_dp, 0); if (new_parent) xfs_trans_ijoin(tp, target_dp, 0); xfs_trans_ijoin(tp, src_ip, 0); if (target_ip) xfs_trans_ijoin(tp, target_ip, 0); if (du_wip.ip) xfs_trans_ijoin(tp, du_wip.ip, 0); /* * If we are using project inheritance, we only allow renames * into our tree when the project IDs are the same; else the * tree quota mechanism would be circumvented. */ if (unlikely((target_dp->i_diflags & XFS_DIFLAG_PROJINHERIT) && target_dp->i_projid != src_ip->i_projid)) { error = -EXDEV; goto out_trans_cancel; } /* RENAME_EXCHANGE is unique from here on. */ if (flags & RENAME_EXCHANGE) { error = xfs_dir_exchange_children(tp, &du_src, &du_tgt, spaceres); if (error) goto out_trans_cancel; goto out_commit; } /* * Try to reserve quota to handle an expansion of the target directory. * We'll allow the rename to continue in reservationless mode if we hit * a space usage constraint. If we trigger reservationless mode, save * the errno if there isn't any free space in the target directory. */ if (spaceres != 0) { error = xfs_trans_reserve_quota_nblks(tp, target_dp, spaceres, 0, false); if (error == -EDQUOT || error == -ENOSPC) { if (!retried) { xfs_trans_cancel(tp); xfs_iunlock_rename(inodes, num_inodes); xfs_blockgc_free_quota(target_dp, 0); retried = true; goto retry; } nospace_error = error; spaceres = 0; error = 0; } if (error) goto out_trans_cancel; } /* * We don't allow quotaless renaming when parent pointers are enabled * because we can't back out if the xattrs must grow. */ if (du_src.ppargs && nospace_error) { error = nospace_error; goto out_trans_cancel; } /* * Lock the AGI buffers we need to handle bumping the nlink of the * whiteout inode off the unlinked list and to handle dropping the * nlink of the target inode. Per locking order rules, do this in * increasing AG order and before directory block allocation tries to * grab AGFs because we grab AGIs before AGFs. * * The (vfs) caller must ensure that if src is a directory then * target_ip is either null or an empty directory. */ for (i = 0; i < num_inodes && inodes[i] != NULL; i++) { if (inodes[i] == du_wip.ip || (inodes[i] == target_ip && (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { struct xfs_perag *pag; struct xfs_buf *bp; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inodes[i]->i_ino)); error = xfs_read_agi(pag, tp, 0, &bp); xfs_perag_put(pag); if (error) goto out_trans_cancel; } } error = xfs_dir_rename_children(tp, &du_src, &du_tgt, spaceres, &du_wip); if (error) goto out_trans_cancel; if (du_wip.ip) { /* * Now we have a real link, clear the "I'm a tmpfile" state * flag from the inode so it doesn't accidentally get misused in * future. */ VFS_I(du_wip.ip)->i_state &= ~I_LINKABLE; } out_commit: /* * If this is a synchronous mount, make sure that the rename * transaction goes to disk before returning to the user. */ if (xfs_has_wsync(tp->t_mountp) || xfs_has_dirsync(tp->t_mountp)) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); nospace_error = 0; goto out_unlock; out_trans_cancel: xfs_trans_cancel(tp); out_unlock: xfs_iunlock_rename(inodes, num_inodes); out_tgt_ppargs: xfs_parent_finish(mp, du_tgt.ppargs); out_wip_ppargs: xfs_parent_finish(mp, du_wip.ppargs); out_src_ppargs: xfs_parent_finish(mp, du_src.ppargs); out_release_wip: if (du_wip.ip) xfs_irele(du_wip.ip); if (error == -ENOSPC && nospace_error) error = nospace_error; return error; } static int xfs_iflush( struct xfs_inode *ip, struct xfs_buf *bp) { struct xfs_inode_log_item *iip = ip->i_itemp; struct xfs_dinode *dip; struct xfs_mount *mp = ip->i_mount; int error; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING)); ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE || ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); ASSERT(iip->ili_item.li_buf == bp); dip = xfs_buf_offset(bp, ip->i_imap.im_boffset); /* * We don't flush the inode if any of the following checks fail, but we * do still update the log item and attach to the backing buffer as if * the flush happened. This is a formality to facilitate predictable * error handling as the caller will shutdown and fail the buffer. */ error = -EFSCORRUPTED; if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC), mp, XFS_ERRTAG_IFLUSH_1)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad inode %llu magic number 0x%x, ptr "PTR_FMT, __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto flush_out; } if (S_ISREG(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE, mp, XFS_ERRTAG_IFLUSH_3)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad regular inode %llu, ptr "PTR_FMT, __func__, ip->i_ino, ip); goto flush_out; } } else if (S_ISDIR(VFS_I(ip)->i_mode)) { if (XFS_TEST_ERROR( ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && ip->i_df.if_format != XFS_DINODE_FMT_BTREE && ip->i_df.if_format != XFS_DINODE_FMT_LOCAL, mp, XFS_ERRTAG_IFLUSH_4)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad directory inode %llu, ptr "PTR_FMT, __func__, ip->i_ino, ip); goto flush_out; } } if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af) > ip->i_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: detected corrupt incore inode %llu, " "total extents = %llu nblocks = %lld, ptr "PTR_FMT, __func__, ip->i_ino, ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af), ip->i_nblocks, ip); goto flush_out; } if (XFS_TEST_ERROR(ip->i_forkoff > mp->m_sb.sb_inodesize, mp, XFS_ERRTAG_IFLUSH_6)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: bad inode %llu, forkoff 0x%x, ptr "PTR_FMT, __func__, ip->i_ino, ip->i_forkoff, ip); goto flush_out; } /* * Inode item log recovery for v2 inodes are dependent on the flushiter * count for correct sequencing. We bump the flush iteration count so * we can detect flushes which postdate a log record during recovery. * This is redundant as we now log every change and hence this can't * happen but we need to still do it to ensure backwards compatibility * with old kernels that predate logging all inode changes. */ if (!xfs_has_v3inodes(mp)) ip->i_flushiter++; /* * If there are inline format data / attr forks attached to this inode, * make sure they are not corrupt. */ if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL && xfs_ifork_verify_local_data(ip)) goto flush_out; if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_format == XFS_DINODE_FMT_LOCAL && xfs_ifork_verify_local_attr(ip)) goto flush_out; /* * Copy the dirty parts of the inode into the on-disk inode. We always * copy out the core of the inode, because if the inode is dirty at all * the core must be. */ xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn); /* Wrap, we never let the log put out DI_MAX_FLUSH */ if (!xfs_has_v3inodes(mp)) { if (ip->i_flushiter == DI_MAX_FLUSH) ip->i_flushiter = 0; } xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); if (xfs_inode_has_attr_fork(ip)) xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); /* * We've recorded everything logged in the inode, so we'd like to clear * the ili_fields bits so we don't log and flush things unnecessarily. * However, we can't stop logging all this information until the data * we've copied into the disk buffer is written to disk. If we did we * might overwrite the copy of the inode in the log with all the data * after re-logging only part of it, and in the face of a crash we * wouldn't have all the data we need to recover. * * What we do is move the bits to the ili_last_fields field. When * logging the inode, these bits are moved back to the ili_fields field. * In the xfs_buf_inode_iodone() routine we clear ili_last_fields, since * we know that the information those bits represent is permanently on * disk. As long as the flush completes before the inode is logged * again, then both ili_fields and ili_last_fields will be cleared. */ error = 0; flush_out: spin_lock(&iip->ili_lock); iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; iip->ili_fsync_fields = 0; set_bit(XFS_LI_FLUSHING, &iip->ili_item.li_flags); spin_unlock(&iip->ili_lock); /* * Store the current LSN of the inode so that we can tell whether the * item has moved in the AIL from xfs_buf_inode_iodone(). */ xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, &iip->ili_item.li_lsn); /* generate the checksum. */ xfs_dinode_calc_crc(mp, dip); if (error) xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return error; } /* * Non-blocking flush of dirty inode metadata into the backing buffer. * * The caller must have a reference to the inode and hold the cluster buffer * locked. The function will walk across all the inodes on the cluster buffer it * can find and lock without blocking, and flush them to the cluster buffer. * * On successful flushing of at least one inode, the caller must write out the * buffer and release it. If no inodes are flushed, -EAGAIN will be returned and * the caller needs to release the buffer. On failure, the filesystem will be * shut down, the buffer will have been unlocked and released, and EFSCORRUPTED * will be returned. */ int xfs_iflush_cluster( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_log_item *lip, *n; struct xfs_inode *ip; struct xfs_inode_log_item *iip; int clcount = 0; int error = 0; /* * We must use the safe variant here as on shutdown xfs_iflush_abort() * will remove itself from the list. */ list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { iip = (struct xfs_inode_log_item *)lip; ip = iip->ili_inode; /* * Quick and dirty check to avoid locks if possible. */ if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) continue; if (xfs_ipincount(ip)) continue; /* * The inode is still attached to the buffer, which means it is * dirty but reclaim might try to grab it. Check carefully for * that, and grab the ilock while still holding the i_flags_lock * to guarantee reclaim will not be able to reclaim this inode * once we drop the i_flags_lock. */ spin_lock(&ip->i_flags_lock); ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE)); if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) { spin_unlock(&ip->i_flags_lock); continue; } /* * ILOCK will pin the inode against reclaim and prevent * concurrent transactions modifying the inode while we are * flushing the inode. If we get the lock, set the flushing * state before we drop the i_flags_lock. */ if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) { spin_unlock(&ip->i_flags_lock); continue; } __xfs_iflags_set(ip, XFS_IFLUSHING); spin_unlock(&ip->i_flags_lock); /* * Abort flushing this inode if we are shut down because the * inode may not currently be in the AIL. This can occur when * log I/O failure unpins the inode without inserting into the * AIL, leaving a dirty/unpinned inode attached to the buffer * that otherwise looks like it should be flushed. */ if (xlog_is_shutdown(mp->m_log)) { xfs_iunpin_wait(ip); xfs_iflush_abort(ip); xfs_iunlock(ip, XFS_ILOCK_SHARED); error = -EIO; continue; } /* don't block waiting on a log force to unpin dirty inodes */ if (xfs_ipincount(ip)) { xfs_iflags_clear(ip, XFS_IFLUSHING); xfs_iunlock(ip, XFS_ILOCK_SHARED); continue; } if (!xfs_inode_clean(ip)) error = xfs_iflush(ip, bp); else xfs_iflags_clear(ip, XFS_IFLUSHING); xfs_iunlock(ip, XFS_ILOCK_SHARED); if (error) break; clcount++; } if (error) { /* * Shutdown first so we kill the log before we release this * buffer. If it is an INODE_ALLOC buffer and pins the tail * of the log, failing it before the _log_ is shut down can * result in the log tail being moved forward in the journal * on disk because log writes can still be taking place. Hence * unpinning the tail will allow the ICREATE intent to be * removed from the log an recovery will fail with uninitialised * inode cluster buffers. */ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); bp->b_flags |= XBF_ASYNC; xfs_buf_ioend_fail(bp); return error; } if (!clcount) return -EAGAIN; XFS_STATS_INC(mp, xs_icluster_flushcnt); XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount); return 0; } /* Release an inode. */ void xfs_irele( struct xfs_inode *ip) { trace_xfs_irele(ip, _RET_IP_); iput(VFS_I(ip)); } /* * Ensure all commited transactions touching the inode are written to the log. */ int xfs_log_force_inode( struct xfs_inode *ip) { xfs_csn_t seq = 0; xfs_ilock(ip, XFS_ILOCK_SHARED); if (xfs_ipincount(ip)) seq = ip->i_itemp->ili_commit_seq; xfs_iunlock(ip, XFS_ILOCK_SHARED); if (!seq) return 0; return xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC, NULL); } /* * Grab the exclusive iolock for a data copy from src to dest, making sure to * abide vfs locking order (lowest pointer value goes first) and breaking the * layout leases before proceeding. The loop is needed because we cannot call * the blocking break_layout() with the iolocks held, and therefore have to * back out both locks. */ static int xfs_iolock_two_inodes_and_break_layout( struct inode *src, struct inode *dest) { int error; if (src > dest) swap(src, dest); retry: /* Wait to break both inodes' layouts before we start locking. */ error = break_layout(src, true); if (error) return error; if (src != dest) { error = break_layout(dest, true); if (error) return error; } /* Lock one inode and make sure nobody got in and leased it. */ inode_lock(src); error = break_layout(src, false); if (error) { inode_unlock(src); if (error == -EWOULDBLOCK) goto retry; return error; } if (src == dest) return 0; /* Lock the other inode and make sure nobody got in and leased it. */ inode_lock_nested(dest, I_MUTEX_NONDIR2); error = break_layout(dest, false); if (error) { inode_unlock(src); inode_unlock(dest); if (error == -EWOULDBLOCK) goto retry; return error; } return 0; } static int xfs_mmaplock_two_inodes_and_break_dax_layout( struct xfs_inode *ip1, struct xfs_inode *ip2) { int error; bool retry; struct page *page; if (ip1->i_ino > ip2->i_ino) swap(ip1, ip2); again: retry = false; /* Lock the first inode */ xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); error = xfs_break_dax_layouts(VFS_I(ip1), &retry); if (error || retry) { xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); if (error == 0 && retry) goto again; return error; } if (ip1 == ip2) return 0; /* Nested lock the second inode */ xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1)); /* * We cannot use xfs_break_dax_layouts() directly here because it may * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable * for this nested lock case. */ page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); if (page && page_ref_count(page) != 1) { xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); goto again; } return 0; } /* * Lock two inodes so that userspace cannot initiate I/O via file syscalls or * mmap activity. */ int xfs_ilock2_io_mmap( struct xfs_inode *ip1, struct xfs_inode *ip2) { int ret; ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2)); if (ret) return ret; if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2); if (ret) { inode_unlock(VFS_I(ip2)); if (ip1 != ip2) inode_unlock(VFS_I(ip1)); return ret; } } else filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, VFS_I(ip2)->i_mapping); return 0; } /* Unlock both inodes to allow IO and mmap activity. */ void xfs_iunlock2_io_mmap( struct xfs_inode *ip1, struct xfs_inode *ip2) { if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); if (ip1 != ip2) xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); } else filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, VFS_I(ip2)->i_mapping); inode_unlock(VFS_I(ip2)); if (ip1 != ip2) inode_unlock(VFS_I(ip1)); } /* Drop the MMAPLOCK and the IOLOCK after a remap completes. */ void xfs_iunlock2_remapping( struct xfs_inode *ip1, struct xfs_inode *ip2) { xfs_iflags_clear(ip1, XFS_IREMAPPING); if (ip1 != ip2) xfs_iunlock(ip1, XFS_MMAPLOCK_SHARED); xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); if (ip1 != ip2) inode_unlock_shared(VFS_I(ip1)); inode_unlock(VFS_I(ip2)); } /* * Reload the incore inode list for this inode. Caller should ensure that * the link count cannot change, either by taking ILOCK_SHARED or otherwise * preventing other threads from executing. */ int xfs_inode_reload_unlinked_bucket( struct xfs_trans *tp, struct xfs_inode *ip) { struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *agibp; struct xfs_agi *agi; struct xfs_perag *pag; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino); xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); xfs_agino_t prev_agino, next_agino; unsigned int bucket; bool foundit = false; int error; /* Grab the first inode in the list */ pag = xfs_perag_get(mp, agno); error = xfs_ialloc_read_agi(pag, tp, 0, &agibp); xfs_perag_put(pag); if (error) return error; /* * We've taken ILOCK_SHARED and the AGI buffer lock to stabilize the * incore unlinked list pointers for this inode. Check once more to * see if we raced with anyone else to reload the unlinked list. */ if (!xfs_inode_unlinked_incomplete(ip)) { foundit = true; goto out_agibp; } bucket = agino % XFS_AGI_UNLINKED_BUCKETS; agi = agibp->b_addr; trace_xfs_inode_reload_unlinked_bucket(ip); xfs_info_ratelimited(mp, "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating list recovery.", agino, agno); prev_agino = NULLAGINO; next_agino = be32_to_cpu(agi->agi_unlinked[bucket]); while (next_agino != NULLAGINO) { struct xfs_inode *next_ip = NULL; /* Found this caller's inode, set its backlink. */ if (next_agino == agino) { next_ip = ip; next_ip->i_prev_unlinked = prev_agino; foundit = true; goto next_inode; } /* Try in-memory lookup first. */ next_ip = xfs_iunlink_lookup(pag, next_agino); if (next_ip) goto next_inode; /* Inode not in memory, try reloading it. */ error = xfs_iunlink_reload_next(tp, agibp, prev_agino, next_agino); if (error) break; /* Grab the reloaded inode. */ next_ip = xfs_iunlink_lookup(pag, next_agino); if (!next_ip) { /* No incore inode at all? We reloaded it... */ ASSERT(next_ip != NULL); error = -EFSCORRUPTED; break; } next_inode: prev_agino = next_agino; next_agino = next_ip->i_next_unlinked; } out_agibp: xfs_trans_brelse(tp, agibp); /* Should have found this inode somewhere in the iunlinked bucket. */ if (!error && !foundit) error = -EFSCORRUPTED; return error; } /* Decide if this inode is missing its unlinked list and reload it. */ int xfs_inode_reload_unlinked( struct xfs_inode *ip) { struct xfs_trans *tp; int error; error = xfs_trans_alloc_empty(ip->i_mount, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_SHARED); if (xfs_inode_unlinked_incomplete(ip)) error = xfs_inode_reload_unlinked_bucket(tp, ip); xfs_iunlock(ip, XFS_ILOCK_SHARED); xfs_trans_cancel(tp); return error; } /* Has this inode fork been zapped by repair? */ bool xfs_ifork_zapped( const struct xfs_inode *ip, int whichfork) { unsigned int datamask = 0; switch (whichfork) { case XFS_DATA_FORK: switch (ip->i_vnode.i_mode & S_IFMT) { case S_IFDIR: datamask = XFS_SICK_INO_DIR_ZAPPED; break; case S_IFLNK: datamask = XFS_SICK_INO_SYMLINK_ZAPPED; break; } return ip->i_sick & (XFS_SICK_INO_BMBTD_ZAPPED | datamask); case XFS_ATTR_FORK: return ip->i_sick & XFS_SICK_INO_BMBTA_ZAPPED; default: return false; } } /* Compute the number of data and realtime blocks used by a file. */ void xfs_inode_count_blocks( struct xfs_trans *tp, struct xfs_inode *ip, xfs_filblks_t *dblocks, xfs_filblks_t *rblocks) { struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); *rblocks = 0; if (XFS_IS_REALTIME_INODE(ip)) xfs_bmap_count_leaves(ifp, rblocks); *dblocks = ip->i_nblocks - *rblocks; } static void xfs_wait_dax_page( struct inode *inode) { struct xfs_inode *ip = XFS_I(inode); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); schedule(); xfs_ilock(ip, XFS_MMAPLOCK_EXCL); } int xfs_break_dax_layouts( struct inode *inode, bool *retry) { struct page *page; xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL); page = dax_layout_busy_page(inode->i_mapping); if (!page) return 0; *retry = true; return ___wait_var_event(&page->_refcount, atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, 0, 0, xfs_wait_dax_page(inode)); } int xfs_break_layouts( struct inode *inode, uint *iolock, enum layout_break_reason reason) { bool retry; int error; xfs_assert_ilocked(XFS_I(inode), XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL); do { retry = false; switch (reason) { case BREAK_UNMAP: error = xfs_break_dax_layouts(inode, &retry); if (error || retry) break; fallthrough; case BREAK_WRITE: error = xfs_break_leased_layouts(inode, iolock, &retry); break; default: WARN_ON_ONCE(1); error = -EINVAL; } } while (error == 0 && retry); return error; } /* Returns the size of fundamental allocation unit for a file, in bytes. */ unsigned int xfs_inode_alloc_unitsize( struct xfs_inode *ip) { unsigned int blocks = 1; if (XFS_IS_REALTIME_INODE(ip)) blocks = ip->i_mount->m_sb.sb_rextsize; return XFS_FSB_TO_B(ip->i_mount, blocks); } /* Should we always be using copy on write for file writes? */ bool xfs_is_always_cow_inode( struct xfs_inode *ip) { return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount); } |
| 15 15 15 15 15 37 3 37 33 36 13 36 4 37 25 26 26 21 23 26 6 6 6 6 15 15 26 26 4 6 25 1 25 1 26 26 4 25 26 10 26 10 26 23 23 23 23 23 23 23 22 22 23 23 26 26 26 23 26 7 7 7 7 7 7 15 15 15 15 4 4 15 15 15 15 15 15 4 4 4 4 4 2 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Keyring handling * * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/seq_file.h> #include <linux/err.h> #include <linux/user_namespace.h> #include <linux/nsproxy.h> #include <keys/keyring-type.h> #include <keys/user-type.h> #include <linux/assoc_array_priv.h> #include <linux/uaccess.h> #include <net/net_namespace.h> #include "internal.h" /* * When plumbing the depths of the key tree, this sets a hard limit * set on how deep we're willing to go. */ #define KEYRING_SEARCH_MAX_DEPTH 6 /* * We mark pointers we pass to the associative array with bit 1 set if * they're keyrings and clear otherwise. */ #define KEYRING_PTR_SUBTYPE 0x2UL static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x) { return (unsigned long)x & KEYRING_PTR_SUBTYPE; } static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x) { void *object = assoc_array_ptr_to_leaf(x); return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE); } static inline void *keyring_key_to_ptr(struct key *key) { if (key->type == &key_type_keyring) return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE); return key; } static DEFINE_RWLOCK(keyring_name_lock); /* * Clean up the bits of user_namespace that belong to us. */ void key_free_user_ns(struct user_namespace *ns) { write_lock(&keyring_name_lock); list_del_init(&ns->keyring_name_list); write_unlock(&keyring_name_lock); key_put(ns->user_keyring_register); #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif } /* * The keyring key type definition. Keyrings are simply keys of this type and * can be treated as ordinary keys in addition to having their own special * operations. */ static int keyring_preparse(struct key_preparsed_payload *prep); static void keyring_free_preparse(struct key_preparsed_payload *prep); static int keyring_instantiate(struct key *keyring, struct key_preparsed_payload *prep); static void keyring_revoke(struct key *keyring); static void keyring_destroy(struct key *keyring); static void keyring_describe(const struct key *keyring, struct seq_file *m); static long keyring_read(const struct key *keyring, char *buffer, size_t buflen); struct key_type key_type_keyring = { .name = "keyring", .def_datalen = 0, .preparse = keyring_preparse, .free_preparse = keyring_free_preparse, .instantiate = keyring_instantiate, .revoke = keyring_revoke, .destroy = keyring_destroy, .describe = keyring_describe, .read = keyring_read, }; EXPORT_SYMBOL(key_type_keyring); /* * Semaphore to serialise link/link calls to prevent two link calls in parallel * introducing a cycle. */ static DEFINE_MUTEX(keyring_serialise_link_lock); /* * Publish the name of a keyring so that it can be found by name (if it has * one and it doesn't begin with a dot). */ static void keyring_publish_name(struct key *keyring) { struct user_namespace *ns = current_user_ns(); if (keyring->description && keyring->description[0] && keyring->description[0] != '.') { write_lock(&keyring_name_lock); list_add_tail(&keyring->name_link, &ns->keyring_name_list); write_unlock(&keyring_name_lock); } } /* * Preparse a keyring payload */ static int keyring_preparse(struct key_preparsed_payload *prep) { return prep->datalen != 0 ? -EINVAL : 0; } /* * Free a preparse of a user defined key payload */ static void keyring_free_preparse(struct key_preparsed_payload *prep) { } /* * Initialise a keyring. * * Returns 0 on success, -EINVAL if given any data. */ static int keyring_instantiate(struct key *keyring, struct key_preparsed_payload *prep) { assoc_array_init(&keyring->keys); /* make the keyring available by name if it has one */ keyring_publish_name(keyring); return 0; } /* * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit. Ideally we'd * fold the carry back too, but that requires inline asm. */ static u64 mult_64x32_and_fold(u64 x, u32 y) { u64 hi = (u64)(u32)(x >> 32) * y; u64 lo = (u64)(u32)(x) * y; return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32); } /* * Hash a key type and description. */ static void hash_key_type_and_desc(struct keyring_index_key *index_key) { const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP; const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK; const char *description = index_key->description; unsigned long hash, type; u32 piece; u64 acc; int n, desc_len = index_key->desc_len; type = (unsigned long)index_key->type; acc = mult_64x32_and_fold(type, desc_len + 13); acc = mult_64x32_and_fold(acc, 9207); piece = (unsigned long)index_key->domain_tag; acc = mult_64x32_and_fold(acc, piece); acc = mult_64x32_and_fold(acc, 9207); for (;;) { n = desc_len; if (n <= 0) break; if (n > 4) n = 4; piece = 0; memcpy(&piece, description, n); description += n; desc_len -= n; acc = mult_64x32_and_fold(acc, piece); acc = mult_64x32_and_fold(acc, 9207); } /* Fold the hash down to 32 bits if need be. */ hash = acc; if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32) hash ^= acc >> 32; /* Squidge all the keyrings into a separate part of the tree to * ordinary keys by making sure the lowest level segment in the hash is * zero for keyrings and non-zero otherwise. */ if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0) hash |= (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1; else if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0) hash = (hash + (hash << level_shift)) & ~fan_mask; index_key->hash = hash; } /* * Finalise an index key to include a part of the description actually in the * index key, to set the domain tag and to calculate the hash. */ void key_set_index_key(struct keyring_index_key *index_key) { static struct key_tag default_domain_tag = { .usage = REFCOUNT_INIT(1), }; size_t n = min_t(size_t, index_key->desc_len, sizeof(index_key->desc)); memcpy(index_key->desc, index_key->description, n); if (!index_key->domain_tag) { if (index_key->type->flags & KEY_TYPE_NET_DOMAIN) index_key->domain_tag = current->nsproxy->net_ns->key_domain; else index_key->domain_tag = &default_domain_tag; } hash_key_type_and_desc(index_key); } /** * key_put_tag - Release a ref on a tag. * @tag: The tag to release. * * This releases a reference the given tag and returns true if that ref was the * last one. */ bool key_put_tag(struct key_tag *tag) { if (refcount_dec_and_test(&tag->usage)) { kfree_rcu(tag, rcu); return true; } return false; } /** * key_remove_domain - Kill off a key domain and gc its keys * @domain_tag: The domain tag to release. * * This marks a domain tag as being dead and releases a ref on it. If that * wasn't the last reference, the garbage collector is poked to try and delete * all keys that were in the domain. */ void key_remove_domain(struct key_tag *domain_tag) { domain_tag->removed = true; if (!key_put_tag(domain_tag)) key_schedule_gc_links(); } /* * Build the next index key chunk. * * We return it one word-sized chunk at a time. */ static unsigned long keyring_get_key_chunk(const void *data, int level) { const struct keyring_index_key *index_key = data; unsigned long chunk = 0; const u8 *d; int desc_len = index_key->desc_len, n = sizeof(chunk); level /= ASSOC_ARRAY_KEY_CHUNK_SIZE; switch (level) { case 0: return index_key->hash; case 1: return index_key->x; case 2: return (unsigned long)index_key->type; case 3: return (unsigned long)index_key->domain_tag; default: level -= 4; if (desc_len <= sizeof(index_key->desc)) return 0; d = index_key->description + sizeof(index_key->desc); d += level * sizeof(long); desc_len -= sizeof(index_key->desc); if (desc_len > n) desc_len = n; do { chunk <<= 8; chunk |= *d++; } while (--desc_len > 0); return chunk; } } static unsigned long keyring_get_object_key_chunk(const void *object, int level) { const struct key *key = keyring_ptr_to_key(object); return keyring_get_key_chunk(&key->index_key, level); } static bool keyring_compare_object(const void *object, const void *data) { const struct keyring_index_key *index_key = data; const struct key *key = keyring_ptr_to_key(object); return key->index_key.type == index_key->type && key->index_key.domain_tag == index_key->domain_tag && key->index_key.desc_len == index_key->desc_len && memcmp(key->index_key.description, index_key->description, index_key->desc_len) == 0; } /* * Compare the index keys of a pair of objects and determine the bit position * at which they differ - if they differ. */ static int keyring_diff_objects(const void *object, const void *data) { const struct key *key_a = keyring_ptr_to_key(object); const struct keyring_index_key *a = &key_a->index_key; const struct keyring_index_key *b = data; unsigned long seg_a, seg_b; int level, i; level = 0; seg_a = a->hash; seg_b = b->hash; if ((seg_a ^ seg_b) != 0) goto differ; level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8; /* The number of bits contributed by the hash is controlled by a * constant in the assoc_array headers. Everything else thereafter we * can deal with as being machine word-size dependent. */ seg_a = a->x; seg_b = b->x; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); /* The next bit may not work on big endian */ seg_a = (unsigned long)a->type; seg_b = (unsigned long)b->type; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); seg_a = (unsigned long)a->domain_tag; seg_b = (unsigned long)b->domain_tag; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); i = sizeof(a->desc); if (a->desc_len <= i) goto same; for (; i < a->desc_len; i++) { seg_a = *(unsigned char *)(a->description + i); seg_b = *(unsigned char *)(b->description + i); if ((seg_a ^ seg_b) != 0) goto differ_plus_i; } same: return -1; differ_plus_i: level += i; differ: i = level * 8 + __ffs(seg_a ^ seg_b); return i; } /* * Free an object after stripping the keyring flag off of the pointer. */ static void keyring_free_object(void *object) { key_put(keyring_ptr_to_key(object)); } /* * Operations for keyring management by the index-tree routines. */ static const struct assoc_array_ops keyring_assoc_array_ops = { .get_key_chunk = keyring_get_key_chunk, .get_object_key_chunk = keyring_get_object_key_chunk, .compare_object = keyring_compare_object, .diff_objects = keyring_diff_objects, .free_object = keyring_free_object, }; /* * Clean up a keyring when it is destroyed. Unpublish its name if it had one * and dispose of its data. * * The garbage collector detects the final key_put(), removes the keyring from * the serial number tree and then does RCU synchronisation before coming here, * so we shouldn't need to worry about code poking around here with the RCU * readlock held by this time. */ static void keyring_destroy(struct key *keyring) { if (keyring->description) { write_lock(&keyring_name_lock); if (keyring->name_link.next != NULL && !list_empty(&keyring->name_link)) list_del(&keyring->name_link); write_unlock(&keyring_name_lock); } if (keyring->restrict_link) { struct key_restriction *keyres = keyring->restrict_link; key_put(keyres->key); kfree(keyres); } assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops); } /* * Describe a keyring for /proc. */ static void keyring_describe(const struct key *keyring, struct seq_file *m) { if (keyring->description) seq_puts(m, keyring->description); else seq_puts(m, "[anon]"); if (key_is_positive(keyring)) { if (keyring->keys.nr_leaves_on_tree != 0) seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree); else seq_puts(m, ": empty"); } } struct keyring_read_iterator_context { size_t buflen; size_t count; key_serial_t *buffer; }; static int keyring_read_iterator(const void *object, void *data) { struct keyring_read_iterator_context *ctx = data; const struct key *key = keyring_ptr_to_key(object); kenter("{%s,%d},,{%zu/%zu}", key->type->name, key->serial, ctx->count, ctx->buflen); if (ctx->count >= ctx->buflen) return 1; *ctx->buffer++ = key->serial; ctx->count += sizeof(key->serial); return 0; } /* * Read a list of key IDs from the keyring's contents in binary form * * The keyring's semaphore is read-locked by the caller. This prevents someone * from modifying it under us - which could cause us to read key IDs multiple * times. */ static long keyring_read(const struct key *keyring, char *buffer, size_t buflen) { struct keyring_read_iterator_context ctx; long ret; kenter("{%d},,%zu", key_serial(keyring), buflen); if (buflen & (sizeof(key_serial_t) - 1)) return -EINVAL; /* Copy as many key IDs as fit into the buffer */ if (buffer && buflen) { ctx.buffer = (key_serial_t *)buffer; ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { kleave(" = %ld [iterate]", ret); return ret; } } /* Return the size of the buffer needed */ ret = keyring->keys.nr_leaves_on_tree * sizeof(key_serial_t); if (ret <= buflen) kleave("= %ld [ok]", ret); else kleave("= %ld [buffer too small]", ret); return ret; } /* * Allocate a keyring and link into the destination keyring. */ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link, struct key *dest) { struct key *keyring; int ret; keyring = key_alloc(&key_type_keyring, description, uid, gid, cred, perm, flags, restrict_link); if (!IS_ERR(keyring)) { ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL); if (ret < 0) { key_put(keyring); keyring = ERR_PTR(ret); } } return keyring; } EXPORT_SYMBOL(keyring_alloc); /** * restrict_link_reject - Give -EPERM to restrict link * @keyring: The keyring being added to. * @type: The type of key being added. * @payload: The payload of the key intended to be added. * @restriction_key: Keys providing additional data for evaluating restriction. * * Reject the addition of any links to a keyring. It can be overridden by * passing KEY_ALLOC_BYPASS_RESTRICTION to key_instantiate_and_link() when * adding a key to a keyring. * * This is meant to be stored in a key_restriction structure which is passed * in the restrict_link parameter to keyring_alloc(). */ int restrict_link_reject(struct key *keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key) { return -EPERM; } /* * By default, we keys found by getting an exact match on their descriptions. */ bool key_default_cmp(const struct key *key, const struct key_match_data *match_data) { return strcmp(key->description, match_data->raw_data) == 0; } /* * Iteration function to consider each key found. */ static int keyring_search_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); unsigned long kflags = READ_ONCE(key->flags); short state = READ_ONCE(key->state); kenter("{%d}", key->serial); /* ignore keys not of this type */ if (key->type != ctx->index_key.type) { kleave(" = 0 [!type]"); return 0; } /* skip invalidated, revoked and expired keys */ if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { time64_t expiry = READ_ONCE(key->expiry); if (kflags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { ctx->result = ERR_PTR(-EKEYREVOKED); kleave(" = %d [invrev]", ctx->skipped_ret); goto skipped; } if (expiry && ctx->now >= expiry) { if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED)) ctx->result = ERR_PTR(-EKEYEXPIRED); kleave(" = %d [expire]", ctx->skipped_ret); goto skipped; } } /* keys that don't match */ if (!ctx->match_data.cmp(key, &ctx->match_data)) { kleave(" = 0 [!match]"); return 0; } /* key must have search permissions */ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) && key_task_permission(make_key_ref(key, ctx->possessed), ctx->cred, KEY_NEED_SEARCH) < 0) { ctx->result = ERR_PTR(-EACCES); kleave(" = %d [!perm]", ctx->skipped_ret); goto skipped; } if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { /* we set a different error code if we pass a negative key */ if (state < 0) { ctx->result = ERR_PTR(state); kleave(" = %d [neg]", ctx->skipped_ret); goto skipped; } } /* Found */ ctx->result = make_key_ref(key, ctx->possessed); kleave(" = 1 [found]"); return 1; skipped: return ctx->skipped_ret; } /* * Search inside a keyring for a key. We can search by walking to it * directly based on its index-key or we can iterate over the entire * tree looking for it, based on the match function. */ static int search_keyring(struct key *keyring, struct keyring_search_context *ctx) { if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) { const void *object; object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, &ctx->index_key); return object ? ctx->iterator(object, ctx) : 0; } return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx); } /* * Search a tree of keyrings that point to other keyrings up to the maximum * depth. */ static bool search_nested_keyrings(struct key *keyring, struct keyring_search_context *ctx) { struct { struct key *keyring; struct assoc_array_node *node; int slot; } stack[KEYRING_SEARCH_MAX_DEPTH]; struct assoc_array_shortcut *shortcut; struct assoc_array_node *node; struct assoc_array_ptr *ptr; struct key *key; int sp = 0, slot; kenter("{%d},{%s,%s}", keyring->serial, ctx->index_key.type->name, ctx->index_key.description); #define STATE_CHECKS (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_DO_STATE_CHECK) BUG_ON((ctx->flags & STATE_CHECKS) == 0 || (ctx->flags & STATE_CHECKS) == STATE_CHECKS); if (ctx->index_key.description) key_set_index_key(&ctx->index_key); /* Check to see if this top-level keyring is what we are looking for * and whether it is valid or not. */ if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE || keyring_compare_object(keyring, &ctx->index_key)) { ctx->skipped_ret = 2; switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) { case 1: goto found; case 2: return false; default: break; } } ctx->skipped_ret = 0; /* Start processing a new keyring */ descend_to_keyring: kdebug("descend to %d", keyring->serial); if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) goto not_this_keyring; /* Search through the keys in this keyring before its searching its * subtrees. */ if (search_keyring(keyring, ctx)) goto found; /* Then manually iterate through the keyrings nested in this one. * * Start from the root node of the index tree. Because of the way the * hash function has been set up, keyrings cluster on the leftmost * branch of the root node (root slot 0) or in the root node itself. * Non-keyrings avoid the leftmost branch of the root entirely (root * slots 1-15). */ if (!(ctx->flags & KEYRING_SEARCH_RECURSE)) goto not_this_keyring; ptr = READ_ONCE(keyring->keys.root); if (!ptr) goto not_this_keyring; if (assoc_array_ptr_is_shortcut(ptr)) { /* If the root is a shortcut, either the keyring only contains * keyring pointers (everything clusters behind root slot 0) or * doesn't contain any keyring pointers. */ shortcut = assoc_array_ptr_to_shortcut(ptr); if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0) goto not_this_keyring; ptr = READ_ONCE(shortcut->next_node); node = assoc_array_ptr_to_node(ptr); goto begin_node; } node = assoc_array_ptr_to_node(ptr); ptr = node->slots[0]; if (!assoc_array_ptr_is_meta(ptr)) goto begin_node; descend_to_node: /* Descend to a more distal node in this keyring's content tree and go * through that. */ kdebug("descend"); if (assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); ptr = READ_ONCE(shortcut->next_node); BUG_ON(!assoc_array_ptr_is_node(ptr)); } node = assoc_array_ptr_to_node(ptr); begin_node: kdebug("begin_node"); slot = 0; ascend_to_node: /* Go through the slots in a node */ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); if (assoc_array_ptr_is_meta(ptr) && node->back_pointer) goto descend_to_node; if (!keyring_ptr_is_keyring(ptr)) continue; key = keyring_ptr_to_key(ptr); if (sp >= KEYRING_SEARCH_MAX_DEPTH) { if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) { ctx->result = ERR_PTR(-ELOOP); return false; } goto not_this_keyring; } /* Search a nested keyring */ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) && key_task_permission(make_key_ref(key, ctx->possessed), ctx->cred, KEY_NEED_SEARCH) < 0) continue; /* stack the current position */ stack[sp].keyring = keyring; stack[sp].node = node; stack[sp].slot = slot; sp++; /* begin again with the new keyring */ keyring = key; goto descend_to_keyring; } /* We've dealt with all the slots in the current node, so now we need * to ascend to the parent and continue processing there. */ ptr = READ_ONCE(node->back_pointer); slot = node->parent_slot; if (ptr && assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); ptr = READ_ONCE(shortcut->back_pointer); slot = shortcut->parent_slot; } if (!ptr) goto not_this_keyring; node = assoc_array_ptr_to_node(ptr); slot++; /* If we've ascended to the root (zero backpointer), we must have just * finished processing the leftmost branch rather than the root slots - * so there can't be any more keyrings for us to find. */ if (node->back_pointer) { kdebug("ascend %d", slot); goto ascend_to_node; } /* The keyring we're looking at was disqualified or didn't contain a * matching key. */ not_this_keyring: kdebug("not_this_keyring %d", sp); if (sp <= 0) { kleave(" = false"); return false; } /* Resume the processing of a keyring higher up in the tree */ sp--; keyring = stack[sp].keyring; node = stack[sp].node; slot = stack[sp].slot + 1; kdebug("ascend to %d [%d]", keyring->serial, slot); goto ascend_to_node; /* We found a viable match */ found: key = key_ref_to_ptr(ctx->result); key_check(key); if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) { key->last_used_at = ctx->now; keyring->last_used_at = ctx->now; while (sp > 0) stack[--sp].keyring->last_used_at = ctx->now; } kleave(" = true"); return true; } /** * keyring_search_rcu - Search a keyring tree for a matching key under RCU * @keyring_ref: A pointer to the keyring with possession indicator. * @ctx: The keyring search context. * * Search the supplied keyring tree for a key that matches the criteria given. * The root keyring and any linked keyrings must grant Search permission to the * caller to be searchable and keys can only be found if they too grant Search * to the caller. The possession flag on the root keyring pointer controls use * of the possessor bits in permissions checking of the entire tree. In * addition, the LSM gets to forbid keyring searches and key matches. * * The search is performed as a breadth-then-depth search up to the prescribed * limit (KEYRING_SEARCH_MAX_DEPTH). The caller must hold the RCU read lock to * prevent keyrings from being destroyed or rearranged whilst they are being * searched. * * Keys are matched to the type provided and are then filtered by the match * function, which is given the description to use in any way it sees fit. The * match function may use any attributes of a key that it wishes to * determine the match. Normally the match function from the key type would be * used. * * RCU can be used to prevent the keyring key lists from disappearing without * the need to take lots of locks. * * Returns a pointer to the found key and increments the key usage count if * successful; -EAGAIN if no matching keys were found, or if expired or revoked * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the * specified keyring wasn't a keyring. * * In the case of a successful return, the possession attribute from * @keyring_ref is propagated to the returned key reference. */ key_ref_t keyring_search_rcu(key_ref_t keyring_ref, struct keyring_search_context *ctx) { struct key *keyring; long err; ctx->iterator = keyring_search_iterator; ctx->possessed = is_key_possessed(keyring_ref); ctx->result = ERR_PTR(-EAGAIN); keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (keyring->type != &key_type_keyring) return ERR_PTR(-ENOTDIR); if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) { err = key_task_permission(keyring_ref, ctx->cred, KEY_NEED_SEARCH); if (err < 0) return ERR_PTR(err); } ctx->now = ktime_get_real_seconds(); if (search_nested_keyrings(keyring, ctx)) __key_get(key_ref_to_ptr(ctx->result)); return ctx->result; } /** * keyring_search - Search the supplied keyring tree for a matching key * @keyring: The root of the keyring tree to be searched. * @type: The type of keyring we want to find. * @description: The name of the keyring we want to find. * @recurse: True to search the children of @keyring also * * As keyring_search_rcu() above, but using the current task's credentials and * type's default matching function and preferred search method. */ key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, const char *description, bool recurse) { struct keyring_search_context ctx = { .index_key.type = type, .index_key.description = description, .index_key.desc_len = strlen(description), .cred = current_cred(), .match_data.cmp = key_default_cmp, .match_data.raw_data = description, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = KEYRING_SEARCH_DO_STATE_CHECK, }; key_ref_t key; int ret; if (recurse) ctx.flags |= KEYRING_SEARCH_RECURSE; if (type->match_preparse) { ret = type->match_preparse(&ctx.match_data); if (ret < 0) return ERR_PTR(ret); } rcu_read_lock(); key = keyring_search_rcu(keyring, &ctx); rcu_read_unlock(); if (type->match_free) type->match_free(&ctx.match_data); return key; } EXPORT_SYMBOL(keyring_search); static struct key_restriction *keyring_restriction_alloc( key_restrict_link_func_t check) { struct key_restriction *keyres = kzalloc(sizeof(struct key_restriction), GFP_KERNEL); if (!keyres) return ERR_PTR(-ENOMEM); keyres->check = check; return keyres; } /* * Semaphore to serialise restriction setup to prevent reference count * cycles through restriction key pointers. */ static DECLARE_RWSEM(keyring_serialise_restrict_sem); /* * Check for restriction cycles that would prevent keyring garbage collection. * keyring_serialise_restrict_sem must be held. */ static bool keyring_detect_restriction_cycle(const struct key *dest_keyring, struct key_restriction *keyres) { while (keyres && keyres->key && keyres->key->type == &key_type_keyring) { if (keyres->key == dest_keyring) return true; keyres = keyres->key->restrict_link; } return false; } /** * keyring_restrict - Look up and apply a restriction to a keyring * @keyring_ref: The keyring to be restricted * @type: The key type that will provide the restriction checker. * @restriction: The restriction options to apply to the keyring * * Look up a keyring and apply a restriction to it. The restriction is managed * by the specific key type, but can be configured by the options specified in * the restriction string. */ int keyring_restrict(key_ref_t keyring_ref, const char *type, const char *restriction) { struct key *keyring; struct key_type *restrict_type = NULL; struct key_restriction *restrict_link; int ret = 0; keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (keyring->type != &key_type_keyring) return -ENOTDIR; if (!type) { restrict_link = keyring_restriction_alloc(restrict_link_reject); } else { restrict_type = key_type_lookup(type); if (IS_ERR(restrict_type)) return PTR_ERR(restrict_type); if (!restrict_type->lookup_restriction) { ret = -ENOENT; goto error; } restrict_link = restrict_type->lookup_restriction(restriction); } if (IS_ERR(restrict_link)) { ret = PTR_ERR(restrict_link); goto error; } down_write(&keyring->sem); down_write(&keyring_serialise_restrict_sem); if (keyring->restrict_link) { ret = -EEXIST; } else if (keyring_detect_restriction_cycle(keyring, restrict_link)) { ret = -EDEADLK; } else { keyring->restrict_link = restrict_link; notify_key(keyring, NOTIFY_KEY_SETATTR, 0); } up_write(&keyring_serialise_restrict_sem); up_write(&keyring->sem); if (ret < 0) { key_put(restrict_link->key); kfree(restrict_link); } error: if (restrict_type) key_type_put(restrict_type); return ret; } EXPORT_SYMBOL(keyring_restrict); /* * Search the given keyring for a key that might be updated. * * The caller must guarantee that the keyring is a keyring and that the * permission is granted to modify the keyring as no check is made here. The * caller must also hold a lock on the keyring semaphore. * * Returns a pointer to the found key with usage count incremented if * successful and returns NULL if not found. Revoked and invalidated keys are * skipped over. * * If successful, the possession indicator is propagated from the keyring ref * to the returned key reference. */ key_ref_t find_key_to_update(key_ref_t keyring_ref, const struct keyring_index_key *index_key) { struct key *keyring, *key; const void *object; keyring = key_ref_to_ptr(keyring_ref); kenter("{%d},{%s,%s}", keyring->serial, index_key->type->name, index_key->description); object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, index_key); if (object) goto found; kleave(" = NULL"); return NULL; found: key = keyring_ptr_to_key(object); if (key->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { kleave(" = NULL [x]"); return NULL; } __key_get(key); kleave(" = {%d}", key->serial); return make_key_ref(key, is_key_possessed(keyring_ref)); } /* * Find a keyring with the specified name. * * Only keyrings that have nonzero refcount, are not revoked, and are owned by a * user in the current user namespace are considered. If @uid_keyring is %true, * the keyring additionally must have been allocated as a user or user session * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct user_namespace *ns = current_user_ns(); struct key *keyring; if (!name) return ERR_PTR(-EINVAL); read_lock(&keyring_name_lock); /* Search this hash bucket for a keyring with a matching name that * grants Search permission and that hasn't been revoked */ list_for_each_entry(keyring, &ns->keyring_name_list, name_link) { if (!kuid_has_mapping(ns, keyring->user->uid)) continue; if (test_bit(KEY_FLAG_REVOKED, &keyring->flags)) continue; if (strcmp(keyring->description, name) != 0) continue; if (uid_keyring) { if (!test_bit(KEY_FLAG_UID_KEYRING, &keyring->flags)) continue; } else { if (key_permission(make_key_ref(keyring, 0), KEY_NEED_SEARCH) < 0) continue; } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' * (ie. it has a zero usage count) */ if (!refcount_inc_not_zero(&keyring->usage)) continue; keyring->last_used_at = ktime_get_real_seconds(); goto out; } keyring = ERR_PTR(-ENOKEY); out: read_unlock(&keyring_name_lock); return keyring; } static int keyring_detect_cycle_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); kenter("{%d}", key->serial); /* We might get a keyring with matching index-key that is nonetheless a * different keyring. */ if (key != ctx->match_data.raw_data) return 0; ctx->result = ERR_PTR(-EDEADLK); return 1; } /* * See if a cycle will be created by inserting acyclic tree B in acyclic * tree A at the topmost level (ie: as a direct child of A). * * Since we are adding B to A at the top level, checking for cycles should just * be a matter of seeing if node A is somewhere in tree B. */ static int keyring_detect_cycle(struct key *A, struct key *B) { struct keyring_search_context ctx = { .index_key = A->index_key, .match_data.raw_data = A, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .iterator = keyring_detect_cycle_iterator, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_NO_UPDATE_TIME | KEYRING_SEARCH_NO_CHECK_PERM | KEYRING_SEARCH_DETECT_TOO_DEEP | KEYRING_SEARCH_RECURSE), }; rcu_read_lock(); search_nested_keyrings(B, &ctx); rcu_read_unlock(); return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result); } /* * Lock keyring for link. */ int __key_link_lock(struct key *keyring, const struct keyring_index_key *index_key) __acquires(&keyring->sem) __acquires(&keyring_serialise_link_lock) { if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); /* Serialise link/link calls to prevent parallel calls causing a cycle * when linking two keyring in opposite orders. */ if (index_key->type == &key_type_keyring) mutex_lock(&keyring_serialise_link_lock); return 0; } /* * Lock keyrings for move (link/unlink combination). */ int __key_move_lock(struct key *l_keyring, struct key *u_keyring, const struct keyring_index_key *index_key) __acquires(&l_keyring->sem) __acquires(&u_keyring->sem) __acquires(&keyring_serialise_link_lock) { if (l_keyring->type != &key_type_keyring || u_keyring->type != &key_type_keyring) return -ENOTDIR; /* We have to be very careful here to take the keyring locks in the * right order, lest we open ourselves to deadlocking against another * move operation. */ if (l_keyring < u_keyring) { down_write(&l_keyring->sem); down_write_nested(&u_keyring->sem, 1); } else { down_write(&u_keyring->sem); down_write_nested(&l_keyring->sem, 1); } /* Serialise link/link calls to prevent parallel calls causing a cycle * when linking two keyring in opposite orders. */ if (index_key->type == &key_type_keyring) mutex_lock(&keyring_serialise_link_lock); return 0; } /* * Preallocate memory so that a key can be linked into to a keyring. */ int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit **_edit) { struct assoc_array_edit *edit; int ret; kenter("%d,%s,%s,", keyring->serial, index_key->type->name, index_key->description); BUG_ON(index_key->desc_len == 0); BUG_ON(*_edit != NULL); *_edit = NULL; ret = -EKEYREVOKED; if (test_bit(KEY_FLAG_REVOKED, &keyring->flags)) goto error; /* Create an edit script that will insert/replace the key in the * keyring tree. */ edit = assoc_array_insert(&keyring->keys, &keyring_assoc_array_ops, index_key, NULL); if (IS_ERR(edit)) { ret = PTR_ERR(edit); goto error; } /* If we're not replacing a link in-place then we're going to need some * extra quota. */ if (!edit->dead_leaf) { ret = key_payload_reserve(keyring, keyring->datalen + KEYQUOTA_LINK_BYTES); if (ret < 0) goto error_cancel; } *_edit = edit; kleave(" = 0"); return 0; error_cancel: assoc_array_cancel_edit(edit); error: kleave(" = %d", ret); return ret; } /* * Check already instantiated keys aren't going to be a problem. * * The caller must have called __key_link_begin(). Don't need to call this for * keys that were created since __key_link_begin() was called. */ int __key_link_check_live_key(struct key *keyring, struct key *key) { if (key->type == &key_type_keyring) /* check that we aren't going to create a cycle by linking one * keyring to another */ return keyring_detect_cycle(keyring, key); return 0; } /* * Link a key into to a keyring. * * Must be called with __key_link_begin() having being called. Discards any * already extant link to matching key if there is one, so that each keyring * holds at most one link to any given key of a particular type+description * combination. */ void __key_link(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { __key_get(key); assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key)); assoc_array_apply_edit(*_edit); *_edit = NULL; notify_key(keyring, NOTIFY_KEY_LINKED, key_serial(key)); } /* * Finish linking a key into to a keyring. * * Must be called with __key_link_begin() having being called. */ void __key_link_end(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit *edit) __releases(&keyring->sem) __releases(&keyring_serialise_link_lock) { BUG_ON(index_key->type == NULL); kenter("%d,%s,", keyring->serial, index_key->type->name); if (edit) { if (!edit->dead_leaf) { key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); } assoc_array_cancel_edit(edit); } up_write(&keyring->sem); if (index_key->type == &key_type_keyring) mutex_unlock(&keyring_serialise_link_lock); } /* * Check addition of keys to restricted keyrings. */ static int __key_link_check_restriction(struct key *keyring, struct key *key) { if (!keyring->restrict_link || !keyring->restrict_link->check) return 0; return keyring->restrict_link->check(keyring, key->type, &key->payload, keyring->restrict_link->key); } /** * key_link - Link a key to a keyring * @keyring: The keyring to make the link in. * @key: The key to link to. * * Make a link in a keyring to a key, such that the keyring holds a reference * on that key and the key can potentially be found by searching that keyring. * * This function will write-lock the keyring's semaphore and will consume some * of the user's key data quota to hold the link. * * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, * -EKEYREVOKED if the keyring has been revoked, -ENFILE if the keyring is * full, -EDQUOT if there is insufficient key data quota remaining to add * another link or -ENOMEM if there's insufficient memory. * * It is assumed that the caller has checked that it is permitted for a link to * be made (the keyring should have Write permission and the key Link * permission). */ int key_link(struct key *keyring, struct key *key) { struct assoc_array_edit *edit = NULL; int ret; kenter("{%d,%d}", keyring->serial, refcount_read(&keyring->usage)); key_check(keyring); key_check(key); ret = __key_link_lock(keyring, &key->index_key); if (ret < 0) goto error; ret = __key_link_begin(keyring, &key->index_key, &edit); if (ret < 0) goto error_end; kdebug("begun {%d,%d}", keyring->serial, refcount_read(&keyring->usage)); ret = __key_link_check_restriction(keyring, key); if (ret == 0) ret = __key_link_check_live_key(keyring, key); if (ret == 0) __key_link(keyring, key, &edit); error_end: __key_link_end(keyring, &key->index_key, edit); error: kleave(" = %d {%d,%d}", ret, keyring->serial, refcount_read(&keyring->usage)); return ret; } EXPORT_SYMBOL(key_link); /* * Lock a keyring for unlink. */ static int __key_unlink_lock(struct key *keyring) __acquires(&keyring->sem) { if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); return 0; } /* * Begin the process of unlinking a key from a keyring. */ static int __key_unlink_begin(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { struct assoc_array_edit *edit; BUG_ON(*_edit != NULL); edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops, &key->index_key); if (IS_ERR(edit)) return PTR_ERR(edit); if (!edit) return -ENOENT; *_edit = edit; return 0; } /* * Apply an unlink change. */ static void __key_unlink(struct key *keyring, struct key *key, struct assoc_array_edit **_edit) { assoc_array_apply_edit(*_edit); notify_key(keyring, NOTIFY_KEY_UNLINKED, key_serial(key)); *_edit = NULL; key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); } /* * Finish unlinking a key from to a keyring. */ static void __key_unlink_end(struct key *keyring, struct key *key, struct assoc_array_edit *edit) __releases(&keyring->sem) { if (edit) assoc_array_cancel_edit(edit); up_write(&keyring->sem); } /** * key_unlink - Unlink the first link to a key from a keyring. * @keyring: The keyring to remove the link from. * @key: The key the link is to. * * Remove a link from a keyring to a key. * * This function will write-lock the keyring's semaphore. * * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, -ENOENT if * the key isn't linked to by the keyring or -ENOMEM if there's insufficient * memory. * * It is assumed that the caller has checked that it is permitted for a link to * be removed (the keyring should have Write permission; no permissions are * required on the key). */ int key_unlink(struct key *keyring, struct key *key) { struct assoc_array_edit *edit = NULL; int ret; key_check(keyring); key_check(key); ret = __key_unlink_lock(keyring); if (ret < 0) return ret; ret = __key_unlink_begin(keyring, key, &edit); if (ret == 0) __key_unlink(keyring, key, &edit); __key_unlink_end(keyring, key, edit); return ret; } EXPORT_SYMBOL(key_unlink); /** * key_move - Move a key from one keyring to another * @key: The key to move * @from_keyring: The keyring to remove the link from. * @to_keyring: The keyring to make the link in. * @flags: Qualifying flags, such as KEYCTL_MOVE_EXCL. * * Make a link in @to_keyring to a key, such that the keyring holds a reference * on that key and the key can potentially be found by searching that keyring * whilst simultaneously removing a link to the key from @from_keyring. * * This function will write-lock both keyring's semaphores and will consume * some of the user's key data quota to hold the link on @to_keyring. * * Returns 0 if successful, -ENOTDIR if either keyring isn't a keyring, * -EKEYREVOKED if either keyring has been revoked, -ENFILE if the second * keyring is full, -EDQUOT if there is insufficient key data quota remaining * to add another link or -ENOMEM if there's insufficient memory. If * KEYCTL_MOVE_EXCL is set, then -EEXIST will be returned if there's already a * matching key in @to_keyring. * * It is assumed that the caller has checked that it is permitted for a link to * be made (the keyring should have Write permission and the key Link * permission). */ int key_move(struct key *key, struct key *from_keyring, struct key *to_keyring, unsigned int flags) { struct assoc_array_edit *from_edit = NULL, *to_edit = NULL; int ret; kenter("%d,%d,%d", key->serial, from_keyring->serial, to_keyring->serial); if (from_keyring == to_keyring) return 0; key_check(key); key_check(from_keyring); key_check(to_keyring); ret = __key_move_lock(from_keyring, to_keyring, &key->index_key); if (ret < 0) goto out; ret = __key_unlink_begin(from_keyring, key, &from_edit); if (ret < 0) goto error; ret = __key_link_begin(to_keyring, &key->index_key, &to_edit); if (ret < 0) goto error; ret = -EEXIST; if (to_edit->dead_leaf && (flags & KEYCTL_MOVE_EXCL)) goto error; ret = __key_link_check_restriction(to_keyring, key); if (ret < 0) goto error; ret = __key_link_check_live_key(to_keyring, key); if (ret < 0) goto error; __key_unlink(from_keyring, key, &from_edit); __key_link(to_keyring, key, &to_edit); error: __key_link_end(to_keyring, &key->index_key, to_edit); __key_unlink_end(from_keyring, key, from_edit); out: kleave(" = %d", ret); return ret; } EXPORT_SYMBOL(key_move); /** * keyring_clear - Clear a keyring * @keyring: The keyring to clear. * * Clear the contents of the specified keyring. * * Returns 0 if successful or -ENOTDIR if the keyring isn't a keyring. */ int keyring_clear(struct key *keyring) { struct assoc_array_edit *edit; int ret; if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops); if (IS_ERR(edit)) { ret = PTR_ERR(edit); } else { if (edit) assoc_array_apply_edit(edit); notify_key(keyring, NOTIFY_KEY_CLEARED, 0); key_payload_reserve(keyring, 0); ret = 0; } up_write(&keyring->sem); return ret; } EXPORT_SYMBOL(keyring_clear); /* * Dispose of the links from a revoked keyring. * * This is called with the key sem write-locked. */ static void keyring_revoke(struct key *keyring) { struct assoc_array_edit *edit; edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops); if (!IS_ERR(edit)) { if (edit) assoc_array_apply_edit(edit); key_payload_reserve(keyring, 0); } } static bool keyring_gc_select_iterator(void *object, void *iterator_data) { struct key *key = keyring_ptr_to_key(object); time64_t *limit = iterator_data; if (key_is_dead(key, *limit)) return false; key_get(key); return true; } static int keyring_gc_check_iterator(const void *object, void *iterator_data) { const struct key *key = keyring_ptr_to_key(object); time64_t *limit = iterator_data; key_check(key); return key_is_dead(key, *limit); } /* * Garbage collect pointers from a keyring. * * Not called with any locks held. The keyring's key struct will not be * deallocated under us as only our caller may deallocate it. */ void keyring_gc(struct key *keyring, time64_t limit) { int result; kenter("%x{%s}", keyring->serial, keyring->description ?: ""); if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) goto dont_gc; /* scan the keyring looking for dead keys */ rcu_read_lock(); result = assoc_array_iterate(&keyring->keys, keyring_gc_check_iterator, &limit); rcu_read_unlock(); if (result == true) goto do_gc; dont_gc: kleave(" [no gc]"); return; do_gc: down_write(&keyring->sem); assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops, keyring_gc_select_iterator, &limit); up_write(&keyring->sem); kleave(" [gc]"); } /* * Garbage collect restriction pointers from a keyring. * * Keyring restrictions are associated with a key type, and must be cleaned * up if the key type is unregistered. The restriction is altered to always * reject additional keys so a keyring cannot be opened up by unregistering * a key type. * * Not called with any keyring locks held. The keyring's key struct will not * be deallocated under us as only our caller may deallocate it. * * The caller is required to hold key_types_sem and dead_type->sem. This is * fulfilled by key_gc_keytype() holding the locks on behalf of * key_garbage_collector(), which it invokes on a workqueue. */ void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type) { struct key_restriction *keyres; kenter("%x{%s}", keyring->serial, keyring->description ?: ""); /* * keyring->restrict_link is only assigned at key allocation time * or with the key type locked, so the only values that could be * concurrently assigned to keyring->restrict_link are for key * types other than dead_type. Given this, it's ok to check * the key type before acquiring keyring->sem. */ if (!dead_type || !keyring->restrict_link || keyring->restrict_link->keytype != dead_type) { kleave(" [no restriction gc]"); return; } /* Lock the keyring to ensure that a link is not in progress */ down_write(&keyring->sem); keyres = keyring->restrict_link; keyres->check = restrict_link_reject; key_put(keyres->key); keyres->key = NULL; keyres->keytype = NULL; up_write(&keyring->sem); kleave(" [restriction gc]"); } |
| 1 1 261 329 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_H #define _LINUX_PID_H #include <linux/pid_types.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/sched.h> #include <linux/wait.h> /* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to individual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. */ /* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */ #define RESERVED_PIDS 300 struct upid { int nr; struct pid_namespace *ns; }; struct pid { refcount_t count; unsigned int level; spinlock_t lock; struct dentry *stashed; u64 ino; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[]; }; extern struct pid init_struct_pid; struct file; struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { if (pid) refcount_inc(&pid->count); return pid; } extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); static inline bool pid_has_task(struct pid *pid, enum pid_type type) { return !hlist_empty(&pid->tasks[type]); } extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); /* * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); extern int pid_max; extern int pid_max_min, pid_max_max; /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified * find_vpid() finds the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); /* * ns_of_pid() returns the pid namespace in which the specified pid was * allocated. * * NOTE: * ns_of_pid() is expected to be called for a process (task) that has * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid * is expected to be non-NULL. If @pid is NULL, caller should handle * the resulting NULL pid-ns. */ static inline struct pid_namespace *ns_of_pid(struct pid *pid) { struct pid_namespace *ns = NULL; if (pid) ns = pid->numbers[pid->level].ns; return ns; } /* * is_child_reaper returns true if the pid is the init process * of the current namespace. As this one could be checked before * pid_ns->child_reaper is assigned in copy_process, we check * with the pid number. */ static inline bool is_child_reaper(struct pid *pid) { return pid->numbers[pid->level].nr == 1; } /* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; * pid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * pid_nr_ns() : id seen from the ns specified. * * see also task_xid_nr() etc in include/linux/sched.h */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) nr = pid->numbers[0].nr; return nr; } pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to * the same pid in the middle of de_thread(). */ #define while_each_pid_task(pid, type, task) \ if (type == PIDTYPE_PID) \ break; \ } \ } while (0) #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ } \ task = tg___; \ } while_each_pid_task(pid, type, task) static inline struct pid *task_pid(struct task_struct *task) { return task->thread_pid; } /* * the helpers to get the task's different pids as they are seen * from various namespaces * * task_xid_nr() : global id, i.e. the id seen from the init namespace; * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * task_xid_nr_ns() : id seen from the ns specified; * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); } static inline pid_t task_pid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } static inline pid_t task_tgid_nr(struct task_struct *tsk) { return tsk->tgid; } /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. * * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. * * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(const struct task_struct *p) { return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); } static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); } static inline pid_t task_session_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; rcu_read_lock(); if (pid_alive(tsk)) pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); rcu_read_unlock(); return pid; } static inline pid_t task_ppid_nr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, &init_pid_ns); } /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. * * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { return task_tgid_nr(tsk) == 1; } #endif /* _LINUX_PID_H */ |
| 2 2 1 1 1 1 2 1 1 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/smp.h> #include "blk.h" #include "blk-mq.h" static void blk_mq_sysfs_release(struct kobject *kobj) { struct blk_mq_ctxs *ctxs = container_of(kobj, struct blk_mq_ctxs, kobj); free_percpu(ctxs->queue_ctx); kfree(ctxs); } static void blk_mq_ctx_sysfs_release(struct kobject *kobj) { struct blk_mq_ctx *ctx = container_of(kobj, struct blk_mq_ctx, kobj); /* ctx->ctxs won't be released until all ctx are freed */ kobject_put(&ctx->ctxs->kobj); } static void blk_mq_hw_sysfs_release(struct kobject *kobj) { struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); blk_free_flush_queue(hctx->fq); sbitmap_free(&hctx->ctx_map); free_cpumask_var(hctx->cpumask); kfree(hctx->ctxs); kfree(hctx); } struct blk_mq_hw_ctx_sysfs_entry { struct attribute attr; ssize_t (*show)(struct blk_mq_hw_ctx *, char *); }; static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, struct attribute *attr, char *page) { struct blk_mq_hw_ctx_sysfs_entry *entry; struct blk_mq_hw_ctx *hctx; struct request_queue *q; ssize_t res; entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr); hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); q = hctx->queue; if (!entry->show) return -EIO; mutex_lock(&q->sysfs_lock); res = entry->show(hctx, page); mutex_unlock(&q->sysfs_lock); return res; } static ssize_t blk_mq_hw_sysfs_nr_tags_show(struct blk_mq_hw_ctx *hctx, char *page) { return sprintf(page, "%u\n", hctx->tags->nr_tags); } static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx, char *page) { return sprintf(page, "%u\n", hctx->tags->nr_reserved_tags); } static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) { const size_t size = PAGE_SIZE - 1; unsigned int i, first = 1; int ret = 0, pos = 0; for_each_cpu(i, hctx->cpumask) { if (first) ret = snprintf(pos + page, size - pos, "%u", i); else ret = snprintf(pos + page, size - pos, ", %u", i); if (ret >= size - pos) break; first = 0; pos += ret; } ret = snprintf(pos + page, size + 1 - pos, "\n"); return pos + ret; } static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = { .attr = {.name = "nr_tags", .mode = 0444 }, .show = blk_mq_hw_sysfs_nr_tags_show, }; static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_reserved_tags = { .attr = {.name = "nr_reserved_tags", .mode = 0444 }, .show = blk_mq_hw_sysfs_nr_reserved_tags_show, }; static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = { .attr = {.name = "cpu_list", .mode = 0444 }, .show = blk_mq_hw_sysfs_cpus_show, }; static struct attribute *default_hw_ctx_attrs[] = { &blk_mq_hw_sysfs_nr_tags.attr, &blk_mq_hw_sysfs_nr_reserved_tags.attr, &blk_mq_hw_sysfs_cpus.attr, NULL, }; ATTRIBUTE_GROUPS(default_hw_ctx); static const struct sysfs_ops blk_mq_hw_sysfs_ops = { .show = blk_mq_hw_sysfs_show, }; static const struct kobj_type blk_mq_ktype = { .release = blk_mq_sysfs_release, }; static const struct kobj_type blk_mq_ctx_ktype = { .release = blk_mq_ctx_sysfs_release, }; static const struct kobj_type blk_mq_hw_ktype = { .sysfs_ops = &blk_mq_hw_sysfs_ops, .default_groups = default_hw_ctx_groups, .release = blk_mq_hw_sysfs_release, }; static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx) { struct blk_mq_ctx *ctx; int i; if (!hctx->nr_ctx) return; hctx_for_each_ctx(hctx, ctx, i) kobject_del(&ctx->kobj); kobject_del(&hctx->kobj); } static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; int i, j, ret; if (!hctx->nr_ctx) return 0; ret = kobject_add(&hctx->kobj, q->mq_kobj, "%u", hctx->queue_num); if (ret) return ret; hctx_for_each_ctx(hctx, ctx, i) { ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu); if (ret) goto out; } return 0; out: hctx_for_each_ctx(hctx, ctx, j) { if (j < i) kobject_del(&ctx->kobj); } kobject_del(&hctx->kobj); return ret; } void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx) { kobject_init(&hctx->kobj, &blk_mq_hw_ktype); } void blk_mq_sysfs_deinit(struct request_queue *q) { struct blk_mq_ctx *ctx; int cpu; for_each_possible_cpu(cpu) { ctx = per_cpu_ptr(q->queue_ctx, cpu); kobject_put(&ctx->kobj); } kobject_put(q->mq_kobj); } void blk_mq_sysfs_init(struct request_queue *q) { struct blk_mq_ctx *ctx; int cpu; kobject_init(q->mq_kobj, &blk_mq_ktype); for_each_possible_cpu(cpu) { ctx = per_cpu_ptr(q->queue_ctx, cpu); kobject_get(q->mq_kobj); kobject_init(&ctx->kobj, &blk_mq_ctx_ktype); } } int blk_mq_sysfs_register(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blk_mq_hw_ctx *hctx; unsigned long i, j; int ret; lockdep_assert_held(&q->sysfs_dir_lock); ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq"); if (ret < 0) goto out; kobject_uevent(q->mq_kobj, KOBJ_ADD); queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); if (ret) goto unreg; } q->mq_sysfs_init_done = true; out: return ret; unreg: queue_for_each_hw_ctx(q, hctx, j) { if (j < i) blk_mq_unregister_hctx(hctx); } kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); return ret; } void blk_mq_sysfs_unregister(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blk_mq_hw_ctx *hctx; unsigned long i; lockdep_assert_held(&q->sysfs_dir_lock); queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); q->mq_sysfs_init_done = false; } void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; mutex_lock(&q->sysfs_dir_lock); if (!q->mq_sysfs_init_done) goto unlock; queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); unlock: mutex_unlock(&q->sysfs_dir_lock); } int blk_mq_sysfs_register_hctxs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; int ret = 0; mutex_lock(&q->sysfs_dir_lock); if (!q->mq_sysfs_init_done) goto unlock; queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); if (ret) break; } unlock: mutex_unlock(&q->sysfs_dir_lock); return ret; } |
| 4 3 4 4 4 3 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 | // 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" #define DEVLINK_PORT_FN_CAPS_VALID_MASK \ (_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1) static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, DEVLINK_PORT_FN_STATE_ACTIVE), [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), [DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] = { .type = NLA_U32 }, }; #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ WARN_ON_ONCE((devlink_port)->registered) struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, unsigned int port_index) { return xa_load(&devlink->ports, port_index); } struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_PORT_INDEX]) { u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (!devlink_port) return ERR_PTR(-ENODEV); return devlink_port; } return ERR_PTR(-EINVAL); } struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_port_get_from_attrs(devlink, info->attrs); } static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps, u32 cap, bool is_enable) { caps->selector |= cap; if (is_enable) caps->value |= cap; } static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_roce_get) return 0; err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable); return 0; } static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_migratable_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_migratable_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable); return 0; } static int devlink_port_fn_ipsec_crypto_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_ipsec_crypto_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_ipsec_crypto_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, is_enable); return 0; } static int devlink_port_fn_ipsec_packet_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; if (!devlink_port->ops->port_fn_ipsec_packet_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; err = devlink_port->ops->port_fn_ipsec_packet_get(devlink_port, &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_IPSEC_PACKET, is_enable); return 0; } static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { struct nla_bitfield32 caps = {}; int err; err = devlink_port_fn_roce_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_ipsec_crypto_fill(devlink_port, &caps, extack); if (err) return err; err = devlink_port_fn_ipsec_packet_fill(devlink_port, &caps, extack); if (err) return err; if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, caps.selector); if (err) return err; *msg_updated = true; return 0; } static int devlink_port_fn_max_io_eqs_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { u32 max_io_eqs; int err; if (!port->ops->port_fn_max_io_eqs_get) return 0; err = port->ops->port_fn_max_io_eqs_get(port, &max_io_eqs, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } err = nla_put_u32(msg, DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, max_io_eqs); if (err) return err; *msg_updated = true; return 0; } int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) { if (devlink_nl_put_handle(msg, devlink_port->devlink)) return -EMSGSIZE; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) return -EMSGSIZE; return 0; } size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ } static int devlink_nl_port_attrs_put(struct sk_buff *msg, struct devlink_port *devlink_port) { struct devlink_port_attrs *attrs = &devlink_port->attrs; if (!devlink_port->attrs_set) return 0; if (attrs->lanes) { if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes)) return -EMSGSIZE; } if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable)) return -EMSGSIZE; if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) return -EMSGSIZE; switch (devlink_port->attrs.flavour) { case DEVLINK_PORT_FLAVOUR_PCI_PF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_pf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_VF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_vf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) return -EMSGSIZE; if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_SF: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, attrs->pci_sf.controller) || nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_sf.pf) || nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, attrs->pci_sf.sf)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->phys.port_number)) return -EMSGSIZE; if (!attrs->split) return 0; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->phys.port_number)) return -EMSGSIZE; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, attrs->phys.split_subport_number)) return -EMSGSIZE; break; default: break; } return 0; } static int devlink_port_fn_hw_addr_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { u8 hw_addr[MAX_ADDR_LEN]; int hw_addr_len; int err; if (!port->ops->port_fn_hw_addr_get) return 0; err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); if (err) return err; *msg_updated = true; return 0; } static bool devlink_port_fn_state_valid(enum devlink_port_fn_state state) { return state == DEVLINK_PORT_FN_STATE_INACTIVE || state == DEVLINK_PORT_FN_STATE_ACTIVE; } static bool devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) { return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; } static int devlink_port_fn_state_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) { enum devlink_port_fn_opstate opstate; enum devlink_port_fn_state state; int err; if (!port->ops->port_fn_state_get) return 0; err = port->ops->port_fn_state_get(port, &state, &opstate, extack); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } if (!devlink_port_fn_state_valid(state)) { WARN_ON_ONCE(1); NL_SET_ERR_MSG(extack, "Invalid state read from driver"); return -EINVAL; } if (!devlink_port_fn_opstate_valid(opstate)) { WARN_ON_ONCE(1); NL_SET_ERR_MSG(extack, "Invalid operational state read from driver"); return -EINVAL; } if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) return -EMSGSIZE; *msg_updated = true; return 0; } static int devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_migratable_set(devlink_port, enable, extack); } static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_roce_set(devlink_port, enable, extack); } static int devlink_port_fn_ipsec_crypto_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_ipsec_crypto_set(devlink_port, enable, extack); } static int devlink_port_fn_ipsec_packet_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { return devlink_port->ops->port_fn_ipsec_packet_set(devlink_port, enable, extack); } static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nla_bitfield32 caps; u32 caps_value; int err; caps = nla_get_bitfield32(attr); caps_value = caps.value & caps.selector; if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) { err = devlink_port_fn_roce_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_ROCE, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { err = devlink_port_fn_mig_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_MIGRATABLE, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { err = devlink_port_fn_ipsec_crypto_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO, extack); if (err) return err; } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { err = devlink_port_fn_ipsec_packet_set(devlink_port, caps_value & DEVLINK_PORT_FN_CAP_IPSEC_PACKET, extack); if (err) return err; } return 0; } static int devlink_port_fn_max_io_eqs_set(struct devlink_port *devlink_port, const struct nlattr *attr, struct netlink_ext_ack *extack) { u32 max_io_eqs; max_io_eqs = nla_get_u32(attr); return devlink_port->ops->port_fn_max_io_eqs_set(devlink_port, max_io_eqs, extack); } static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { struct nlattr *function_attr; bool msg_updated = false; int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_port_fn_max_io_eqs_fill(port, msg, extack, &msg_updated); if (err) goto out; err = devlink_rel_devlink_handle_put(msg, port->devlink, port->rel_index, DEVLINK_PORT_FN_ATTR_DEVLINK, &msg_updated); out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); return err; } static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink_port *devlink_port, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { struct devlink *devlink = devlink_port->devlink; void *hdr; 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_PORT_INDEX, devlink_port->index)) goto nla_put_failure; spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { if (devlink_port->type_eth.netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, devlink_port->type_eth.ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, devlink_port->type_eth.ifname))) goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { struct ib_device *ibdev = devlink_port->type_ib.ibdev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, ibdev->name)) goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) goto nla_put_failure; if (devlink_port->linecard && nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, devlink_linecard_index(devlink_port->linecard))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { struct devlink *devlink = devlink_port->devlink; struct devlink_obj_desc desc; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_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_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } devlink_nl_obj_desc_init(&desc, devlink); devlink_nl_obj_desc_port_set(&desc, devlink_port); devlink_nl_notify_send_desc(devlink, msg, &desc); } static void devlink_ports_notify(struct devlink *devlink, enum devlink_command cmd) { struct devlink_port *devlink_port; unsigned long port_index; xa_for_each(&devlink->ports, port_index, devlink_port) devlink_port_notify(devlink_port, cmd); } void devlink_ports_notify_register(struct devlink *devlink) { devlink_ports_notify(devlink, DEVLINK_CMD_PORT_NEW); } void devlink_ports_notify_unregister(struct devlink *devlink) { devlink_ports_notify(devlink, DEVLINK_CMD_PORT_DEL); } int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_port_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_port *devlink_port; unsigned long port_index; int err = 0; xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) { err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); if (err) { state->idx = port_index; break; } } return err; } int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_port_get_dump_one); } static int devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type port_type) { int err; if (!devlink_port->ops->port_type_set) return -EOPNOTSUPP; if (port_type == devlink_port->type) return 0; err = devlink_port->ops->port_type_set(devlink_port, port_type); if (err) return err; devlink_port->desired_type = port_type; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } static int devlink_port_function_hw_addr_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { const u8 *hw_addr; int hw_addr_len; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); if (hw_addr_len > MAX_ADDR_LEN) { NL_SET_ERR_MSG(extack, "Port function hardware address too long"); return -EINVAL; } if (port->type == DEVLINK_PORT_TYPE_ETH) { if (hw_addr_len != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Address must be 6 bytes for Ethernet device"); return -EINVAL; } if (!is_unicast_ether_addr(hw_addr)) { NL_SET_ERR_MSG(extack, "Non-unicast hardware address unsupported"); return -EINVAL; } } return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len, extack); } static int devlink_port_fn_state_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { enum devlink_port_fn_state state; state = nla_get_u8(attr); return port->ops->port_fn_state_set(port, state, extack); } static int devlink_port_function_validate(struct devlink_port *devlink_port, struct nlattr **tb, struct netlink_ext_ack *extack) { const struct devlink_port_ops *ops = devlink_port->ops; struct nlattr *attr; if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] && !ops->port_fn_hw_addr_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR], "Port doesn't support function attributes"); return -EOPNOTSUPP; } if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE], "Function does not support state setting"); return -EOPNOTSUPP; } attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; if (attr) { struct nla_bitfield32 caps; caps = nla_get_bitfield32(attr); if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE && !ops->port_fn_roce_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support RoCE function attribute"); return -EOPNOTSUPP; } if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { if (!ops->port_fn_migratable_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support migratable function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "migratable function attribute supported for VFs only"); return -EOPNOTSUPP; } } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO) { if (!ops->port_fn_ipsec_crypto_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support ipsec_crypto function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "ipsec_crypto function attribute supported for VFs only"); return -EOPNOTSUPP; } } if (caps.selector & DEVLINK_PORT_FN_CAP_IPSEC_PACKET) { if (!ops->port_fn_ipsec_packet_set) { NL_SET_ERR_MSG_ATTR(extack, attr, "Port doesn't support ipsec_packet function attribute"); return -EOPNOTSUPP; } if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { NL_SET_ERR_MSG_ATTR(extack, attr, "ipsec_packet function attribute supported for VFs only"); return -EOPNOTSUPP; } } } if (tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] && !ops->port_fn_max_io_eqs_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS], "Function does not support max_io_eqs setting"); return -EOPNOTSUPP; } return 0; } static int devlink_port_function_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1]; int err; err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr, devlink_function_nl_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Fail to parse port function attributes"); return err; } err = devlink_port_function_validate(port, tb, extack); if (err) return err; attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; if (attr) { err = devlink_port_function_hw_addr_set(port, attr, extack); if (err) return err; } attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; if (attr) { err = devlink_port_fn_caps_set(port, attr, extack); if (err) return err; } attr = tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS]; if (attr) { err = devlink_port_fn_max_io_eqs_set(port, attr, extack); if (err) return err; } /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. */ attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; if (attr) err = devlink_port_fn_state_set(port, attr, extack); if (!err) devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; int err; if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { enum devlink_port_type port_type; port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); err = devlink_port_type_set(devlink_port, port_type); if (err) return err; } if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) { struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION]; struct netlink_ext_ack *extack = info->extack; err = devlink_port_function_set(devlink_port, attr, extack); if (err) return err; } return 0; } int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; u32 count; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT)) return -EINVAL; if (!devlink_port->ops->port_split) return -EOPNOTSUPP; count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); if (!devlink_port->attrs.splittable) { /* Split ports cannot be split. */ if (devlink_port->attrs.split) NL_SET_ERR_MSG(info->extack, "Port cannot be split further"); else NL_SET_ERR_MSG(info->extack, "Port cannot be split"); return -EINVAL; } if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) { NL_SET_ERR_MSG(info->extack, "Invalid split count"); return -EINVAL; } return devlink_port->ops->port_split(devlink, devlink_port, count, info->extack); } int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; if (!devlink_port->ops->port_unsplit) return -EOPNOTSUPP; return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack); } int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink_port_new_attrs new_attrs = {}; struct devlink *devlink = info->user_ptr[0]; struct devlink_port *devlink_port; struct sk_buff *msg; int err; if (!devlink->ops->port_new) return -EOPNOTSUPP; if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { NL_SET_ERR_MSG(extack, "Port flavour or PCI PF are not specified"); return -EINVAL; } new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); new_attrs.pfnum = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { /* Port index of the new port being created by driver. */ new_attrs.port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); new_attrs.port_index_valid = true; } if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { new_attrs.controller = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); new_attrs.controller_valid = true; } if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); new_attrs.sfnum_valid = true; } err = devlink->ops->port_new(devlink, &new_attrs, extack, &devlink_port); if (err) return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto err_out_port_del; } err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, NULL); if (WARN_ON_ONCE(err)) goto err_out_msg_free; err = genlmsg_reply(msg, info); if (err) goto err_out_port_del; return 0; err_out_msg_free: nlmsg_free(msg); err_out_port_del: devlink_port->ops->port_del(devlink, devlink_port, NULL); return err; } int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; if (!devlink_port->ops->port_del) return -EOPNOTSUPP; return devlink_port->ops->port_del(devlink, devlink_port, extack); } static void devlink_port_type_warn(struct work_struct *work) { struct devlink_port *port = container_of(to_delayed_work(work), struct devlink_port, type_warn_dw); dev_warn(port->devlink->dev, "Type was not set for devlink port."); } static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) { /* Ignore CPU and DSA flavours. */ return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; } #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) { if (!devlink_port_type_should_warn(devlink_port)) return; /* Schedule a work to WARN in case driver does not set port * type within timeout. */ schedule_delayed_work(&devlink_port->type_warn_dw, DEVLINK_PORT_TYPE_WARN_TIMEOUT); } static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) { if (!devlink_port_type_should_warn(devlink_port)) return; cancel_delayed_work_sync(&devlink_port->type_warn_dw); } /** * devlink_port_init() - Init devlink port * * @devlink: devlink * @devlink_port: devlink port * * Initialize essential stuff that is needed for functions * that may be called before devlink port registration. * Call to this function is optional and not needed * in case the driver does not use such functions. */ void devlink_port_init(struct devlink *devlink, struct devlink_port *devlink_port) { if (devlink_port->initialized) return; devlink_port->devlink = devlink; INIT_LIST_HEAD(&devlink_port->region_list); devlink_port->initialized = true; } EXPORT_SYMBOL_GPL(devlink_port_init); /** * devlink_port_fini() - Deinitialize devlink port * * @devlink_port: devlink port * * Deinitialize essential stuff that is in use for functions * that may be called after devlink port unregistration. * Call to this function is optional and not needed * in case the driver does not use such functions. */ void devlink_port_fini(struct devlink_port *devlink_port) { WARN_ON(!list_empty(&devlink_port->region_list)); } EXPORT_SYMBOL_GPL(devlink_port_fini); static const struct devlink_port_ops devlink_port_dummy_ops = {}; /** * devl_port_register_with_ops() - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. */ int devl_port_register_with_ops(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index, const struct devlink_port_ops *ops) { int err; devl_assert_locked(devlink); ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port_init(devlink, devlink_port); devlink_port->registered = true; devlink_port->index = port_index; devlink_port->ops = ops ? ops : &devlink_port_dummy_ops; spin_lock_init(&devlink_port->type_lock); INIT_LIST_HEAD(&devlink_port->reporter_list); err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL); if (err) { devlink_port->registered = false; return err; } INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } EXPORT_SYMBOL_GPL(devl_port_register_with_ops); /** * devlink_port_register_with_ops - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. * * Context: Takes and release devlink->lock <mutex>. */ int devlink_port_register_with_ops(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index, const struct devlink_port_ops *ops) { int err; devl_lock(devlink); err = devl_port_register_with_ops(devlink, devlink_port, port_index, ops); devl_unlock(devlink); return err; } EXPORT_SYMBOL_GPL(devlink_port_register_with_ops); /** * devl_port_unregister() - Unregister devlink port * * @devlink_port: devlink port */ void devl_port_unregister(struct devlink_port *devlink_port) { lockdep_assert_held(&devlink_port->devlink->lock); WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); xa_erase(&devlink_port->devlink->ports, devlink_port->index); WARN_ON(!list_empty(&devlink_port->reporter_list)); devlink_port->registered = false; } EXPORT_SYMBOL_GPL(devl_port_unregister); /** * devlink_port_unregister - Unregister devlink port * * @devlink_port: devlink port * * Context: Takes and release devlink->lock <mutex>. */ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; devl_lock(devlink); devl_port_unregister(devlink_port); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_port_unregister); static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, struct net_device *netdev) { const struct net_device_ops *ops = netdev->netdev_ops; /* If driver registers devlink port, it should set devlink port * attributes accordingly so the compat functions are called * and the original ops are not used. */ if (ops->ndo_get_phys_port_name) { /* Some drivers use the same set of ndos for netdevs * that have devlink_port registered and also for * those who don't. Make sure that ndo_get_phys_port_name * returns -EOPNOTSUPP here in case it is defined. * Warn if not. */ char name[IFNAMSIZ]; int err; err = ops->ndo_get_phys_port_name(netdev, name, sizeof(name)); WARN_ON(err != -EOPNOTSUPP); } if (ops->ndo_get_port_parent_id) { /* Some drivers use the same set of ndos for netdevs * that have devlink_port registered and also for * those who don't. Make sure that ndo_get_port_parent_id * returns -EOPNOTSUPP here in case it is defined. * Warn if not. */ struct netdev_phys_item_id ppid; int err; err = ops->ndo_get_port_parent_id(netdev, &ppid); WARN_ON(err != -EOPNOTSUPP); } } static void __devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type type, void *type_dev) { struct net_device *netdev = type_dev; ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); if (type == DEVLINK_PORT_TYPE_NOTSET) { devlink_port_type_warn_schedule(devlink_port); } else { devlink_port_type_warn_cancel(devlink_port); if (type == DEVLINK_PORT_TYPE_ETH && netdev) devlink_port_type_netdev_checks(devlink_port, netdev); } spin_lock_bh(&devlink_port->type_lock); devlink_port->type = type; switch (type) { case DEVLINK_PORT_TYPE_ETH: devlink_port->type_eth.netdev = netdev; if (netdev) { ASSERT_RTNL(); devlink_port->type_eth.ifindex = netdev->ifindex; BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) != sizeof(netdev->name)); strcpy(devlink_port->type_eth.ifname, netdev->name); } break; case DEVLINK_PORT_TYPE_IB: devlink_port->type_ib.ibdev = type_dev; break; default: break; } spin_unlock_bh(&devlink_port->type_lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } /** * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port * * If driver is calling this, most likely it is doing something wrong. */ void devlink_port_type_eth_set(struct devlink_port *devlink_port) { dev_warn(devlink_port->devlink->dev, "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); /** * devlink_port_type_ib_set - Set port type to InfiniBand * * @devlink_port: devlink port * @ibdev: related IB device */ void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev) { __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); } EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); /** * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port * * If driver is calling this for clearing Ethernet type, most likely * it is doing something wrong. */ void devlink_port_type_clear(struct devlink_port *devlink_port) { if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) dev_warn(devlink_port->devlink->dev, "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); int devlink_port_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct devlink_port *devlink_port = netdev->devlink_port; struct devlink *devlink; if (!devlink_port) return NOTIFY_OK; devlink = devlink_port->devlink; switch (event) { case NETDEV_POST_INIT: /* Set the type but not netdev pointer. It is going to be set * later on by NETDEV_REGISTER event. Happens once during * netdevice register */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: if (devlink_net(devlink) != dev_net(netdev)) return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this * namespace. */ __devlink_port_type_set(devlink_port, devlink_port->type, netdev); break; case NETDEV_UNREGISTER: if (devlink_net(devlink) != dev_net(netdev)) return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. */ __devlink_port_type_set(devlink_port, devlink_port->type, NULL); break; case NETDEV_PRE_UNINIT: /* Clear the type and the netdev pointer. Happens one during * netdevice unregister. */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); break; } return NOTIFY_OK; } static int __devlink_port_attrs_set(struct devlink_port *devlink_port, enum devlink_port_flavour flavour) { struct devlink_port_attrs *attrs = &devlink_port->attrs; devlink_port->attrs_set = true; attrs->flavour = flavour; if (attrs->switch_id.id_len) { devlink_port->switch_port = true; if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN)) attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN; } else { devlink_port->switch_port = false; } return 0; } /** * devlink_port_attrs_set - Set port attributes * * @devlink_port: devlink port * @attrs: devlink port attrs */ void devlink_port_attrs_set(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs) { int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) return; WARN_ON(attrs->splittable && attrs->split); } EXPORT_SYMBOL_GPL(devlink_port_attrs_set); /** * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) return; attrs->pci_pf.controller = controller; attrs->pci_pf.pf = pf; attrs->pci_pf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); /** * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance * @vf: associated VF of a PF for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u16 vf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) return; attrs->pci_vf.controller = controller; attrs->pci_vf.pf = pf; attrs->pci_vf.vf = vf; attrs->pci_vf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); /** * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes * * @devlink_port: devlink port * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance * @sf: associated SF of a PF for the devlink port instance * @external: indicates if the port is for an external controller */ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_SF); if (ret) return; attrs->pci_sf.controller = controller; attrs->pci_sf.pf = pf; attrs->pci_sf.sf = sf; attrs->pci_sf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); static void devlink_port_rel_notify_cb(struct devlink *devlink, u32 port_index) { struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (!devlink_port) return; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } static void devlink_port_rel_cleanup_cb(struct devlink *devlink, u32 port_index, u32 rel_index) { struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (devlink_port && devlink_port->rel_index == rel_index) devlink_port->rel_index = 0; } /** * devl_port_fn_devlink_set - Attach peer devlink * instance to port function. * @devlink_port: devlink port * @fn_devlink: devlink instance to attach */ int devl_port_fn_devlink_set(struct devlink_port *devlink_port, struct devlink *fn_devlink) { ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); if (WARN_ON(devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_SF || devlink_port->attrs.pci_sf.external)) return -EINVAL; return devlink_rel_nested_in_add(&devlink_port->rel_index, devlink_port->devlink->index, devlink_port->index, devlink_port_rel_notify_cb, devlink_port_rel_cleanup_cb, fn_devlink); } EXPORT_SYMBOL_GPL(devl_port_fn_devlink_set); /** * devlink_port_linecard_set - Link port with a linecard * * @devlink_port: devlink port * @linecard: devlink linecard */ void devlink_port_linecard_set(struct devlink_port *devlink_port, struct devlink_linecard *linecard) { ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port); devlink_port->linecard = linecard; } EXPORT_SYMBOL_GPL(devlink_port_linecard_set); static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; if (!devlink_port->attrs_set) return -EOPNOTSUPP; switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: if (devlink_port->linecard) n = snprintf(name, len, "l%u", devlink_linecard_index(devlink_port->linecard)); if (n < len) n += snprintf(name + n, len - n, "p%u", attrs->phys.port_number); if (n < len && attrs->split) n += snprintf(name + n, len - n, "s%u", attrs->phys.split_subport_number); break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: case DEVLINK_PORT_FLAVOUR_UNUSED: /* As CPU and DSA ports do not have a netdevice associated * case should not ever happen. */ WARN_ON(1); return -EINVAL; case DEVLINK_PORT_FLAVOUR_PCI_PF: if (attrs->pci_pf.external) { n = snprintf(name, len, "c%u", attrs->pci_pf.controller); if (n >= len) return -EINVAL; len -= n; name += n; } n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); break; case DEVLINK_PORT_FLAVOUR_PCI_VF: if (attrs->pci_vf.external) { n = snprintf(name, len, "c%u", attrs->pci_vf.controller); if (n >= len) return -EINVAL; len -= n; name += n; } n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; case DEVLINK_PORT_FLAVOUR_PCI_SF: if (attrs->pci_sf.external) { n = snprintf(name, len, "c%u", attrs->pci_sf.controller); if (n >= len) return -EINVAL; len -= n; name += n; } n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; case DEVLINK_PORT_FLAVOUR_VIRTUAL: return -EOPNOTSUPP; } if (n >= len) return -EINVAL; return 0; } int devlink_compat_phys_port_name_get(struct net_device *dev, char *name, size_t len) { struct devlink_port *devlink_port; /* RTNL mutex is held here which ensures that devlink_port * instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ ASSERT_RTNL(); devlink_port = dev->devlink_port; if (!devlink_port) return -EOPNOTSUPP; return __devlink_port_phys_port_name_get(devlink_port, name, len); } int devlink_compat_switch_id_get(struct net_device *dev, struct netdev_phys_item_id *ppid) { struct devlink_port *devlink_port; /* Caller must hold RTNL mutex or reference to dev, which ensures that * devlink_port instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ devlink_port = dev->devlink_port; if (!devlink_port || !devlink_port->switch_port) return -EOPNOTSUPP; memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid)); return 0; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/drivers/char/ttyprintk.c * * Copyright (C) 2010 Samo Pogacnik */ /* * This pseudo device allows user to make printk messages. It is possible * to store "console" messages inline with kernel messages for better analyses * of the boot process, for example. */ #include <linux/console.h> #include <linux/device.h> #include <linux/serial.h> #include <linux/tty.h> #include <linux/module.h> #include <linux/spinlock.h> struct ttyprintk_port { struct tty_port port; spinlock_t spinlock; }; static struct ttyprintk_port tpk_port; /* * Our simple preformatting supports transparent output of (time-stamped) * printk messages (also suitable for logging service): * - any cr is replaced by nl * - adds a ttyprintk source tag in front of each line * - too long message is fragmented, with '\'nl between fragments * - TPK_STR_SIZE isn't really the write_room limiting factor, because * it is emptied on the fly during preformatting. */ #define TPK_STR_SIZE 508 /* should be bigger then max expected line length */ #define TPK_MAX_ROOM 4096 /* we could assume 4K for instance */ #define TPK_PREFIX KERN_SOH __stringify(CONFIG_TTY_PRINTK_LEVEL) static int tpk_curr; static u8 tpk_buffer[TPK_STR_SIZE + 4]; static void tpk_flush(void) { if (tpk_curr > 0) { tpk_buffer[tpk_curr] = '\0'; printk(TPK_PREFIX "[U] %s\n", tpk_buffer); tpk_curr = 0; } } static int tpk_printk(const u8 *buf, size_t count) { size_t i; for (i = 0; i < count; i++) { if (tpk_curr >= TPK_STR_SIZE) { /* end of tmp buffer reached: cut the message in two */ tpk_buffer[tpk_curr++] = '\\'; tpk_flush(); } switch (buf[i]) { case '\r': tpk_flush(); if ((i + 1) < count && buf[i + 1] == '\n') i++; break; case '\n': tpk_flush(); break; default: tpk_buffer[tpk_curr++] = buf[i]; break; } } return count; } /* * TTY operations open function. */ static int tpk_open(struct tty_struct *tty, struct file *filp) { tty->driver_data = &tpk_port; return tty_port_open(&tpk_port.port, tty, filp); } /* * TTY operations close function. */ static void tpk_close(struct tty_struct *tty, struct file *filp) { struct ttyprintk_port *tpkp = tty->driver_data; tty_port_close(&tpkp->port, tty, filp); } /* * TTY operations write function. */ static ssize_t tpk_write(struct tty_struct *tty, const u8 *buf, size_t count) { struct ttyprintk_port *tpkp = tty->driver_data; unsigned long flags; int ret; /* exclusive use of tpk_printk within this tty */ spin_lock_irqsave(&tpkp->spinlock, flags); ret = tpk_printk(buf, count); spin_unlock_irqrestore(&tpkp->spinlock, flags); return ret; } /* * TTY operations write_room function. */ static unsigned int tpk_write_room(struct tty_struct *tty) { return TPK_MAX_ROOM; } /* * TTY operations hangup function. */ static void tpk_hangup(struct tty_struct *tty) { struct ttyprintk_port *tpkp = tty->driver_data; tty_port_hangup(&tpkp->port); } /* * TTY port operations shutdown function. */ static void tpk_port_shutdown(struct tty_port *tport) { struct ttyprintk_port *tpkp = container_of(tport, struct ttyprintk_port, port); unsigned long flags; spin_lock_irqsave(&tpkp->spinlock, flags); tpk_flush(); spin_unlock_irqrestore(&tpkp->spinlock, flags); } static const struct tty_operations ttyprintk_ops = { .open = tpk_open, .close = tpk_close, .write = tpk_write, .write_room = tpk_write_room, .hangup = tpk_hangup, }; static const struct tty_port_operations tpk_port_ops = { .shutdown = tpk_port_shutdown, }; static struct tty_driver *ttyprintk_driver; static struct tty_driver *ttyprintk_console_device(struct console *c, int *index) { *index = 0; return ttyprintk_driver; } static struct console ttyprintk_console = { .name = "ttyprintk", .device = ttyprintk_console_device, }; static int __init ttyprintk_init(void) { int ret; spin_lock_init(&tpk_port.spinlock); ttyprintk_driver = tty_alloc_driver(1, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_UNNUMBERED_NODE); if (IS_ERR(ttyprintk_driver)) return PTR_ERR(ttyprintk_driver); tty_port_init(&tpk_port.port); tpk_port.port.ops = &tpk_port_ops; ttyprintk_driver->driver_name = "ttyprintk"; ttyprintk_driver->name = "ttyprintk"; ttyprintk_driver->major = TTYAUX_MAJOR; ttyprintk_driver->minor_start = 3; ttyprintk_driver->type = TTY_DRIVER_TYPE_CONSOLE; ttyprintk_driver->init_termios = tty_std_termios; ttyprintk_driver->init_termios.c_oflag = OPOST | OCRNL | ONOCR | ONLRET; tty_set_operations(ttyprintk_driver, &ttyprintk_ops); tty_port_link_device(&tpk_port.port, ttyprintk_driver, 0); ret = tty_register_driver(ttyprintk_driver); if (ret < 0) { printk(KERN_ERR "Couldn't register ttyprintk driver\n"); goto error; } register_console(&ttyprintk_console); return 0; error: tty_driver_kref_put(ttyprintk_driver); tty_port_destroy(&tpk_port.port); return ret; } static void __exit ttyprintk_exit(void) { unregister_console(&ttyprintk_console); tty_unregister_driver(ttyprintk_driver); tty_driver_kref_put(ttyprintk_driver); tty_port_destroy(&tpk_port.port); } device_initcall(ttyprintk_init); module_exit(ttyprintk_exit); MODULE_DESCRIPTION("TTY driver to output user messages via printk"); MODULE_LICENSE("GPL"); |
| 6 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which emulate a local clock-event * device via a broadcast event source. * * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> #include <linux/smp.h> #include <linux/module.h> #include "tick-internal.h" /* * Broadcast support for broken x86 hardware, where the local apic * timer stops in C3 state. */ static struct tick_device tick_broadcast_device; static cpumask_var_t tick_broadcast_mask __cpumask_var_read_mostly; static cpumask_var_t tick_broadcast_on __cpumask_var_read_mostly; static cpumask_var_t tmpmask __cpumask_var_read_mostly; static int tick_broadcast_forced; static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); #ifdef CONFIG_TICK_ONESHOT static DEFINE_PER_CPU(struct clock_event_device *, tick_oneshot_wakeup_device); static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); # ifdef CONFIG_HOTPLUG_CPU static void tick_broadcast_oneshot_offline(unsigned int cpu); # endif #else static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } # ifdef CONFIG_HOTPLUG_CPU static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { } # endif #endif /* * Debugging: see timer_list.c */ struct tick_device *tick_get_broadcast_device(void) { return &tick_broadcast_device; } struct cpumask *tick_get_broadcast_mask(void) { return tick_broadcast_mask; } static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu); const struct clock_event_device *tick_get_wakeup_device(int cpu) { return tick_get_oneshot_wakeup_device(cpu); } /* * Start the device in periodic mode */ static void tick_broadcast_start_periodic(struct clock_event_device *bc) { if (bc) tick_setup_periodic(bc, 1); } /* * Check, if the device can be utilized as broadcast device: */ static bool tick_check_broadcast_device(struct clock_event_device *curdev, struct clock_event_device *newdev) { if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || (newdev->features & CLOCK_EVT_FEAT_PERCPU) || (newdev->features & CLOCK_EVT_FEAT_C3STOP)) return false; if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT && !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) return false; return !curdev || newdev->rating > curdev->rating; } #ifdef CONFIG_TICK_ONESHOT static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu) { return per_cpu(tick_oneshot_wakeup_device, cpu); } static void tick_oneshot_wakeup_handler(struct clock_event_device *wd) { /* * If we woke up early and the tick was reprogrammed in the * meantime then this may be spurious but harmless. */ tick_receive_broadcast(); } static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, int cpu) { struct clock_event_device *curdev = tick_get_oneshot_wakeup_device(cpu); if (!newdev) goto set_device; if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || (newdev->features & CLOCK_EVT_FEAT_C3STOP)) return false; if (!(newdev->features & CLOCK_EVT_FEAT_PERCPU) || !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) return false; if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) return false; if (curdev && newdev->rating <= curdev->rating) return false; if (!try_module_get(newdev->owner)) return false; newdev->event_handler = tick_oneshot_wakeup_handler; set_device: clockevents_exchange_device(curdev, newdev); per_cpu(tick_oneshot_wakeup_device, cpu) = newdev; return true; } #else static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu) { return NULL; } static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, int cpu) { return false; } #endif /* * Conditionally install/replace broadcast device */ void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { struct clock_event_device *cur = tick_broadcast_device.evtdev; if (tick_set_oneshot_wakeup_device(dev, cpu)) return; if (!tick_check_broadcast_device(cur, dev)) return; if (!try_module_get(dev->owner)) return; clockevents_exchange_device(cur, dev); if (cur) cur->event_handler = clockevents_handle_noop; tick_broadcast_device.evtdev = dev; if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(dev); if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; /* * If the system already runs in oneshot mode, switch the newly * registered broadcast device to oneshot mode explicitly. */ if (tick_broadcast_oneshot_active()) { tick_broadcast_switch_to_oneshot(); return; } /* * Inform all cpus about this. We might be in a situation * where we did not switch to oneshot mode because the per cpu * devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack * of a oneshot capable broadcast device. Without that * notification the systems stays stuck in periodic mode * forever. */ tick_clock_notify(); } /* * Check, if the device is the broadcast device */ int tick_is_broadcast_device(struct clock_event_device *dev) { return (dev && tick_broadcast_device.evtdev == dev); } int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { int ret = -ENODEV; if (tick_is_broadcast_device(dev)) { raw_spin_lock(&tick_broadcast_lock); ret = __clockevents_update_freq(dev, freq); raw_spin_unlock(&tick_broadcast_lock); } return ret; } static void err_broadcast(const struct cpumask *mask) { pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n"); } static void tick_device_setup_broadcast_func(struct clock_event_device *dev) { if (!dev->broadcast) dev->broadcast = tick_broadcast; if (!dev->broadcast) { pr_warn_once("%s depends on broadcast, but no broadcast function available\n", dev->name); dev->broadcast = err_broadcast; } } /* * Check, if the device is dysfunctional and a placeholder, which * needs to be handled by the broadcast device. */ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { struct clock_event_device *bc = tick_broadcast_device.evtdev; unsigned long flags; int ret = 0; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); /* * Devices might be registered with both periodic and oneshot * mode disabled. This signals, that the device needs to be * operated from the broadcast device and is a placeholder for * the cpu local device. */ if (!tick_device_is_functional(dev)) { dev->event_handler = tick_handle_periodic; tick_device_setup_broadcast_func(dev); cpumask_set_cpu(cpu, tick_broadcast_mask); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else tick_broadcast_setup_oneshot(bc, false); ret = 1; } else { /* * Clear the broadcast bit for this cpu if the * device is not power state affected. */ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) cpumask_clear_cpu(cpu, tick_broadcast_mask); else tick_device_setup_broadcast_func(dev); /* * Clear the broadcast bit if the CPU is not in * periodic broadcast on state. */ if (!cpumask_test_cpu(cpu, tick_broadcast_on)) cpumask_clear_cpu(cpu, tick_broadcast_mask); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_ONESHOT: /* * If the system is in oneshot mode we can * unconditionally clear the oneshot mask bit, * because the CPU is running and therefore * not in an idle state which causes the power * state affected device to stop. Let the * caller initialize the device. */ tick_broadcast_clear_oneshot(cpu); ret = 0; break; case TICKDEV_MODE_PERIODIC: /* * If the system is in periodic mode, check * whether the broadcast device can be * switched off now. */ if (cpumask_empty(tick_broadcast_mask) && bc) clockevents_shutdown(bc); /* * If we kept the cpu in the broadcast mask, * tell the caller to leave the per cpu device * in shutdown state. The periodic interrupt * is delivered by the broadcast device, if * the broadcast device exists and is not * hrtimer based. */ if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER)) ret = cpumask_test_cpu(cpu, tick_broadcast_mask); break; default: break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); return ret; } int tick_receive_broadcast(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *evt = td->evtdev; if (!evt) return -ENODEV; if (!evt->event_handler) return -EINVAL; evt->event_handler(evt); return 0; } /* * Broadcast the event to the cpus, which are set in the mask (mangled). */ static bool tick_do_broadcast(struct cpumask *mask) { int cpu = smp_processor_id(); struct tick_device *td; bool local = false; /* * Check, if the current cpu is in the mask */ if (cpumask_test_cpu(cpu, mask)) { struct clock_event_device *bc = tick_broadcast_device.evtdev; cpumask_clear_cpu(cpu, mask); /* * We only run the local handler, if the broadcast * device is not hrtimer based. Otherwise we run into * a hrtimer recursion. * * local timer_interrupt() * local_handler() * expire_hrtimers() * bc_handler() * local_handler() * expire_hrtimers() */ local = !(bc->features & CLOCK_EVT_FEAT_HRTIMER); } if (!cpumask_empty(mask)) { /* * It might be necessary to actually check whether the devices * have different broadcast functions. For now, just use the * one of the first device. This works as long as we have this * misfeature only on x86 (lapic) */ td = &per_cpu(tick_cpu_device, cpumask_first(mask)); td->evtdev->broadcast(mask); } return local; } /* * Periodic broadcast: * - invoke the broadcast handlers */ static bool tick_do_periodic_broadcast(void) { cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask); return tick_do_broadcast(tmpmask); } /* * Event handler for periodic broadcast ticks */ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool bc_local; raw_spin_lock(&tick_broadcast_lock); /* Handle spurious interrupts gracefully */ if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) { raw_spin_unlock(&tick_broadcast_lock); return; } bc_local = tick_do_periodic_broadcast(); if (clockevent_state_oneshot(dev)) { ktime_t next = ktime_add_ns(dev->next_event, TICK_NSEC); clockevents_program_event(dev, next, true); } raw_spin_unlock(&tick_broadcast_lock); /* * We run the handler of the local cpu after dropping * tick_broadcast_lock because the handler might deadlock when * trying to switch to oneshot mode. */ if (bc_local) td->evtdev->event_handler(td->evtdev); } /** * tick_broadcast_control - Enable/disable or force broadcast mode * @mode: The selected broadcast mode * * Called when the system enters a state where affected tick devices * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. */ void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; int cpu, bc_stopped; unsigned long flags; /* Protects also the local clockevent device. */ raw_spin_lock_irqsave(&tick_broadcast_lock, flags); td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; /* * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) goto out; if (!tick_device_is_functional(dev)) goto out; cpu = smp_processor_id(); bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); switch (mode) { case TICK_BROADCAST_FORCE: tick_broadcast_forced = 1; fallthrough; case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { /* * Only shutdown the cpu local device, if: * * - the broadcast device exists * - the broadcast device is not a hrtimer based one * - the broadcast device is in periodic mode to * avoid a hiccup during switch to oneshot mode */ if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) && tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); } break; case TICK_BROADCAST_OFF: if (tick_broadcast_forced) break; cpumask_clear_cpu(cpu, tick_broadcast_on); if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); } break; } if (bc) { if (cpumask_empty(tick_broadcast_mask)) { if (!bc_stopped) clockevents_shutdown(bc); } else if (bc_stopped) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else tick_broadcast_setup_oneshot(bc, false); } } out: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } EXPORT_SYMBOL_GPL(tick_broadcast_control); /* * Set the periodic handler depending on broadcast on/off */ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) { if (!broadcast) dev->event_handler = tick_handle_periodic; else dev->event_handler = tick_handle_periodic_broadcast; } #ifdef CONFIG_HOTPLUG_CPU static void tick_shutdown_broadcast(void) { struct clock_event_device *bc = tick_broadcast_device.evtdev; if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) clockevents_shutdown(bc); } } /* * Remove a CPU from broadcasting */ void tick_broadcast_offline(unsigned int cpu) { raw_spin_lock(&tick_broadcast_lock); cpumask_clear_cpu(cpu, tick_broadcast_mask); cpumask_clear_cpu(cpu, tick_broadcast_on); tick_broadcast_oneshot_offline(cpu); tick_shutdown_broadcast(); raw_spin_unlock(&tick_broadcast_lock); } #endif void tick_suspend_broadcast(void) { struct clock_event_device *bc; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc) clockevents_shutdown(bc); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } /* * This is called from tick_resume_local() on a resuming CPU. That's * called from the core resume function, tick_unfreeze() and the magic XEN * resume hackery. * * In none of these cases the broadcast device mode can change and the * bit of the resuming CPU in the broadcast mask is safe as well. */ bool tick_resume_check_broadcast(void) { if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) return false; else return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask); } void tick_resume_broadcast(void) { struct clock_event_device *bc; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc) { clockevents_tick_resume(bc); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_PERIODIC: if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(bc); break; case TICKDEV_MODE_ONESHOT: if (!cpumask_empty(tick_broadcast_mask)) tick_resume_broadcast_oneshot(bc); break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #ifdef CONFIG_TICK_ONESHOT static cpumask_var_t tick_broadcast_oneshot_mask __cpumask_var_read_mostly; static cpumask_var_t tick_broadcast_pending_mask __cpumask_var_read_mostly; static cpumask_var_t tick_broadcast_force_mask __cpumask_var_read_mostly; /* * Exposed for debugging: see timer_list.c */ struct cpumask *tick_get_broadcast_oneshot_mask(void) { return tick_broadcast_oneshot_mask; } /* * Called before going idle with interrupts disabled. Checks whether a * broadcast event from the other core is about to happen. We detected * that in tick_broadcast_oneshot_control(). The callsite can use this * to avoid a deep idle transition as we are about to get the * broadcast IPI right away. */ noinstr int tick_check_broadcast_expired(void) { #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H return arch_test_bit(smp_processor_id(), cpumask_bits(tick_broadcast_force_mask)); #else return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask); #endif } /* * Set broadcast interrupt affinity */ static void tick_broadcast_set_affinity(struct clock_event_device *bc, const struct cpumask *cpumask) { if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ)) return; if (cpumask_equal(bc->cpumask, cpumask)) return; bc->cpumask = cpumask; irq_set_affinity(bc->irq, bc->cpumask); } static void tick_broadcast_set_event(struct clock_event_device *bc, int cpu, ktime_t expires) { if (!clockevent_state_oneshot(bc)) clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(bc, expires, 1); tick_broadcast_set_affinity(bc, cpumask_of(cpu)); } static void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); } /* * Called from irq_enter() when idle was interrupted to reenable the * per cpu device. */ void tick_check_oneshot_broadcast_this_cpu(void) { if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); /* * We might be in the middle of switching over from * periodic to oneshot. If the CPU has not yet * switched over, leave the device alone. */ if (td->mode == TICKDEV_MODE_ONESHOT) { clockevents_switch_state(td->evtdev, CLOCK_EVT_STATE_ONESHOT); } } } /* * Handle oneshot mode broadcasting */ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) { struct tick_device *td; ktime_t now, next_event; int cpu, next_cpu = 0; bool bc_local; raw_spin_lock(&tick_broadcast_lock); dev->next_event = KTIME_MAX; next_event = KTIME_MAX; cpumask_clear(tmpmask); now = ktime_get(); /* Find all expired events */ for_each_cpu(cpu, tick_broadcast_oneshot_mask) { /* * Required for !SMP because for_each_cpu() reports * unconditionally CPU0 as set on UP kernels. */ if (!IS_ENABLED(CONFIG_SMP) && cpumask_empty(tick_broadcast_oneshot_mask)) break; td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event <= now) { cpumask_set_cpu(cpu, tmpmask); /* * Mark the remote cpu in the pending mask, so * it can avoid reprogramming the cpu local * timer in tick_broadcast_oneshot_control(). */ cpumask_set_cpu(cpu, tick_broadcast_pending_mask); } else if (td->evtdev->next_event < next_event) { next_event = td->evtdev->next_event; next_cpu = cpu; } } /* * Remove the current cpu from the pending mask. The event is * delivered immediately in tick_do_broadcast() ! */ cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask); /* Take care of enforced broadcast requests */ cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask); cpumask_clear(tick_broadcast_force_mask); /* * Sanity check. Catch the case where we try to broadcast to * offline cpus. */ if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask))) cpumask_and(tmpmask, tmpmask, cpu_online_mask); /* * Wakeup the cpus which have an expired event. */ bc_local = tick_do_broadcast(tmpmask); /* * Two reasons for reprogram: * * - The global event did not expire any CPU local * events. This happens in dyntick mode, as the maximum PIT * delta is quite small. * * - There are pending events on sleeping CPUs which were not * in the event mask */ if (next_event != KTIME_MAX) tick_broadcast_set_event(dev, next_cpu, next_event); raw_spin_unlock(&tick_broadcast_lock); if (bc_local) { td = this_cpu_ptr(&tick_cpu_device); td->evtdev->event_handler(td->evtdev); } } static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu) { if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER)) return 0; if (bc->next_event == KTIME_MAX) return 0; return bc->bound_on == cpu ? -EBUSY : 0; } static void broadcast_shutdown_local(struct clock_event_device *bc, struct clock_event_device *dev) { /* * For hrtimer based broadcasting we cannot shutdown the cpu * local device if our own event is the first one to expire or * if we own the broadcast timer. */ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) { if (broadcast_needs_cpu(bc, smp_processor_id())) return; if (dev->next_event < bc->next_event) return; } clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } static int ___tick_broadcast_oneshot_control(enum tick_broadcast_state state, struct tick_device *td, int cpu) { struct clock_event_device *bc, *dev = td->evtdev; int ret = 0; ktime_t now; raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; if (state == TICK_BROADCAST_ENTER) { /* * If the current CPU owns the hrtimer broadcast * mechanism, it cannot go deep idle and we do not add * the CPU to the broadcast mask. We don't have to go * through the EXIT path as the local timer is not * shutdown. */ ret = broadcast_needs_cpu(bc, cpu); if (ret) goto out; /* * If the broadcast device is in periodic mode, we * return. */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { /* If it is a hrtimer based broadcast, return busy */ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) ret = -EBUSY; goto out; } if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); /* Conditionally shut down the local timer. */ broadcast_shutdown_local(bc, dev); /* * We only reprogram the broadcast timer if we * did not mark ourself in the force mask and * if the cpu local event is earlier than the * broadcast event. If the current CPU is in * the force mask, then we are going to be * woken by the IPI right away; we return * busy, so the CPU does not try to go deep * idle. */ if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) { ret = -EBUSY; } else if (dev->next_event < bc->next_event) { tick_broadcast_set_event(bc, cpu, dev->next_event); /* * In case of hrtimer broadcasts the * programming might have moved the * timer to this cpu. If yes, remove * us from the broadcast mask and * return busy. */ ret = broadcast_needs_cpu(bc, cpu); if (ret) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } } } } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast * pending mask and fired the broadcast * IPI. So we are going to handle the expired * event anyway via the broadcast IPI * handler. No need to reprogram the timer * with an already expired event. */ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_pending_mask)) goto out; /* * Bail out if there is no next event. */ if (dev->next_event == KTIME_MAX) goto out; /* * If the pending bit is not set, then we are * either the CPU handling the broadcast * interrupt or we got woken by something else. * * We are no longer in the broadcast mask, so * if the cpu local expiry time is already * reached, we would reprogram the cpu local * timer with an already expired event. * * This can lead to a ping-pong when we return * to idle and therefore rearm the broadcast * timer before the cpu local timer was able * to fire. This happens because the forced * reprogramming makes sure that the event * will happen in the future and depending on * the min_delta setting this might be far * enough out that the ping-pong starts. * * If the cpu local next_event has expired * then we know that the broadcast timer * next_event has expired as well and * broadcast is about to be handled. So we * avoid reprogramming and enforce that the * broadcast handler, which did not run yet, * will invoke the cpu local handler. * * We cannot call the handler directly from * here, because we might be in a NOHZ phase * and we did not go through the irq_enter() * nohz fixups. */ now = ktime_get(); if (dev->next_event <= now) { cpumask_set_cpu(cpu, tick_broadcast_force_mask); goto out; } /* * We got woken by something else. Reprogram * the cpu local timer device. */ tick_program_event(dev->next_event, 1); } } out: raw_spin_unlock(&tick_broadcast_lock); return ret; } static int tick_oneshot_wakeup_control(enum tick_broadcast_state state, struct tick_device *td, int cpu) { struct clock_event_device *dev, *wd; dev = td->evtdev; if (td->mode != TICKDEV_MODE_ONESHOT) return -EINVAL; wd = tick_get_oneshot_wakeup_device(cpu); if (!wd) return -ENODEV; switch (state) { case TICK_BROADCAST_ENTER: clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); clockevents_switch_state(wd, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(wd, dev->next_event, 1); break; case TICK_BROADCAST_EXIT: /* We may have transitioned to oneshot mode while idle */ if (clockevent_get_state(wd) != CLOCK_EVT_STATE_ONESHOT) return -ENODEV; } return 0; } int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); int cpu = smp_processor_id(); if (!tick_oneshot_wakeup_control(state, td, cpu)) return 0; if (tick_broadcast_device.evtdev) return ___tick_broadcast_oneshot_control(state, td, cpu); /* * If there is no broadcast or wakeup device, tell the caller not * to go into deep idle. */ return -EBUSY; } /* * Reset the one shot broadcast for a cpu * * Called with tick_broadcast_lock held */ static void tick_broadcast_clear_oneshot(int cpu) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); } static void tick_broadcast_init_next_event(struct cpumask *mask, ktime_t expires) { struct tick_device *td; int cpu; for_each_cpu(cpu, mask) { td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev) td->evtdev->next_event = expires; } } static inline ktime_t tick_get_next_period(void) { ktime_t next; /* * Protect against concurrent updates (store /load tearing on * 32bit). It does not matter if the time is already in the * past. The broadcast device which is about to be programmed will * fire in any case. */ raw_spin_lock(&jiffies_lock); next = tick_next_period; raw_spin_unlock(&jiffies_lock); return next; } /** * tick_broadcast_setup_oneshot - setup the broadcast device */ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { int cpu = smp_processor_id(); ktime_t nexttick = 0; if (!bc) return; /* * When the broadcast device was switched to oneshot by the first * CPU handling the NOHZ change, the other CPUs will reach this * code via hrtimer_run_queues() -> tick_check_oneshot_change() * too. Set up the broadcast device only once! */ if (bc->event_handler == tick_handle_oneshot_broadcast) { /* * The CPU which switched from periodic to oneshot mode * set the broadcast oneshot bit for all other CPUs which * are in the general (periodic) broadcast mask to ensure * that CPUs which wait for the periodic broadcast are * woken up. * * Clear the bit for the local CPU as the set bit would * prevent the first tick_broadcast_enter() after this CPU * switched to oneshot state to program the broadcast * device. * * This code can also be reached via tick_broadcast_control(), * but this cannot avoid the tick_broadcast_clear_oneshot() * as that would break the periodic to oneshot transition of * secondary CPUs. But that's harmless as the below only * clears already cleared bits. */ tick_broadcast_clear_oneshot(cpu); return; } bc->event_handler = tick_handle_oneshot_broadcast; bc->next_event = KTIME_MAX; /* * When the tick mode is switched from periodic to oneshot it must * be ensured that CPUs which are waiting for periodic broadcast * get their wake-up at the next tick. This is achieved by ORing * tick_broadcast_mask into tick_broadcast_oneshot_mask. * * For other callers, e.g. broadcast device replacement, * tick_broadcast_oneshot_mask must not be touched as this would * set bits for CPUs which are already NOHZ, but not idle. Their * next tick_broadcast_enter() would observe the bit set and fail * to update the expiry time and the broadcast event device. */ if (from_periodic) { cpumask_copy(tmpmask, tick_broadcast_mask); /* Remove the local CPU as it is obviously not idle */ cpumask_clear_cpu(cpu, tmpmask); cpumask_or(tick_broadcast_oneshot_mask, tick_broadcast_oneshot_mask, tmpmask); /* * Ensure that the oneshot broadcast handler will wake the * CPUs which are still waiting for periodic broadcast. */ nexttick = tick_get_next_period(); tick_broadcast_init_next_event(tmpmask, nexttick); /* * If the underlying broadcast clock event device is * already in oneshot state, then there is nothing to do. * The device was already armed for the next tick * in tick_handle_broadcast_periodic() */ if (clockevent_state_oneshot(bc)) return; } /* * When switching from periodic to oneshot mode arm the broadcast * device for the next tick. * * If the broadcast device has been replaced in oneshot mode and * the oneshot broadcast mask is not empty, then arm it to expire * immediately in order to reevaluate the next expiring timer. * @nexttick is 0 and therefore in the past which will cause the * clockevent code to force an event. * * For both cases the programming can be avoided when the oneshot * broadcast mask is empty. * * tick_broadcast_set_event() implicitly switches the broadcast * device to oneshot state. */ if (!cpumask_empty(tick_broadcast_oneshot_mask)) tick_broadcast_set_event(bc, cpu, nexttick); } /* * Select oneshot operating mode for the broadcast device */ void tick_broadcast_switch_to_oneshot(void) { struct clock_event_device *bc; enum tick_device_mode oldmode; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); oldmode = tick_broadcast_device.mode; tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) tick_broadcast_setup_oneshot(bc, oldmode == TICKDEV_MODE_PERIODIC); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #ifdef CONFIG_HOTPLUG_CPU void hotplug_cpu__broadcast_tick_pull(int deadcpu) { struct clock_event_device *bc; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc && broadcast_needs_cpu(bc, deadcpu)) { /* * If the broadcast force bit of the current CPU is set, * then the current CPU has not yet reprogrammed the local * timer device to avoid a ping-pong race. See * ___tick_broadcast_oneshot_control(). * * If the broadcast device is hrtimer based then * programming the broadcast event below does not have any * effect because the local clockevent device is not * running and not programmed because the broadcast event * is not earlier than the pending event of the local clock * event device. As a consequence all CPUs waiting for a * broadcast event are stuck forever. * * Detect this condition and reprogram the cpu local timer * device to avoid the starvation. */ if (tick_check_broadcast_expired()) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask); tick_program_event(td->evtdev->next_event, 1); } /* This moves the broadcast assignment to this CPU: */ clockevents_program_event(bc, bc->next_event, 1); } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } /* * Remove a dying CPU from broadcasting */ static void tick_broadcast_oneshot_offline(unsigned int cpu) { if (tick_get_oneshot_wakeup_device(cpu)) tick_set_oneshot_wakeup_device(NULL, cpu); /* * Clear the broadcast masks for the dead cpu, but do not stop * the broadcast device! */ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); } #endif /* * Check, whether the broadcast device is in one shot mode */ int tick_broadcast_oneshot_active(void) { return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; } /* * Check whether the broadcast device supports oneshot. */ bool tick_broadcast_oneshot_available(void) { struct clock_event_device *bc = tick_broadcast_device.evtdev; return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; } #else int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc = tick_broadcast_device.evtdev; if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER)) return -EBUSY; return 0; } #endif void __init tick_broadcast_init(void) { zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT); zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); #ifdef CONFIG_TICK_ONESHOT zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); #endif } |
| 2 219 162 220 217 220 220 2 104 104 104 102 102 102 102 101 101 102 27 25 2 27 27 27 26 27 2 2 2 1041 1043 5 4831 4828 4830 4834 4828 4834 35 4827 4831 4840 1 4831 5 35 35 4827 4841 4833 40 4828 4845 5 5 5 98 98 1 98 98 98 3 95 94 4 98 98 98 98 98 98 98 93 95 95 95 95 93 95 95 95 94 95 95 95 94 95 95 95 94 95 94 4829 4843 2 4833 4821 4833 95 95 95 95 95 95 93 94 93 94 93 93 93 94 94 4619 4627 2 4620 4611 4616 4620 4615 4680 4680 4687 697 4686 1 4688 33 2 2 2 2 1042 35 36 36 35 4533 34 2 2 35 36 36 36 36 36 36 36 36 2 2 214 7 1 1 7 7 222 220 381 381 140 383 381 253 36 25 129 104 25 129 129 2 219 1 1 219 220 2 2 4703 775 4832 4525 4522 4520 4513 4516 4533 4525 4523 4522 628 4516 4512 4520 93 67 251 66 33 220 5161 2044 254 4610 4521 93 93 4530 254 253 1 1 1 1467 879 4620 4831 4826 4824 4823 4829 4823 4842 4835 1408 4837 4834 4829 4841 4841 4831 4840 4831 4827 4827 4684 879 2 3 3 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 1 2 3 3 2 3 3 2 2 2 2 2 2 2 2 2 2 2 2 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 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 | // SPDX-License-Identifier: GPL-2.0 /* * Block multiqueue core code * * Copyright (C) 2013-2014 Jens Axboe * Copyright (C) 2013-2014 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> #include <linux/kmemleak.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/llist.h> #include <linux/cpu.h> #include <linux/cache.h> #include <linux/sched/topology.h> #include <linux/sched/signal.h> #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> #include <linux/blk-crypto.h> #include <linux/part_stat.h> #include <linux/sched/isolation.h> #include <trace/events/block.h> #include <linux/t10-pi.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-pm.h" #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags); static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags); /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { return !list_empty_careful(&hctx->dispatch) || sbitmap_any_bit_set(&hctx->ctx_map) || blk_mq_sched_has_work(hctx); } /* * Mark this ctx as having pending work in this hardware queue */ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; if (!sbitmap_test_bit(&hctx->ctx_map, bit)) sbitmap_set_bit(&hctx->ctx_map, bit); } static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; sbitmap_clear_bit(&hctx->ctx_map, bit); } struct mq_inflight { struct block_device *part; unsigned int inflight[2]; }; static bool blk_mq_check_inflight(struct request *rq, void *priv) { struct mq_inflight *mi = priv; if (rq->part && blk_do_io_stat(rq) && (!bdev_is_partition(mi->part) || rq->part == mi->part) && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++; return true; } unsigned int blk_mq_in_flight(struct request_queue *q, struct block_device *part) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); return mi.inflight[0] + mi.inflight[1]; } void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); inflight[0] = mi.inflight[0]; inflight[1] = mi.inflight[1]; } void blk_freeze_queue_start(struct request_queue *q) { mutex_lock(&q->mq_freeze_lock); if (++q->mq_freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); mutex_unlock(&q->mq_freeze_lock); if (queue_is_mq(q)) blk_mq_run_hw_queues(q, false); } else { mutex_unlock(&q->mq_freeze_lock); } } EXPORT_SYMBOL_GPL(blk_freeze_queue_start); void blk_mq_freeze_queue_wait(struct request_queue *q) { wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout) { return wait_event_timeout(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter), timeout); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); /* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. */ void blk_freeze_queue(struct request_queue *q) { /* * In the !blk_mq case we are only calling this to kill the * q_usage_counter, otherwise this increases the freeze depth * and waits for it to return to zero. For this reason there is * no blk_unfreeze_queue(), and blk_freeze_queue() is not * exported to drivers as the only user for unfreeze is blk_mq. */ blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } void blk_mq_freeze_queue(struct request_queue *q) { /* * ...just an alias to keep freeze and unfreeze actions balanced * in the blk_mq_* namespace */ blk_freeze_queue(q); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) { mutex_lock(&q->mq_freeze_lock); if (force_atomic) q->q_usage_counter.data->force_atomic = true; q->mq_freeze_depth--; WARN_ON_ONCE(q->mq_freeze_depth < 0); if (!q->mq_freeze_depth) { percpu_ref_resurrect(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } mutex_unlock(&q->mq_freeze_lock); } void blk_mq_unfreeze_queue(struct request_queue *q) { __blk_mq_unfreeze_queue(q, false); } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); /* * FIXME: replace the scsi_internal_device_*block_nowait() calls in the * mpt3sas driver such that this function can be removed. */ void blk_mq_quiesce_queue_nowait(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->queue_lock, flags); if (!q->quiesce_depth++) blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); spin_unlock_irqrestore(&q->queue_lock, flags); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); /** * blk_mq_wait_quiesce_done() - wait until in-progress quiesce is done * @set: tag_set to wait on * * Note: it is driver's responsibility for making sure that quiesce has * been started on or more of the request_queues of the tag_set. This * function only waits for the quiesce on those request_queues that had * the quiesce flag set using blk_mq_quiesce_queue_nowait. */ void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set) { if (set->flags & BLK_MQ_F_BLOCKING) synchronize_srcu(set->srcu); else synchronize_rcu(); } EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done); /** * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished * @q: request queue. * * Note: this function does not prevent that the struct request end_io() * callback function is invoked. Once this function is returned, we make * sure no dispatch can happen until the queue is unquiesced via * blk_mq_unquiesce_queue(). */ void blk_mq_quiesce_queue(struct request_queue *q) { blk_mq_quiesce_queue_nowait(q); /* nothing to wait for non-mq queues */ if (queue_is_mq(q)) blk_mq_wait_quiesce_done(q->tag_set); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); /* * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() * @q: request queue. * * This function recovers queue into the state before quiescing * which is done by blk_mq_quiesce_queue. */ void blk_mq_unquiesce_queue(struct request_queue *q) { unsigned long flags; bool run_queue = false; spin_lock_irqsave(&q->queue_lock, flags); if (WARN_ON_ONCE(q->quiesce_depth <= 0)) { ; } else if (!--q->quiesce_depth) { blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); run_queue = true; } spin_unlock_irqrestore(&q->queue_lock, flags); /* dispatch requests which are inserted during quiescing */ if (run_queue) blk_mq_run_hw_queues(q, true); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; mutex_lock(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_quiesce_queue_nowait(q); } blk_mq_wait_quiesce_done(set); mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset); void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; mutex_lock(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_unquiesce_queue(q); } mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset); void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_wakeup_all(hctx->tags, true); } void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = blk_time_get_ns(); rq->part = NULL; blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); /* Set start and alloc time when the allocated request is actually used */ static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns) { if (blk_mq_need_time_stamp(rq)) rq->start_time_ns = blk_time_get_ns(); else rq->start_time_ns = 0; #ifdef CONFIG_BLK_RQ_ALLOC_TIME if (blk_queue_rq_alloc_time(rq->q)) rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns; else rq->alloc_time_ns = 0; #endif } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, struct blk_mq_tags *tags, unsigned int tag) { struct blk_mq_ctx *ctx = data->ctx; struct blk_mq_hw_ctx *hctx = data->hctx; struct request_queue *q = data->q; struct request *rq = tags->static_rqs[tag]; rq->q = q; rq->mq_ctx = ctx; rq->mq_hctx = hctx; rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PM) data->rq_flags |= RQF_PM; if (blk_queue_io_stat(q)) data->rq_flags |= RQF_IO_STAT; rq->rq_flags = data->rq_flags; if (data->rq_flags & RQF_SCHED_TAGS) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; } rq->timeout = 0; rq->part = NULL; rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif rq->end_io = NULL; rq->end_io_data = NULL; blk_crypto_rq_set_defaults(rq); INIT_LIST_HEAD(&rq->queuelist); /* tag was already set */ WRITE_ONCE(rq->deadline, 0); req_ref_set(rq, 1); if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = data->q->elevator; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); if (e->type->ops.prepare_request) e->type->ops.prepare_request(rq); } return rq; } static inline struct request * __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data) { unsigned int tag, tag_offset; struct blk_mq_tags *tags; struct request *rq; unsigned long tag_mask; int i, nr = 0; tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset); if (unlikely(!tag_mask)) return NULL; tags = blk_mq_tags_from_data(data); for (i = 0; tag_mask; i++) { if (!(tag_mask & (1UL << i))) continue; tag = tag_offset + i; prefetch(tags->static_rqs[tag]); tag_mask &= ~(1UL << i); rq = blk_mq_rq_ctx_init(data, tags, tag); rq_list_add(data->cached_rq, rq); nr++; } if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_add_active_requests(data->hctx, nr); /* caller already holds a reference, add for remainder */ percpu_ref_get_many(&data->q->q_usage_counter, nr - 1); data->nr_tags -= nr; return rq_list_pop(data->cached_rq); } static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) { struct request_queue *q = data->q; u64 alloc_time_ns = 0; struct request *rq; unsigned int tag; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = blk_time_get_ns(); if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); if (q->elevator) { /* * All requests use scheduler tags when an I/O scheduler is * enabled for the queue. */ data->rq_flags |= RQF_SCHED_TAGS; /* * Flush/passthrough requests are special and go directly to the * dispatch list. */ if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH && !blk_op_is_passthrough(data->cmd_flags)) { struct elevator_mq_ops *ops = &q->elevator->type->ops; WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED); data->rq_flags |= RQF_USE_SCHED; if (ops->limit_depth) ops->limit_depth(data->cmd_flags, data); } } else { blk_mq_tag_busy(data->hctx); } if (data->flags & BLK_MQ_REQ_RESERVED) data->rq_flags |= RQF_RESV; /* * Try batched alloc if we want more than 1 tag. */ if (data->nr_tags > 1) { rq = __blk_mq_alloc_requests_batch(data); if (rq) { blk_mq_rq_time_init(rq, alloc_time_ns); return rq; } data->nr_tags = 1; } /* * Waiting allocations only fail because of an inactive hctx. In that * case just retry the hctx assignment and tag allocation as CPU hotplug * should have migrated us to an online CPU by now. */ tag = blk_mq_get_tag(data); if (tag == BLK_MQ_NO_TAG) { if (data->flags & BLK_MQ_REQ_NOWAIT) return NULL; /* * Give up the CPU and sleep for a random short time to * ensure that thread using a realtime scheduling class * are migrated off the CPU, and thus off the hctx that * is going away. */ msleep(3); goto retry; } if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_inc_active_requests(data->hctx); rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag); blk_mq_rq_time_init(rq, alloc_time_ns); return rq; } static struct request *blk_mq_rq_cache_fill(struct request_queue *q, struct blk_plug *plug, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = opf, .nr_tags = plug->nr_ios, .cached_rq = &plug->cached_rq, }; struct request *rq; if (blk_queue_enter(q, flags)) return NULL; plug->nr_ios = 1; rq = __blk_mq_alloc_requests(&data); if (unlikely(!rq)) blk_queue_exit(q); return rq; } static struct request *blk_mq_alloc_cached_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_plug *plug = current->plug; struct request *rq; if (!plug) return NULL; if (rq_list_empty(plug->cached_rq)) { if (plug->nr_ios == 1) return NULL; rq = blk_mq_rq_cache_fill(q, plug, opf, flags); if (!rq) return NULL; } else { rq = rq_list_peek(&plug->cached_rq); if (!rq || rq->q != q) return NULL; if (blk_mq_get_hctx_type(opf) != rq->mq_hctx->type) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; plug->cached_rq = rq_list_next(rq); blk_mq_rq_time_init(rq, 0); } rq->cmd_flags = opf; INIT_LIST_HEAD(&rq->queuelist); return rq; } struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct request *rq; rq = blk_mq_alloc_cached_request(q, opf, flags); if (!rq) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = opf, .nr_tags = 1, }; int ret; ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); rq = __blk_mq_alloc_requests(&data); if (!rq) goto out_queue_exit; } rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); } EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = opf, .nr_tags = 1, }; u64 alloc_time_ns = 0; struct request *rq; unsigned int cpu; unsigned int tag; int ret; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = blk_time_get_ns(); /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) || WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) return ERR_PTR(-EIO); ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); /* * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ ret = -EXDEV; data.hctx = xa_load(&q->hctx_table, hctx_idx); if (!blk_mq_hw_queue_mapped(data.hctx)) goto out_queue_exit; cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); if (q->elevator) data.rq_flags |= RQF_SCHED_TAGS; else blk_mq_tag_busy(data.hctx); if (flags & BLK_MQ_REQ_RESERVED) data.rq_flags |= RQF_RESV; ret = -EWOULDBLOCK; tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) goto out_queue_exit; if (!(data.rq_flags & RQF_SCHED_TAGS)) blk_mq_inc_active_requests(data.hctx); rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag); blk_mq_rq_time_init(rq, alloc_time_ns); rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); static void blk_mq_finish_request(struct request *rq) { struct request_queue *q = rq->q; blk_zone_finish_request(rq); if (rq->rq_flags & RQF_USE_SCHED) { q->elevator->type->ops.finish_request(rq); /* * For postflush request that may need to be * completed twice, we should clear this flag * to avoid double finish_request() on the rq. */ rq->rq_flags &= ~RQF_USE_SCHED; } } static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != BLK_MQ_NO_TAG) { blk_mq_dec_active_requests(hctx); blk_mq_put_tag(hctx->tags, ctx, rq->tag); } if (sched_tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_finish_request(rq); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->disk->bdi); rq_qos_done(q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (req_ref_put_and_test(rq)) __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); void blk_mq_free_plug_rqs(struct blk_plug *plug) { struct request *rq; while ((rq = rq_list_pop(&plug->cached_rq)) != NULL) blk_mq_free_request(rq); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->q->disk ? rq->q->disk->disk_name : "?", (__force unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } static void blk_print_req_error(struct request *req, blk_status_t status) { printk_ratelimited(KERN_ERR "%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", blk_status_to_str(status), req->q->disk ? req->q->disk->disk_name : "?", blk_rq_pos(req), (__force u32)req_op(req), blk_op_str(req_op(req)), (__force u32)(req->cmd_flags & ~REQ_OP_MASK), req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } /* * Fully end IO on a request. Does not support partial completions, or * errors. */ static void blk_complete_request(struct request *req) { const bool is_flush = (req->rq_flags & RQF_FLUSH_SEQ) != 0; int total_bytes = blk_rq_bytes(req); struct bio *bio = req->bio; trace_block_rq_complete(req, BLK_STS_OK, total_bytes); if (!bio) return; if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ) blk_integrity_complete(req, total_bytes); /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ blk_crypto_rq_put_keyslot(req); blk_account_io_completion(req, total_bytes); do { struct bio *next = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); blk_zone_update_request_bio(req, bio); if (!is_flush) bio_endio(bio); bio = next; } while (bio); /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ if (!req->end_io) { req->bio = NULL; req->__data_len = 0; } } /** * blk_update_request - Complete multiple bytes without completing the request * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete for @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function * except in the consistency check at the end of this function. * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { bool is_flush = req->rq_flags & RQF_FLUSH_SEQ; bool quiet = req->rq_flags & RQF_QUIET; int total_bytes; trace_block_rq_complete(req, error, nr_bytes); if (!req->bio) return false; if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) blk_integrity_complete(req, nr_bytes); /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req)) __blk_crypto_rq_put_keyslot(req); if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) && !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); } blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (unlikely(error)) bio->bi_status = error; if (bio_bytes == bio->bi_iter.bi_size) { req->bio = bio->bi_next; } else if (bio_is_zone_append(bio) && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported * as the BIO fragments may end up not being written * sequentially. */ bio->bi_status = BLK_STS_IOERR; } /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); if (unlikely(quiet)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, bio_bytes); /* Don't actually finish bio if it's part of flush sequence */ if (!bio->bi_iter.bi_size) { blk_zone_update_request_bio(req, bio); if (!is_flush) bio_endio(bio); } total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); static inline void blk_account_io_done(struct request *req, u64 now) { trace_block_io_done(req); /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the * containing request is enough. */ if (blk_do_io_stat(req) && req->part && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_local_dec(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } static inline void blk_account_io_start(struct request *req) { trace_block_io_start(req); if (blk_do_io_stat(req)) { /* * All non-passthrough requests are created from a bio with one * exception: when a flush command that is part of a flush sequence * generated by the state machine in blk-flush.c is cloned onto the * lower device by dm-multipath we can get here without a bio. */ if (req->bio) req->part = req->bio->bi_bdev; else req->part = req->q->disk->part0; part_stat_lock(); update_io_ticks(req->part, jiffies, false); part_stat_local_inc(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } static inline void __blk_mq_end_request_acct(struct request *rq, u64 now) { if (rq->rq_flags & RQF_STATS) blk_stat_add(rq, now); blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); } inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_mq_need_time_stamp(rq)) __blk_mq_end_request_acct(rq, blk_time_get_ns()); blk_mq_finish_request(rq); if (rq->end_io) { rq_qos_done(rq->q, rq); if (rq->end_io(rq, error) == RQ_END_IO_FREE) blk_mq_free_request(rq); } else { blk_mq_free_request(rq); } } EXPORT_SYMBOL(__blk_mq_end_request); void blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); __blk_mq_end_request(rq, error); } EXPORT_SYMBOL(blk_mq_end_request); #define TAG_COMP_BATCH 32 static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx, int *tag_array, int nr_tags) { struct request_queue *q = hctx->queue; blk_mq_sub_active_requests(hctx, nr_tags); blk_mq_put_tags(hctx->tags, tag_array, nr_tags); percpu_ref_put_many(&q->q_usage_counter, nr_tags); } void blk_mq_end_request_batch(struct io_comp_batch *iob) { int tags[TAG_COMP_BATCH], nr_tags = 0; struct blk_mq_hw_ctx *cur_hctx = NULL; struct request *rq; u64 now = 0; if (iob->need_ts) now = blk_time_get_ns(); while ((rq = rq_list_pop(&iob->req_list)) != NULL) { prefetch(rq->bio); prefetch(rq->rq_next); blk_complete_request(rq); if (iob->need_ts) __blk_mq_end_request_acct(rq, now); blk_mq_finish_request(rq); rq_qos_done(rq->q, rq); /* * If end_io handler returns NONE, then it still has * ownership of the request. */ if (rq->end_io && rq->end_io(rq, 0) == RQ_END_IO_NONE) continue; WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (!req_ref_put_and_test(rq)) continue; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) { if (cur_hctx) blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags); nr_tags = 0; cur_hctx = rq->mq_hctx; } tags[nr_tags++] = rq->tag; } if (nr_tags) blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags); } EXPORT_SYMBOL_GPL(blk_mq_end_request_batch); static void blk_complete_reqs(struct llist_head *list) { struct llist_node *entry = llist_reverse_order(llist_del_all(list)); struct request *rq, *next; llist_for_each_entry_safe(rq, next, entry, ipi_list) rq->q->mq_ops->complete(rq); } static __latent_entropy void blk_done_softirq(struct softirq_action *h) { blk_complete_reqs(this_cpu_ptr(&blk_cpu_done)); } static int blk_softirq_cpu_dead(unsigned int cpu) { blk_complete_reqs(&per_cpu(blk_cpu_done, cpu)); return 0; } static void __blk_mq_complete_request_remote(void *data) { __raise_softirq_irqoff(BLOCK_SOFTIRQ); } static inline bool blk_mq_complete_need_ipi(struct request *rq) { int cpu = raw_smp_processor_id(); if (!IS_ENABLED(CONFIG_SMP) || !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) return false; /* * With force threaded interrupts enabled, raising softirq from an SMP * function call will always result in waking the ksoftirqd thread. * This is probably worse than completing the request on a different * cache domain. */ if (force_irqthreads()) return false; /* same CPU or cache domain and capacity? Complete locally */ if (cpu == rq->mq_ctx->cpu || (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) && cpus_share_cache(cpu, rq->mq_ctx->cpu) && cpus_equal_capacity(cpu, rq->mq_ctx->cpu))) return false; /* don't try to IPI to an offline CPU */ return cpu_online(rq->mq_ctx->cpu); } static void blk_mq_complete_send_ipi(struct request *rq) { unsigned int cpu; cpu = rq->mq_ctx->cpu; if (llist_add(&rq->ipi_list, &per_cpu(blk_cpu_done, cpu))) smp_call_function_single_async(cpu, &per_cpu(blk_cpu_csd, cpu)); } static void blk_mq_raise_softirq(struct request *rq) { struct llist_head *list; preempt_disable(); list = this_cpu_ptr(&blk_cpu_done); if (llist_add(&rq->ipi_list, list)) raise_softirq(BLOCK_SOFTIRQ); preempt_enable(); } bool blk_mq_complete_request_remote(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* * For request which hctx has only one ctx mapping, * or a polled request, always complete locally, * it's pointless to redirect the completion. */ if ((rq->mq_hctx->nr_ctx == 1 && rq->mq_ctx->cpu == raw_smp_processor_id()) || rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { blk_mq_complete_send_ipi(rq); return true; } if (rq->q->nr_hw_queues == 1) { blk_mq_raise_softirq(rq); return true; } return false; } EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote); /** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed * * Description: * Complete a request by scheduling the ->complete_rq operation. **/ void blk_mq_complete_request(struct request *rq) { if (!blk_mq_complete_request_remote(rq)) rq->q->mq_ops->complete(rq); } EXPORT_SYMBOL(blk_mq_complete_request); /** * blk_mq_start_request - Start processing a request * @rq: Pointer to request to be started * * Function used by device drivers to notify the block layer that a request * is going to be processed now, so blk layer can do proper initializations * such as starting the timeout timer. */ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) && !blk_rq_is_passthrough(rq)) { rq->io_start_time_ns = blk_time_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); blk_add_timer(rq); WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); rq->mq_hctx->tags->rqs[rq->tag] = rq; if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) blk_integrity_prepare(rq); if (rq->bio && rq->bio->bi_opf & REQ_POLLED) WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num); } EXPORT_SYMBOL(blk_mq_start_request); /* * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple * queues. This is important for md arrays to benefit from merging * requests. */ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) { if (plug->multiple_queues) return BLK_MAX_REQUEST_COUNT * 2; return BLK_MAX_REQUEST_COUNT; } static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) { struct request *last = rq_list_peek(&plug->mq_list); if (!plug->rq_count) { trace_block_plug(rq->q); } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || (!blk_queue_nomerges(rq->q) && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_mq_flush_plug_list(plug, false); last = NULL; trace_block_plug(rq->q); } if (!plug->multiple_queues && last && last->q != rq->q) plug->multiple_queues = true; /* * Any request allocated from sched tags can't be issued to * ->queue_rqs() directly */ if (!plug->has_elevator && (rq->rq_flags & RQF_SCHED_TAGS)) plug->has_elevator = true; rq->rq_next = NULL; rq_list_add(&plug->mq_list, rq); plug->rq_count++; } /** * blk_execute_rq_nowait - insert a request to I/O scheduler for execution * @rq: request to insert * @at_head: insert request at head or tail of queue * * Description: * Insert a fully prepared request at the back of the I/O scheduler queue * for execution. Don't wait for completion. * * Note: * This function will invoke @done directly if the queue is dead. */ void blk_execute_rq_nowait(struct request *rq, bool at_head) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); blk_account_io_start(rq); if (current->plug && !at_head) { blk_add_rq_to_plug(current->plug, rq); return; } blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0); blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING); } EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); struct blk_rq_wait { struct completion done; blk_status_t ret; }; static enum rq_end_io_ret blk_end_sync_rq(struct request *rq, blk_status_t ret) { struct blk_rq_wait *wait = rq->end_io_data; wait->ret = ret; complete(&wait->done); return RQ_END_IO_NONE; } bool blk_rq_is_poll(struct request *rq) { if (!rq->mq_hctx) return false; if (rq->mq_hctx->type != HCTX_TYPE_POLL) return false; return true; } EXPORT_SYMBOL_GPL(blk_rq_is_poll); static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { blk_hctx_poll(rq->q, rq->mq_hctx, NULL, 0); cond_resched(); } while (!completion_done(wait)); } /** * blk_execute_rq - insert a request into queue for execution * @rq: request to insert * @at_head: insert request at head or tail of queue * * Description: * Insert a fully prepared request at the back of the I/O scheduler queue * for execution and wait for completion. * Return: The blk_status_t result provided to blk_mq_end_request(). */ blk_status_t blk_execute_rq(struct request *rq, bool at_head) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_rq_wait wait = { .done = COMPLETION_INITIALIZER_ONSTACK(wait.done), }; WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); rq->end_io_data = &wait; rq->end_io = blk_end_sync_rq; blk_account_io_start(rq); blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0); blk_mq_run_hw_queue(hctx, false); if (blk_rq_is_poll(rq)) blk_rq_poll_completion(rq, &wait.done); else blk_wait_io(&wait.done); return wait.ret; } EXPORT_SYMBOL(blk_execute_rq); static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_put_driver_tag(rq); trace_block_rq_requeue(rq); rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); rq->rq_flags &= ~RQF_TIMED_OUT; } } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { struct request_queue *q = rq->q; unsigned long flags; __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); spin_lock_irqsave(&q->requeue_lock, flags); list_add_tail(&rq->queuelist, &q->requeue_list); spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); } EXPORT_SYMBOL(blk_mq_requeue_request); static void blk_mq_requeue_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); LIST_HEAD(flush_list); struct request *rq; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); list_splice_init(&q->flush_list, &flush_list); spin_unlock_irq(&q->requeue_lock); while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); /* * If RQF_DONTPREP ist set, the request has been started by the * driver already and might have driver-specific data allocated * already. Insert it into the hctx dispatch list to avoid * block layer merges for the request. */ if (rq->rq_flags & RQF_DONTPREP) { list_del_init(&rq->queuelist); blk_mq_request_bypass_insert(rq, 0); } else { list_del_init(&rq->queuelist); blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD); } } while (!list_empty(&flush_list)) { rq = list_entry(flush_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_insert_request(rq, 0); } blk_mq_run_hw_queues(q, false); } void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); } EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); static bool blk_is_flush_data_rq(struct request *rq) { return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq); } static bool blk_mq_rq_inflight(struct request *rq, void *priv) { /* * If we find a request that isn't idle we know the queue is busy * as it's checked in the iter. * Return false to stop the iteration. * * In case of queue quiesce, if one flush data request is completed, * don't count it as inflight given the flush sequence is suspended, * and the original flush data request is invisible to driver, just * like other pending requests because of quiesce */ if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) && blk_is_flush_data_rq(rq) && blk_mq_request_completed(rq))) { bool *busy = priv; *busy = true; return false; } return true; } bool blk_mq_queue_inflight(struct request_queue *q) { bool busy = false; blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy); return busy; } EXPORT_SYMBOL_GPL(blk_mq_queue_inflight); static void blk_mq_rq_timed_out(struct request *req) { req->rq_flags |= RQF_TIMED_OUT; if (req->q->mq_ops->timeout) { enum blk_eh_timer_return ret; ret = req->q->mq_ops->timeout(req); if (ret == BLK_EH_DONE) return; WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } blk_add_timer(req); } struct blk_expired_data { bool has_timedout_rq; unsigned long next; unsigned long timeout_start; }; static bool blk_mq_req_expired(struct request *rq, struct blk_expired_data *expired) { unsigned long deadline; if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT) return false; if (rq->rq_flags & RQF_TIMED_OUT) return false; deadline = READ_ONCE(rq->deadline); if (time_after_eq(expired->timeout_start, deadline)) return true; if (expired->next == 0) expired->next = deadline; else if (time_after(expired->next, deadline)) expired->next = deadline; return false; } void blk_mq_put_rq_ref(struct request *rq) { if (is_flush_rq(rq)) { if (rq->end_io(rq, 0) == RQ_END_IO_FREE) blk_mq_free_request(rq); } else if (req_ref_put_and_test(rq)) { __blk_mq_free_request(rq); } } static bool blk_mq_check_expired(struct request *rq, void *priv) { struct blk_expired_data *expired = priv; /* * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot * be reallocated underneath the timeout handler's processing, then * the expire check is reliable. If the request is not expired, then * it was completed and reallocated as a new request after returning * from blk_mq_check_expired(). */ if (blk_mq_req_expired(rq, expired)) { expired->has_timedout_rq = true; return false; } return true; } static bool blk_mq_handle_expired(struct request *rq, void *priv) { struct blk_expired_data *expired = priv; if (blk_mq_req_expired(rq, expired)) blk_mq_rq_timed_out(rq); return true; } static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); struct blk_expired_data expired = { .timeout_start = jiffies, }; struct blk_mq_hw_ctx *hctx; unsigned long i; /* A deadlock might occur if a request is stuck requiring a * timeout at the same time a queue freeze is waiting * completion, since the timeout code would not be able to * acquire the queue reference here. * * That's why we don't use blk_queue_enter here; instead, we use * percpu_ref_tryget directly, because we need to be able to * obtain a reference even in the short window between the queue * starting to freeze, by dropping the first reference in * blk_freeze_queue_start, and the moment the last request is * consumed, marked by the instant q_usage_counter reaches * zero. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; /* check if there is any timed-out request */ blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &expired); if (expired.has_timedout_rq) { /* * Before walking tags, we must ensure any submit started * before the current time has finished. Since the submit * uses srcu or rcu, wait for a synchronization point to * ensure all running submits have finished */ blk_mq_wait_quiesce_done(q->tag_set); expired.next = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_handle_expired, &expired); } if (expired.next != 0) { mod_timer(&q->timeout, expired.next); } else { /* * Request timeouts are handled as a forward rolling timer. If * we end up here it means that no requests are pending and * also that no request has been pending for a while. Mark * each hctx as idle. */ queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); } } blk_queue_exit(q); } struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; }; static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct flush_busy_ctx_data *flush_data = data; struct blk_mq_hw_ctx *hctx = flush_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); list_splice_tail_init(&ctx->rq_lists[type], flush_data->list); sbitmap_clear_bit(sb, bitnr); spin_unlock(&ctx->lock); return true; } /* * Process software queues that have been marked busy, splicing them * to the for-dispatch */ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) { struct flush_busy_ctx_data data = { .hctx = hctx, .list = list, }; sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data); } EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs); struct dispatch_rq_data { struct blk_mq_hw_ctx *hctx; struct request *rq; }; static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct dispatch_rq_data *dispatch_data = data; struct blk_mq_hw_ctx *hctx = dispatch_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next); list_del_init(&dispatch_data->rq->queuelist); if (list_empty(&ctx->rq_lists[type])) sbitmap_clear_bit(sb, bitnr); } spin_unlock(&ctx->lock); return !dispatch_data->rq; } struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start) { unsigned off = start ? start->index_hw[hctx->type] : 0; struct dispatch_rq_data data = { .hctx = hctx, .rq = NULL, }; __sbitmap_for_each_set(&hctx->ctx_map, off, dispatch_rq_from_ctx, &data); return data.rq; } bool __blk_mq_alloc_driver_tag(struct request *rq) { struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; int tag; blk_mq_tag_busy(rq->mq_hctx); if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { bt = &rq->mq_hctx->tags->breserved_tags; tag_offset = 0; } else { if (!hctx_may_queue(rq->mq_hctx, bt)) return false; } tag = __sbitmap_queue_get(bt); if (tag == BLK_MQ_NO_TAG) return false; rq->tag = tag + tag_offset; blk_mq_inc_active_requests(rq->mq_hctx); return true; } static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx; hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { struct sbitmap_queue *sbq; list_del_init(&wait->entry); sbq = &hctx->tags->bitmap_tags; atomic_dec(&sbq->ws_active); } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); return 1; } /* * Mark us waiting for a tag. For shared tags, this involves hooking us into * the tag wakeups. For non-shared tags, we can simply mark us needing a * restart. For both cases, take care to check the condition again after * marking us as waiting. */ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct sbitmap_queue *sbq; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(blk_mq_is_shared_tags(hctx->flags))) { blk_mq_sched_mark_restart_hctx(hctx); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. * * Don't clear RESTART here, someone else could have set it. * At most this will cost an extra queue run. */ return blk_mq_get_driver_tag(rq); } wait = &hctx->dispatch_wait; if (!list_empty_careful(&wait->entry)) return false; if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) sbq = &hctx->tags->breserved_tags; else sbq = &hctx->tags->bitmap_tags; wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); /* * Add one explicit barrier since blk_mq_get_driver_tag() may * not imply barrier in case of failure. * * Order adding us to wait queue and allocating driver tag. * * The pair is the one implied in sbitmap_queue_wake_up() which * orders clearing sbitmap tag bits and waitqueue_active() in * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless * * Otherwise, re-order of adding wait queue and getting driver tag * may cause __sbitmap_queue_wake_up() to wake up nothing because * the waitqueue_active() may not observe us in wait queue. */ smp_mb(); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. */ ret = blk_mq_get_driver_tag(rq); if (!ret) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } /* * We got a tag, remove ourselves from the wait queue to ensure * someone else gets the wakeup. */ list_del_init(&wait->entry); atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return true; } #define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8 #define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4 /* * Update dispatch busy with the Exponential Weighted Moving Average(EWMA): * - EWMA is one simple way to compute running average value * - weight(7/8 and 1/8) is applied so that it can decrease exponentially * - take 4 as factor for avoiding to get too small(0) result, and this * factor doesn't matter because EWMA decreases exponentially */ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; ewma = hctx->dispatch_busy; if (!ewma && !busy) return; ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1; if (busy) ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR; ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT; hctx->dispatch_busy = ewma; } #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ static void blk_mq_handle_dev_resource(struct request *rq, struct list_head *list) { list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); } enum prep_dispatch { PREP_DISPATCH_OK, PREP_DISPATCH_NO_TAG, PREP_DISPATCH_NO_BUDGET, }; static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, bool need_budget) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; int budget_token = -1; if (need_budget) { budget_token = blk_mq_get_dispatch_budget(rq->q); if (budget_token < 0) { blk_mq_put_driver_tag(rq); return PREP_DISPATCH_NO_BUDGET; } blk_mq_set_rq_budget_token(rq, budget_token); } if (!blk_mq_get_driver_tag(rq)) { /* * The initial allocation attempt failed, so we need to * rerun the hardware queue when a tag is freed. The * waitqueue takes care of that. If the queue is run * before we add this entry back on the dispatch list, * we'll re-run it below. */ if (!blk_mq_mark_tag_wait(hctx, rq)) { /* * All budgets not got from this function will be put * together during handling partial dispatch */ if (need_budget) blk_mq_put_dispatch_budget(rq->q, budget_token); return PREP_DISPATCH_NO_TAG; } } return PREP_DISPATCH_OK; } /* release all allocated budgets before calling to blk_mq_dispatch_rq_list */ static void blk_mq_release_budgets(struct request_queue *q, struct list_head *list) { struct request *rq; list_for_each_entry(rq, list, queuelist) { int budget_token = blk_mq_get_rq_budget_token(rq); if (budget_token >= 0) blk_mq_put_dispatch_budget(q, budget_token); } } /* * blk_mq_commit_rqs will notify driver using bd->last that there is no * more requests. (See comment in struct blk_mq_ops for commit_rqs for * details) * Attention, we should explicitly call this in unusual cases: * 1) did not queue everything initially scheduled to queue * 2) the last attempt to queue a request failed */ static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued, bool from_schedule) { if (hctx->queue->mq_ops->commit_rqs && queued) { trace_block_unplug(hctx->queue, queued, !from_schedule); hctx->queue->mq_ops->commit_rqs(hctx); } } /* * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, unsigned int nr_budgets) { enum prep_dispatch prep; struct request_queue *q = hctx->queue; struct request *rq; int queued; blk_status_t ret = BLK_STS_OK; bool needs_resource = false; if (list_empty(list)) return false; /* * Now process all the entries, sending them to the driver. */ queued = 0; do { struct blk_mq_queue_data bd; rq = list_first_entry(list, struct request, queuelist); WARN_ON_ONCE(hctx != rq->mq_hctx); prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets); if (prep != PREP_DISPATCH_OK) break; list_del_init(&rq->queuelist); bd.rq = rq; bd.last = list_empty(list); /* * once the request is queued to lld, no need to cover the * budget any more */ if (nr_budgets) nr_budgets--; ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: needs_resource = true; fallthrough; case BLK_STS_DEV_RESOURCE: blk_mq_handle_dev_resource(rq, list); goto out; default: blk_mq_end_request(rq, ret); } } while (!list_empty(list)); out: /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ if (!list_empty(list) || ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. */ if (!list_empty(list)) { bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) || blk_mq_is_shared_tags(hctx->flags)); if (nr_budgets) blk_mq_release_budgets(q, list); spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* * Order adding requests to hctx->dispatch and checking * SCHED_RESTART flag. The pair of this smp_mb() is the one * in blk_mq_sched_restart(). Avoid restart code path to * miss the new added requests to hctx->dispatch, meantime * SCHED_RESTART is observed here. */ smp_mb(); /* * If SCHED_RESTART was set by the caller of this function and * it is no longer set that means that it was cleared by another * thread and hence that a queue rerun is needed. * * If 'no_tag' is set, that means that we failed getting * a driver tag with an I/O scheduler attached. If our dispatch * waitqueue is no longer active, ensure that we run the queue * AFTER adding our entries back to the list. * * If no I/O scheduler has been configured it is possible that * the hardware queue got stopped and restarted before requests * were pushed back onto the dispatch list. Rerun the queue to * avoid starvation. Notes: * - blk_mq_run_hw_queue() checks whether or not a queue has * been stopped before rerunning a queue. * - Some but not all block drivers stop a queue before * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq * and dm-rq. * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do * similar if we couldn't get budget or couldn't lock a zone * and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (prep == PREP_DISPATCH_NO_BUDGET) needs_resource = true; if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); else if (needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); return false; } blk_mq_update_dispatch_busy(hctx, false); return true; } static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx) { int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(hctx->cpumask); return cpu; } /* * ->next_cpu is always calculated from hctx->cpumask, so simply use * it for speeding up the check */ static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx) { return hctx->next_cpu >= nr_cpu_ids; } /* * It'd be great if the workqueue API had a way to pass * in a mask and had some smarts for more clever placement. * For now we just round-robin here, switching for every * BLK_MQ_CPU_WORK_BATCH queued items. */ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { bool tried = false; int next_cpu = hctx->next_cpu; /* Switch to unbound if no allowable CPUs in this hctx */ if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx)) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { select_cpu: next_cpu = cpumask_next_and(next_cpu, hctx->cpumask, cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } /* * Do unbound schedule if we can't find a online CPU for this hctx, * and it should only happen in the path of handling CPU DEAD. */ if (!cpu_online(next_cpu)) { if (!tried) { tried = true; goto select_cpu; } /* * Make sure to re-select CPU next time once after CPUs * in hctx->cpumask become online again. */ hctx->next_cpu = next_cpu; hctx->next_cpu_batch = 1; return WORK_CPU_UNBOUND; } hctx->next_cpu = next_cpu; return next_cpu; } /** * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously. * @hctx: Pointer to the hardware queue to run. * @msecs: Milliseconds of delay to wait before running the queue. * * Run a hardware queue asynchronously with a delay of @msecs. */ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { if (unlikely(blk_mq_hctx_stopped(hctx))) return; kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); /** * blk_mq_run_hw_queue - Start to run a hardware queue. * @hctx: Pointer to the hardware queue to run. * @async: If we want to run the queue asynchronously. * * Check if the request queue is not in a quiesced state and if there are * pending requests to be sent. If this is true, run the queue to send requests * to hardware. */ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { bool need_run; /* * We can't run the queue inline with interrupts disabled. */ WARN_ON_ONCE(!async && in_interrupt()); might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING); /* * When queue is quiesced, we may be switching io scheduler, or * updating nr_hw_queues, or other things, and we can't run queue * any more, even __blk_mq_hctx_has_pending() can't be called safely. * * And queue will be rerun in blk_mq_unquiesce_queue() if it is * quiesced. */ __blk_mq_run_dispatch_ops(hctx->queue, false, need_run = !blk_queue_quiesced(hctx->queue) && blk_mq_hctx_has_pending(hctx)); if (!need_run) return; if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) { blk_mq_delay_run_hw_queue(hctx, 0); return; } blk_mq_run_dispatch_ops(hctx->queue, blk_mq_sched_dispatch_requests(hctx)); } EXPORT_SYMBOL(blk_mq_run_hw_queue); /* * Return prefered queue to dispatch from (if any) for non-mq aware IO * scheduler. */ static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q) { struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); /* * If the IO scheduler does not respect hardware queues when * dispatching, we just don't bother with multiple HW queues and * dispatch from hctx for the current CPU since running multiple queues * just causes lock contention inside the scheduler and pointless cache * bouncing. */ struct blk_mq_hw_ctx *hctx = ctx->hctxs[HCTX_TYPE_DEFAULT]; if (!blk_mq_hctx_stopped(hctx)) return hctx; return NULL; } /** * blk_mq_run_hw_queues - Run all hardware queues in a request queue. * @q: Pointer to the request queue to run. * @async: If we want to run the queue asynchronously. */ void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx, *sq_hctx; unsigned long i; sq_hctx = NULL; if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; /* * Dispatch from this hctx either if there's no hctx preferred * by IO scheduler or if it has requests that bypass the * scheduler. */ if (!sq_hctx || sq_hctx == hctx || !list_empty_careful(&hctx->dispatch)) blk_mq_run_hw_queue(hctx, async); } } EXPORT_SYMBOL(blk_mq_run_hw_queues); /** * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously. * @q: Pointer to the request queue to run. * @msecs: Milliseconds of delay to wait before running the queues. */ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) { struct blk_mq_hw_ctx *hctx, *sq_hctx; unsigned long i; sq_hctx = NULL; if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; /* * If there is already a run_work pending, leave the * pending delay untouched. Otherwise, a hctx can stall * if another hctx is re-delaying the other's work * before the work executes. */ if (delayed_work_pending(&hctx->run_work)) continue; /* * Dispatch from this hctx either if there's no hctx preferred * by IO scheduler or if it has requests that bypass the * scheduler. */ if (!sq_hctx || sq_hctx == hctx || !list_empty_careful(&hctx->dispatch)) blk_mq_delay_run_hw_queue(hctx, msecs); } } EXPORT_SYMBOL(blk_mq_delay_run_hw_queues); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queue() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { cancel_delayed_work(&hctx->run_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); } EXPORT_SYMBOL(blk_mq_stop_hw_queue); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queues() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_stop_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_stop_hw_queues); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING); } EXPORT_SYMBOL(blk_mq_start_hw_queue); void blk_mq_start_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_start_hw_queues); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { if (!blk_mq_hctx_stopped(hctx)) return; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, async); } EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_stopped_hw_queue(hctx, async || (hctx->flags & BLK_MQ_F_BLOCKING)); } EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues); static void blk_mq_run_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work); blk_mq_run_dispatch_ops(hctx->queue, blk_mq_sched_dispatch_requests(hctx)); } /** * blk_mq_request_bypass_insert - Insert a request at dispatch list. * @rq: Pointer to request to be inserted. * @flags: BLK_MQ_INSERT_* * * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); if (flags & BLK_MQ_INSERT_AT_HEAD) list_add(&rq->queuelist, &hctx->dispatch); else list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); } static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list, bool run_queue_async) { struct request *rq; enum hctx_type type = hctx->type; /* * Try to issue requests directly if the hw queue isn't busy to save an * extra enqueue & dequeue to the sw queue. */ if (!hctx->dispatch_busy && !run_queue_async) { blk_mq_run_dispatch_ops(hctx->queue, blk_mq_try_issue_list_directly(hctx, list)); if (list_empty(list)) goto out; } /* * preemption doesn't flush plug list, so it's possible ctx->cpu is * offline now */ list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx); trace_block_rq_insert(rq); if (rq->cmd_flags & REQ_NOWAIT) run_queue_async = true; } spin_lock(&ctx->lock); list_splice_tail_init(list, &ctx->rq_lists[type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); out: blk_mq_run_hw_queue(hctx, run_queue_async); } static void blk_mq_insert_request(struct request *rq, blk_insert_t flags) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (blk_rq_is_passthrough(rq)) { /* * Passthrough request have to be added to hctx->dispatch * directly. The device may be in a situation where it can't * handle FS request, and always returns BLK_STS_RESOURCE for * them, which gets them added to hctx->dispatch. * * If a passthrough request is required to unblock the queues, * and it is added to the scheduler queue, there is no chance to * dispatch it given we prioritize requests in hctx->dispatch. */ blk_mq_request_bypass_insert(rq, flags); } else if (req_op(rq) == REQ_OP_FLUSH) { /* * Firstly normal IO request is inserted to scheduler queue or * sw queue, meantime we add flush request to dispatch queue( * hctx->dispatch) directly and there is at most one in-flight * flush request for each hw queue, so it doesn't matter to add * flush request to tail or front of the dispatch queue. * * Secondly in case of NCQ, flush request belongs to non-NCQ * command, and queueing it will fail when there is any * in-flight normal IO request(NCQ command). When adding flush * rq to the front of hctx->dispatch, it is easier to introduce * extra time to flush rq's latency because of S_SCHED_RESTART * compared with adding to the tail of dispatch queue, then * chance of flush merge is increased, and less flush requests * will be issued to controller. It is observed that ~10% time * is saved in blktests block/004 on disk attached to AHCI/NCQ * drive when adding flush rq to the front of hctx->dispatch. * * Simply queue flush rq to the front of hctx->dispatch so that * intensive flush workloads can benefit in case of NCQ HW. */ blk_mq_request_bypass_insert(rq, BLK_MQ_INSERT_AT_HEAD); } else if (q->elevator) { LIST_HEAD(list); WARN_ON_ONCE(rq->tag != BLK_MQ_NO_TAG); list_add(&rq->queuelist, &list); q->elevator->type->ops.insert_requests(hctx, &list, flags); } else { trace_block_rq_insert(rq); spin_lock(&ctx->lock); if (flags & BLK_MQ_INSERT_AT_HEAD) list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]); else list_add_tail(&rq->queuelist, &ctx->rq_lists[hctx->type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); } } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { int err; if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; rq->__sector = bio->bi_iter.bi_sector; rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); WARN_ON_ONCE(err); blk_account_io_start(rq); } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, bool last) { struct request_queue *q = rq->q; struct blk_mq_queue_data bd = { .rq = rq, .last = last, }; blk_status_t ret; /* * For OK queue, we are done. For error, caller may kill it. * Any other error (busy), just add it to our list as we * previously would have done. */ ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: blk_mq_update_dispatch_busy(hctx, false); break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_update_dispatch_busy(hctx, true); __blk_mq_requeue_request(rq); break; default: blk_mq_update_dispatch_busy(hctx, false); break; } return ret; } static bool blk_mq_get_budget_and_tag(struct request *rq) { int budget_token; budget_token = blk_mq_get_dispatch_budget(rq->q); if (budget_token < 0) return false; blk_mq_set_rq_budget_token(rq, budget_token); if (!blk_mq_get_driver_tag(rq)) { blk_mq_put_dispatch_budget(rq->q, budget_token); return false; } return true; } /** * blk_mq_try_issue_directly - Try to send a request directly to device driver. * @hctx: Pointer of the associated hardware queue. * @rq: Pointer to request to be sent. * * If the device has enough resources to accept a new request now, send the * request directly to device driver. Else, insert at hctx->dispatch queue, so * we can try send it another time in the future. Requests inserted at this * queue have higher priority. */ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_status_t ret; if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); return; } if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, rq->cmd_flags & REQ_NOWAIT); return; } ret = __blk_mq_issue_directly(hctx, rq, true); switch (ret) { case BLK_STS_OK: break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); blk_mq_run_hw_queue(hctx, false); break; default: blk_mq_end_request(rq, ret); break; } } static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); return BLK_STS_OK; } if (!blk_mq_get_budget_and_tag(rq)) return BLK_STS_RESOURCE; return __blk_mq_issue_directly(hctx, rq, last); } static void blk_mq_plug_issue_direct(struct blk_plug *plug) { struct blk_mq_hw_ctx *hctx = NULL; struct request *rq; int queued = 0; blk_status_t ret = BLK_STS_OK; while ((rq = rq_list_pop(&plug->mq_list))) { bool last = rq_list_empty(plug->mq_list); if (hctx != rq->mq_hctx) { if (hctx) { blk_mq_commit_rqs(hctx, queued, false); queued = 0; } hctx = rq->mq_hctx; } ret = blk_mq_request_issue_directly(rq, last); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); blk_mq_run_hw_queue(hctx, false); goto out; default: blk_mq_end_request(rq, ret); break; } } out: if (ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); } static void __blk_mq_flush_plug_list(struct request_queue *q, struct blk_plug *plug) { if (blk_queue_quiesced(q)) return; q->mq_ops->queue_rqs(&plug->mq_list); } static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) { struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct request *requeue_list = NULL; struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; bool is_passthrough = false; LIST_HEAD(list); do { struct request *rq = rq_list_pop(&plug->mq_list); if (!this_hctx) { this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; is_passthrough = blk_rq_is_passthrough(rq); } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx || is_passthrough != blk_rq_is_passthrough(rq)) { rq_list_add_tail(&requeue_lastp, rq); continue; } list_add(&rq->queuelist, &list); depth++; } while (!rq_list_empty(plug->mq_list)); plug->mq_list = requeue_list; trace_block_unplug(this_hctx->queue, depth, !from_sched); percpu_ref_get(&this_hctx->queue->q_usage_counter); /* passthrough requests should never be issued to the I/O scheduler */ if (is_passthrough) { spin_lock(&this_hctx->lock); list_splice_tail_init(&list, &this_hctx->dispatch); spin_unlock(&this_hctx->lock); blk_mq_run_hw_queue(this_hctx, from_sched); } else if (this_hctx->queue->elevator) { this_hctx->queue->elevator->type->ops.insert_requests(this_hctx, &list, 0); blk_mq_run_hw_queue(this_hctx, from_sched); } else { blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched); } percpu_ref_put(&this_hctx->queue->q_usage_counter); } void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct request *rq; /* * We may have been called recursively midway through handling * plug->mq_list via a schedule() in the driver's queue_rq() callback. * To avoid mq_list changing under our feet, clear rq_count early and * bail out specifically if rq_count is 0 rather than checking * whether the mq_list is empty. */ if (plug->rq_count == 0) return; plug->rq_count = 0; if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) { struct request_queue *q; rq = rq_list_peek(&plug->mq_list); q = rq->q; /* * Peek first request and see if we have a ->queue_rqs() hook. * If we do, we can dispatch the whole plug list in one go. We * already know at this point that all requests belong to the * same queue, caller must ensure that's the case. */ if (q->mq_ops->queue_rqs) { blk_mq_run_dispatch_ops(q, __blk_mq_flush_plug_list(q, plug)); if (rq_list_empty(plug->mq_list)) return; } blk_mq_run_dispatch_ops(q, blk_mq_plug_issue_direct(plug)); if (rq_list_empty(plug->mq_list)) return; } do { blk_mq_dispatch_plug_list(plug, from_schedule); } while (!rq_list_empty(plug->mq_list)); } static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; blk_status_t ret = BLK_STS_OK; while (!list_empty(list)) { struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); if (list_empty(list)) blk_mq_run_hw_queue(hctx, false); goto out; default: blk_mq_end_request(rq, ret); break; } } out: if (ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); } static bool blk_mq_attempt_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { if (!blk_queue_nomerges(q) && bio_mergeable(bio)) { if (blk_attempt_plug_merge(q, bio, nr_segs)) return true; if (blk_mq_sched_bio_merge(q, bio, nr_segs)) return true; } return false; } static struct request *blk_mq_get_new_requests(struct request_queue *q, struct blk_plug *plug, struct bio *bio, unsigned int nsegs) { struct blk_mq_alloc_data data = { .q = q, .nr_tags = 1, .cmd_flags = bio->bi_opf, }; struct request *rq; rq_qos_throttle(q, bio); if (plug) { data.nr_tags = plug->nr_ios; plug->nr_ios = 1; data.cached_rq = &plug->cached_rq; } rq = __blk_mq_alloc_requests(&data); if (rq) return rq; rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); return NULL; } /* * Check if there is a suitable cached request and return it. */ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug, struct request_queue *q, blk_opf_t opf) { enum hctx_type type = blk_mq_get_hctx_type(opf); struct request *rq; if (!plug) return NULL; rq = rq_list_peek(&plug->cached_rq); if (!rq || rq->q != q) return NULL; if (type != rq->mq_hctx->type && (type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT)) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; return rq; } static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug, struct bio *bio) { WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); /* * If any qos ->throttle() end up blocking, we will have flushed the * plug and hence killed the cached_rq list as well. Pop this entry * before we throttle. */ plug->cached_rq = rq_list_next(rq); rq_qos_throttle(rq->q, bio); blk_mq_rq_time_init(rq, 0); rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); } static bool bio_unaligned(const struct bio *bio, struct request_queue *q) { unsigned int bs_mask = queue_logical_block_size(q) - 1; /* .bi_sector of any zero sized bio need to be initialized */ if ((bio->bi_iter.bi_size & bs_mask) || ((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask)) return true; return false; } /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. * * Builds up a request structure from @q and @bio and send to the device. The * request may not be queued directly to hardware if: * * This request can be merged with another one * * We want to place request at plug queue for possible future merging * * There is an IO scheduler active at this queue * * It will not queue the request if there is an error with the bio, or at the * request creation. */ void blk_mq_submit_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blk_plug *plug = current->plug; const int is_sync = op_is_sync(bio->bi_opf); struct blk_mq_hw_ctx *hctx; unsigned int nr_segs = 1; struct request *rq; blk_status_t ret; /* * If the plug has a cached request for this queue, try to use it. */ rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf); /* * A BIO that was released from a zone write plug has already been * through the preparation in this function, already holds a reference * on the queue usage counter, and is the only write BIO in-flight for * the target zone. Go straight to preparing a request for it. */ if (bio_zone_write_plugging(bio)) { nr_segs = bio->__bi_nr_segments; if (rq) blk_queue_exit(q); goto new_request; } bio = blk_queue_bounce(bio, q); /* * The cached request already holds a q_usage_counter reference and we * don't have to acquire a new one if we use it. */ if (!rq) { if (unlikely(bio_queue_enter(bio))) return; } /* * Device reconfiguration may change logical block size, so alignment * check has to be done with queue usage counter held */ if (unlikely(bio_unaligned(bio, q))) { bio_io_error(bio); goto queue_exit; } if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); if (!bio) goto queue_exit; } if (!bio_integrity_prep(bio)) goto queue_exit; if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) goto queue_exit; if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs)) goto queue_exit; new_request: if (!rq) { rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); if (unlikely(!rq)) goto queue_exit; } else { blk_mq_use_cached_rq(rq, plug, bio); } trace_block_getrq(bio); rq_qos_track(q, rq, bio); blk_mq_bio_to_request(rq, bio, nr_segs); ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); blk_mq_free_request(rq); return; } if (bio_zone_write_plugging(bio)) blk_zone_write_plug_init_request(rq); if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq)) return; if (plug) { blk_add_rq_to_plug(plug, rq); return; } hctx = rq->mq_hctx; if ((rq->rq_flags & RQF_USE_SCHED) || (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, true); } else { blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq)); } return; queue_exit: /* * Don't drop the queue reference if we were trying to use a cached * request and thus didn't acquire one. */ if (!rq) blk_queue_exit(q); } #ifdef CONFIG_BLK_MQ_STACKING /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request *rq) { struct request_queue *q = rq->q; unsigned int max_sectors = blk_queue_get_max_sectors(rq); unsigned int max_segments = blk_rq_get_max_segments(rq); blk_status_t ret; if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * The queue settings related to segment counting may differ from the * original queue. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > max_segments) { printk(KERN_ERR "%s: over max segments limit. (%u > %u)\n", __func__, rq->nr_phys_segments, max_segments); return BLK_STS_IOERR; } if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) return ret; blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ blk_mq_run_dispatch_ops(q, ret = blk_mq_request_issue_directly(rq, true)); if (ret) blk_account_io_done(rq, blk_time_get_ns()); return ret; } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio, *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_alloc_clone(rq->q->disk->part0, bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) goto free_and_out; if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } bio = NULL; } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; rq->write_hint = rq_src->write_hint; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: if (bio) bio_put(bio); blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); #endif /* CONFIG_BLK_MQ_STACKING */ /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); static size_t order_to_size(unsigned int order) { return (size_t)PAGE_SIZE << order; } /* called before freeing request pool in @tags */ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags, struct blk_mq_tags *tags) { struct page *page; unsigned long flags; /* * There is no need to clear mapping if driver tags is not initialized * or the mapping belongs to the driver tags. */ if (!drv_tags || drv_tags == tags) return; list_for_each_entry(page, &tags->page_list, lru) { unsigned long start = (unsigned long)page_address(page); unsigned long end = start + order_to_size(page->private); int i; for (i = 0; i < drv_tags->nr_tags; i++) { struct request *rq = drv_tags->rqs[i]; unsigned long rq_addr = (unsigned long)rq; if (rq_addr >= start && rq_addr < end) { WARN_ON_ONCE(req_ref_read(rq) != 0); cmpxchg(&drv_tags->rqs[i], rq, NULL); } } } /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ spin_lock_irqsave(&drv_tags->lock, flags); spin_unlock_irqrestore(&drv_tags->lock, flags); } void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct blk_mq_tags *drv_tags; struct page *page; if (list_empty(&tags->page_list)) return; if (blk_mq_is_shared_tags(set->flags)) drv_tags = set->shared_tags; else drv_tags = set->tags[hctx_idx]; if (tags->static_rqs && set->ops->exit_request) { int i; for (i = 0; i < tags->nr_tags; i++) { struct request *rq = tags->static_rqs[i]; if (!rq) continue; set->ops->exit_request(set, rq, hctx_idx); tags->static_rqs[i] = NULL; } } blk_mq_clear_rq_mapping(drv_tags, tags); while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); /* * Remove kmemleak object previously allocated in * blk_mq_alloc_rqs(). */ kmemleak_free(page_address(page)); __free_pages(page, page->private); } } void blk_mq_free_rq_map(struct blk_mq_tags *tags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; blk_mq_free_tags(tags); } static enum hctx_type hctx_idx_to_type(struct blk_mq_tag_set *set, unsigned int hctx_idx) { int i; for (i = 0; i < set->nr_maps; i++) { unsigned int start = set->map[i].queue_offset; unsigned int end = start + set->map[i].nr_queues; if (hctx_idx >= start && hctx_idx < end) break; } if (i >= set->nr_maps) i = HCTX_TYPE_DEFAULT; return i; } static int blk_mq_get_hctx_node(struct blk_mq_tag_set *set, unsigned int hctx_idx) { enum hctx_type type = hctx_idx_to_type(set, hctx_idx); return blk_mq_hw_queue_to_node(&set->map[type], hctx_idx); } static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags) { int node = blk_mq_get_hctx_node(set, hctx_idx); struct blk_mq_tags *tags; if (node == NUMA_NO_NODE) node = set->numa_node; tags = blk_mq_init_tags(nr_tags, reserved_tags, node, BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); if (!tags) return NULL; tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) goto err_free_tags; tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->static_rqs) goto err_free_rqs; return tags; err_free_rqs: kfree(tags->rqs); err_free_tags: blk_mq_free_tags(tags); return NULL; } static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { int ret; if (set->ops->init_request) { ret = set->ops->init_request(set, rq, hctx_idx, node); if (ret) return ret; } WRITE_ONCE(rq->state, MQ_RQ_IDLE); return 0; } static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth) { unsigned int i, j, entries_per_page, max_order = 4; int node = blk_mq_get_hctx_node(set, hctx_idx); size_t rq_size, left; if (node == NUMA_NO_NODE) node = set->numa_node; INIT_LIST_HEAD(&tags->page_list); /* * rq_size is the size of the request plus driver payload, rounded * to the cacheline size */ rq_size = round_up(sizeof(struct request) + set->cmd_size, cache_line_size()); left = rq_size * depth; for (i = 0; i < depth; ) { int this_order = max_order; struct page *page; int to_do; void *p; while (this_order && left < order_to_size(this_order - 1)) this_order--; do { page = alloc_pages_node(node, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; if (!this_order--) break; if (order_to_size(this_order) < rq_size) break; } while (1); if (!page) goto fail; page->private = this_order; list_add_tail(&page->lru, &tags->page_list); p = page_address(page); /* * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, depth - i); left -= to_do * rq_size; for (j = 0; j < to_do; j++) { struct request *rq = p; tags->static_rqs[i] = rq; if (blk_mq_init_request(set, rq, hctx_idx, node)) { tags->static_rqs[i] = NULL; goto fail; } p += rq_size; i++; } } return 0; fail: blk_mq_free_rqs(set, tags, hctx_idx); return -ENOMEM; } struct rq_iter_data { struct blk_mq_hw_ctx *hctx; bool has_rq; }; static bool blk_mq_has_request(struct request *rq, void *data) { struct rq_iter_data *iter_data = data; if (rq->mq_hctx != iter_data->hctx) return true; iter_data->has_rq = true; return false; } static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->sched_tags ? hctx->sched_tags : hctx->tags; struct rq_iter_data data = { .hctx = hctx, }; blk_mq_all_tag_iter(tags, blk_mq_has_request, &data); return data.has_rq; } static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx, unsigned int this_cpu) { enum hctx_type type = hctx->type; int cpu; /* * hctx->cpumask has to rule out isolated CPUs, but userspace still * might submit IOs on these isolated CPUs, so use the queue map to * check if all CPUs mapped to this hctx are offline */ for_each_online_cpu(cpu) { struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue, type, cpu); if (h != hctx) continue; /* this hctx has at least one online CPU */ if (this_cpu != cpu) return true; } return false; } static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); if (blk_mq_hctx_has_online_cpu(hctx, cpu)) return 0; /* * Prevent new request from being allocated on the current hctx. * * The smp_mb__after_atomic() Pairs with the implied barrier in * test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is * seen once we return from the tag allocator. */ set_bit(BLK_MQ_S_INACTIVE, &hctx->state); smp_mb__after_atomic(); /* * Try to grab a reference to the queue and wait for any outstanding * requests. If we could not grab a reference the queue has been * frozen and there are no requests. */ if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) { while (blk_mq_hctx_has_requests(hctx)) msleep(5); percpu_ref_put(&hctx->queue->q_usage_counter); } return 0; } /* * Check if one CPU is mapped to the specified hctx * * Isolated CPUs have been ruled out from hctx->cpumask, which is supposed * to be used for scheduling kworker only. For other usage, please call this * helper for checking if one CPU belongs to the specified hctx */ static bool blk_mq_cpu_mapped_to_hctx(unsigned int cpu, const struct blk_mq_hw_ctx *hctx) { struct blk_mq_hw_ctx *mapped_hctx = blk_mq_map_queue_type(hctx->queue, hctx->type, cpu); return mapped_hctx == hctx; } static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); if (blk_mq_cpu_mapped_to_hctx(cpu, hctx)) clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); return 0; } /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it * gets run. */ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); if (!blk_mq_cpu_mapped_to_hctx(cpu, hctx)) return 0; ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { list_splice_init(&ctx->rq_lists[type], &tmp); blk_mq_hctx_clear_pending(hctx, ctx); } spin_unlock(&ctx->lock); if (list_empty(&tmp)) return 0; spin_lock(&hctx->lock); list_splice_tail_init(&tmp, &hctx->dispatch); spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); return 0; } static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { if (!(hctx->flags & BLK_MQ_F_STACKING)) cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } /* * Before freeing hw queue, clearing the flush request reference in * tags->rqs[] for avoiding potential UAF. */ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, unsigned int queue_depth, struct request *flush_rq) { int i; unsigned long flags; /* The hw queue may not be mapped yet */ if (!tags) return; WARN_ON_ONCE(req_ref_read(flush_rq) != 0); for (i = 0; i < queue_depth; i++) cmpxchg(&tags->rqs[i], flush_rq, NULL); /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ spin_lock_irqsave(&tags->lock, flags); spin_unlock_irqrestore(&tags->lock, flags); } /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { struct request *flush_rq = hctx->fq->flush_rq; if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); if (blk_queue_init_done(q)) blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], set->queue_depth, flush_rq); if (set->ops->exit_request) set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); blk_mq_remove_cpuhp(hctx); xa_erase(&q->hctx_table, hctx_idx); spin_lock(&q->unused_hctx_lock); list_add(&hctx->hctx_list, &q->unused_hctx_list); spin_unlock(&q->unused_hctx_lock); } static void blk_mq_exit_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set, int nr_queue) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; blk_mq_exit_hctx(q, set, hctx, i); } } static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) { hctx->queue_num = hctx_idx; if (!(hctx->flags & BLK_MQ_F_STACKING)) cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto unregister_cpu_notifier; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, hctx->numa_node)) goto exit_hctx; if (xa_insert(&q->hctx_table, hctx_idx, hctx, GFP_KERNEL)) goto exit_flush_rq; return 0; exit_flush_rq: if (set->ops->exit_request) set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); unregister_cpu_notifier: blk_mq_remove_cpuhp(hctx); return -1; } static struct blk_mq_hw_ctx * blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, int node) { struct blk_mq_hw_ctx *hctx; gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node); if (!hctx) goto fail_alloc_hctx; if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node)) goto free_hctx; atomic_set(&hctx->nr_active, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); /* * Allocate space for all possible cpus to avoid allocation at * runtime */ hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *), gfp, node); if (!hctx->ctxs) goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), gfp, node, false, false)) goto free_ctxs; hctx->nr_ctx = 0; spin_lock_init(&hctx->dispatch_wait_lock); init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake); INIT_LIST_HEAD(&hctx->dispatch_wait.entry); hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp); if (!hctx->fq) goto free_bitmap; blk_mq_hctx_kobj_init(hctx); return hctx; free_bitmap: sbitmap_free(&hctx->ctx_map); free_ctxs: kfree(hctx->ctxs); free_cpumask: free_cpumask_var(hctx->cpumask); free_hctx: kfree(hctx); fail_alloc_hctx: return NULL; } static void blk_mq_init_cpu_queues(struct request_queue *q, unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; unsigned int i, j; for_each_possible_cpu(i) { struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; int k; __ctx->cpu = i; spin_lock_init(&__ctx->lock); for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++) INIT_LIST_HEAD(&__ctx->rq_lists[k]); __ctx->queue = q; /* * Set local node, IFF we have more than one hw queue. If * not, we remain on the home node of the device */ for (j = 0; j < set->nr_maps; j++) { hctx = blk_mq_map_queue_type(q, j, i); if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) hctx->numa_node = cpu_to_node(i); } } } struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int depth) { struct blk_mq_tags *tags; int ret; tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags); if (!tags) return NULL; ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth); if (ret) { blk_mq_free_rq_map(tags); return NULL; } return tags; } static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, int hctx_idx) { if (blk_mq_is_shared_tags(set->flags)) { set->tags[hctx_idx] = set->shared_tags; return true; } set->tags[hctx_idx] = blk_mq_alloc_map_and_rqs(set, hctx_idx, set->queue_depth); return set->tags[hctx_idx]; } void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { if (tags) { blk_mq_free_rqs(set, tags, hctx_idx); blk_mq_free_rq_map(tags); } } static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx) { if (!blk_mq_is_shared_tags(set->flags)) blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx); set->tags[hctx_idx] = NULL; } static void blk_mq_map_swqueue(struct request_queue *q) { unsigned int j, hctx_idx; unsigned long i; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; hctx->dispatch_from = NULL; } /* * Map software to hardware queues. * * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { ctx = per_cpu_ptr(q->queue_ctx, i); for (j = 0; j < set->nr_maps; j++) { if (!set->map[j].nr_queues) { ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); continue; } hctx_idx = set->map[j].mq_map[i]; /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[hctx_idx] && !__blk_mq_alloc_map_and_rqs(set, hctx_idx)) { /* * If tags initialization fail for some hctx, * that hctx won't be brought online. In this * case, remap the current ctx to hctx[0] which * is guaranteed to always have tags allocated */ set->map[j].mq_map[i] = 0; } hctx = blk_mq_map_queue_type(q, j, i); ctx->hctxs[j] = hctx; /* * If the CPU is already set in the mask, then we've * mapped this one already. This can happen if * devices share queues across queue maps. */ if (cpumask_test_cpu(i, hctx->cpumask)) continue; cpumask_set_cpu(i, hctx->cpumask); hctx->type = j; ctx->index_hw[hctx->type] = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; /* * If the nr_ctx type overflows, we have exceeded the * amount of sw queues we can support. */ BUG_ON(!hctx->nr_ctx); } for (; j < HCTX_MAX_TYPES; j++) ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); } queue_for_each_hw_ctx(q, hctx, i) { int cpu; /* * If no software queues are mapped to this hardware queue, * disable it and free the request entries. */ if (!hctx->nr_ctx) { /* Never unmap queue 0. We need it as a * fallback in case of a new remap fails * allocation */ if (i) __blk_mq_free_map_and_rqs(set, i); hctx->tags = NULL; continue; } hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping * over all possibly mapped software queues. */ sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx); /* * Rule out isolated CPUs from hctx->cpumask to avoid * running block kworker on isolated CPUs */ for_each_cpu(cpu, hctx->cpumask) { if (cpu_is_isolated(cpu)) cpumask_clear_cpu(cpu, hctx->cpumask); } /* * Initialize batch roundrobin counts */ hctx->next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } } /* * Caller needs to ensure that we're either frozen/quiesced, or that * the queue isn't live yet. */ static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { if (shared) { hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; } else { blk_mq_tag_idle(hctx); hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; } } } static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q); } } static void blk_mq_del_queue_tag_set(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); list_del(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); INIT_LIST_HEAD(&q->tag_set_list); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { mutex_lock(&set->tag_list_lock); /* * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, true); } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } /* All allocations will be freed in release handler of q->mq_kobj */ static int blk_mq_alloc_ctxs(struct request_queue *q) { struct blk_mq_ctxs *ctxs; int cpu; ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL); if (!ctxs) return -ENOMEM; ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!ctxs->queue_ctx) goto fail; for_each_possible_cpu(cpu) { struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu); ctx->ctxs = ctxs; } q->mq_kobj = &ctxs->kobj; q->queue_ctx = ctxs->queue_ctx; return 0; fail: kfree(ctxs); return -ENOMEM; } /* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free * and headache because q->mq_kobj shouldn't have been introduced, * but we can't group ctx/kctx kobj without it. */ void blk_mq_release(struct request_queue *q) { struct blk_mq_hw_ctx *hctx, *next; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list)); /* all hctx are in .unused_hctx_list now */ list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) { list_del_init(&hctx->hctx_list); kobject_put(&hctx->kobj); } xa_destroy(&q->hctx_table); /* * release .mq_kobj and sw queue's kobject now because * both share lifetime with request queue. */ blk_mq_sysfs_deinit(q); } static bool blk_mq_can_poll(struct blk_mq_tag_set *set) { return set->nr_maps > HCTX_TYPE_POLL && set->map[HCTX_TYPE_POLL].nr_queues; } struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata) { struct queue_limits default_lim = { }; struct request_queue *q; int ret; if (!lim) lim = &default_lim; lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT; if (blk_mq_can_poll(set)) lim->features |= BLK_FEAT_POLL; q = blk_alloc_queue(lim, set->numa_node); if (IS_ERR(q)) return q; q->queuedata = queuedata; ret = blk_mq_init_allocated_queue(set, q); if (ret) { blk_put_queue(q); return ERR_PTR(ret); } return q; } EXPORT_SYMBOL(blk_mq_alloc_queue); /** * blk_mq_destroy_queue - shutdown a request queue * @q: request queue to shutdown * * This shuts down a request queue allocated by blk_mq_alloc_queue(). All future * requests will be failed with -ENODEV. The caller is responsible for dropping * the reference from blk_mq_alloc_queue() by calling blk_put_queue(). * * Context: can sleep */ void blk_mq_destroy_queue(struct request_queue *q) { WARN_ON_ONCE(!queue_is_mq(q)); WARN_ON_ONCE(blk_queue_registered(q)); might_sleep(); blk_queue_flag_set(QUEUE_FLAG_DYING, q); blk_queue_start_drain(q); blk_mq_freeze_queue_wait(q); blk_sync_queue(q); blk_mq_cancel_work_sync(q); blk_mq_exit_queue(q); } EXPORT_SYMBOL(blk_mq_destroy_queue); struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; q = blk_mq_alloc_queue(set, lim, queuedata); if (IS_ERR(q)) return ERR_CAST(q); disk = __alloc_disk_node(q, set->numa_node, lkclass); if (!disk) { blk_mq_destroy_queue(q); blk_put_queue(q); return ERR_PTR(-ENOMEM); } set_bit(GD_OWNS_QUEUE, &disk->state); return disk; } EXPORT_SYMBOL(__blk_mq_alloc_disk); struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass) { struct gendisk *disk; if (!blk_get_queue(q)) return NULL; disk = __alloc_disk_node(q, NUMA_NO_NODE, lkclass); if (!disk) blk_put_queue(q); return disk; } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) { struct blk_mq_hw_ctx *hctx = NULL, *tmp; /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { if (tmp->numa_node == node) { hctx = tmp; break; } } if (hctx) list_del_init(&hctx->hctx_list); spin_unlock(&q->unused_hctx_lock); if (!hctx) hctx = blk_mq_alloc_hctx(q, set, node); if (!hctx) goto fail; if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) goto free_hctx; return hctx; free_hctx: kobject_put(&hctx->kobj); fail: return NULL; } static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i, j; /* protect against switching io scheduler */ mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); struct blk_mq_hw_ctx *old_hctx = xa_load(&q->hctx_table, i); if (old_hctx) { old_node = old_hctx->numa_node; blk_mq_exit_hctx(q, set, old_hctx, i); } if (!blk_mq_alloc_and_init_hctx(set, q, i, node)) { if (!old_hctx) break; pr_warn("Allocate new hctx on node %d fails, fallback to previous one on node %d\n", node, old_node); hctx = blk_mq_alloc_and_init_hctx(set, q, i, old_node); WARN_ON_ONCE(!hctx); } } /* * Increasing nr_hw_queues fails. Free the newly allocated * hctxs and keep the previous q->nr_hw_queues. */ if (i != set->nr_hw_queues) { j = q->nr_hw_queues; } else { j = i; q->nr_hw_queues = set->nr_hw_queues; } xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); mutex_unlock(&q->sysfs_lock); } int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q) { /* mark the queue as mq asap */ q->mq_ops = set->ops; if (blk_mq_alloc_ctxs(q)) goto err_exit; /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); xa_init(&q->hctx_table); blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->tag_set = set; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->flush_list); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); q->nr_requests = set->queue_depth; blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); return 0; err_hctxs: blk_mq_release(q); err_exit: q->mq_ops = NULL; return -ENOMEM; } EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; if (blk_mq_is_shared_tags(set->flags)) { set->shared_tags = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, set->queue_depth); if (!set->shared_tags) return -ENOMEM; } for (i = 0; i < set->nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_rqs(set, i)) goto out_unwind; cond_resched(); } return 0; out_unwind: while (--i >= 0) __blk_mq_free_map_and_rqs(set, i); if (blk_mq_is_shared_tags(set->flags)) { blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } return -ENOMEM; } /* * Allocate the request maps associated with this tag_set. Note that this * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */ static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set) { unsigned int depth; int err; depth = set->queue_depth; do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); if (!set->queue_depth || err) { pr_err("blk-mq: failed to allocate request map\n"); return -ENOMEM; } if (depth != set->queue_depth) pr_info("blk-mq: reduced tag depth (%u -> %u)\n", depth, set->queue_depth); return 0; } static void blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the * number of hardware queues. */ if (set->nr_maps == 1) set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues; if (set->ops->map_queues) { int i; /* * transport .map_queues is usually done in the following * way: * * for (queue = 0; queue < set->nr_hw_queues; queue++) { * mask = get_cpu_mask(queue) * for_each_cpu(cpu, mask) * set->map[x].mq_map[cpu] = queue; * } * * When we need to remap, the table has to be cleared for * killing stale mapping since one CPU may not be mapped * to any hw queue. */ for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set, int new_nr_hw_queues) { struct blk_mq_tags **new_tags; int i; if (set->nr_hw_queues >= new_nr_hw_queues) goto done; new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!new_tags) return -ENOMEM; if (set->tags) memcpy(new_tags, set->tags, set->nr_hw_queues * sizeof(*set->tags)); kfree(set->tags); set->tags = new_tags; for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_rqs(set, i)) { while (--i >= set->nr_hw_queues) __blk_mq_free_map_and_rqs(set, i); return -ENOMEM; } cond_resched(); } done: set->nr_hw_queues = new_nr_hw_queues; return 0; } /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the * requested depth down, if it's too large. In that case, the set * value will be stored in set->queue_depth. */ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) { int i, ret; BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS); if (!set->nr_hw_queues) return -EINVAL; if (!set->queue_depth) return -EINVAL; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) return -EINVAL; if (!set->ops->queue_rq) return -EINVAL; if (!set->ops->get_budget ^ !set->ops->put_budget) return -EINVAL; if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); set->queue_depth = BLK_MQ_MAX_DEPTH; } if (!set->nr_maps) set->nr_maps = 1; else if (set->nr_maps > HCTX_MAX_TYPES) return -EINVAL; /* * If a crashdump is active, then we are potentially in a very * memory constrained environment. Limit us to 64 tags to prevent * using too much memory. */ if (is_kdump_kernel()) set->queue_depth = min(64U, set->queue_depth); /* * There is no use for more h/w queues than cpus if we just have * a single map */ if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; if (set->flags & BLK_MQ_F_BLOCKING) { set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL); if (!set->srcu) return -ENOMEM; ret = init_srcu_struct(set->srcu); if (ret) goto out_free_srcu; } ret = -ENOMEM; set->tags = kcalloc_node(set->nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!set->tags) goto out_cleanup_srcu; for (i = 0; i < set->nr_maps; i++) { set->map[i].mq_map = kcalloc_node(nr_cpu_ids, sizeof(set->map[i].mq_map[0]), GFP_KERNEL, set->numa_node); if (!set->map[i].mq_map) goto out_free_mq_map; set->map[i].nr_queues = set->nr_hw_queues; } blk_mq_update_queue_map(set); ret = blk_mq_alloc_set_map_and_rqs(set); if (ret) goto out_free_mq_map; mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); set->map[i].mq_map = NULL; } kfree(set->tags); set->tags = NULL; out_cleanup_srcu: if (set->flags & BLK_MQ_F_BLOCKING) cleanup_srcu_struct(set->srcu); out_free_srcu: if (set->flags & BLK_MQ_F_BLOCKING) kfree(set->srcu); return ret; } EXPORT_SYMBOL(blk_mq_alloc_tag_set); /* allocate and initialize a tagset for a simple single-queue device */ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags) { memset(set, 0, sizeof(*set)); set->ops = ops; set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = queue_depth; set->numa_node = NUMA_NO_NODE; set->flags = set_flags; return blk_mq_alloc_tag_set(set); } EXPORT_SYMBOL_GPL(blk_mq_alloc_sq_tag_set); void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; for (i = 0; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); if (blk_mq_is_shared_tags(set->flags)) { blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; } kfree(set->tags); set->tags = NULL; if (set->flags & BLK_MQ_F_BLOCKING) { cleanup_srcu_struct(set->srcu); kfree(set->srcu); } } EXPORT_SYMBOL(blk_mq_free_tag_set); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) { struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_hw_ctx *hctx; int ret; unsigned long i; if (WARN_ON_ONCE(!q->mq_freeze_depth)) return -EINVAL; if (!set) return -EINVAL; if (q->nr_requests == nr) return 0; blk_mq_quiesce_queue(q); ret = 0; queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->tags) continue; /* * If we're using an MQ scheduler, just update the scheduler * queue depth. This is similar to what the old code would do. */ if (hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); } else { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); } if (ret) break; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(hctx); } if (!ret) { q->nr_requests = nr; if (blk_mq_is_shared_tags(set->flags)) { if (q->elevator) blk_mq_tag_update_sched_shared_tags(q); else blk_mq_tag_resize_shared_tags(set, nr); } } blk_mq_unquiesce_queue(q); return ret; } /* * request_queue and elevator_type pair. * It is just used by __blk_mq_update_nr_hw_queues to cache * the elevator_type associated with a request_queue. */ struct blk_mq_qe_pair { struct list_head node; struct request_queue *q; struct elevator_type *type; }; /* * Cache the elevator_type in qe pair list and switch the * io scheduler to 'none' */ static bool blk_mq_elv_switch_none(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!qe) return false; /* q->elevator needs protection from ->sysfs_lock */ mutex_lock(&q->sysfs_lock); /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); goto unlock; } INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; /* keep a reference to the elevator module as we'll switch back */ __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); unlock: mutex_unlock(&q->sysfs_lock); return true; } static struct blk_mq_qe_pair *blk_lookup_qe_pair(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; list_for_each_entry(qe, head, node) if (qe->q == q) return qe; return NULL; } static void blk_mq_elv_switch_back(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; struct elevator_type *t; qe = blk_lookup_qe_pair(head, q); if (!qe) return; t = qe->type; list_del(&qe->node); kfree(qe); mutex_lock(&q->sysfs_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; LIST_HEAD(head); int prev_nr_hw_queues = set->nr_hw_queues; int i; lockdep_assert_held(&set->tag_list_lock); if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; if (nr_hw_queues < 1) return; if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. */ list_for_each_entry(q, &set->tag_list, tag_set_list) if (!blk_mq_elv_switch_none(&head, q)) goto switch_back; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); blk_mq_sysfs_unregister_hctxs(q); } if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0) goto reregister; fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { struct queue_limits lim; blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { int i = prev_nr_hw_queues; pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n", nr_hw_queues, prev_nr_hw_queues); for (; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); set->nr_hw_queues = prev_nr_hw_queues; goto fallback; } lim = queue_limits_start_update(q); if (blk_mq_can_poll(set)) lim.features |= BLK_FEAT_POLL; else lim.features &= ~BLK_FEAT_POLL; if (queue_limits_commit_update(q, &lim) < 0) pr_warn("updating the poll flag failed\n"); blk_mq_map_swqueue(q); } reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register_hctxs(q); blk_mq_debugfs_register_hctxs(q); } switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); } void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { mutex_lock(&set->tag_list_lock); __blk_mq_update_nr_hw_queues(set, nr_hw_queues); mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags) { long state = get_current_state(); int ret; do { ret = q->mq_ops->poll(hctx, iob); if (ret > 0) { __set_current_state(TASK_RUNNING); return ret; } if (signal_pending_state(state, current)) __set_current_state(TASK_RUNNING); if (task_is_running(current)) return 1; if (ret < 0 || (flags & BLK_POLL_ONESHOT)) break; cpu_relax(); } while (!need_resched()); __set_current_state(TASK_RUNNING); return 0; } int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, unsigned int flags) { struct blk_mq_hw_ctx *hctx = xa_load(&q->hctx_table, cookie); return blk_hctx_poll(q, hctx, iob, flags); } int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, unsigned int poll_flags) { struct request_queue *q = rq->q; int ret; if (!blk_rq_is_poll(rq)) return 0; if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; ret = blk_hctx_poll(q, rq->mq_hctx, iob, poll_flags); blk_queue_exit(q); return ret; } EXPORT_SYMBOL_GPL(blk_rq_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { return rq->mq_ctx->cpu; } EXPORT_SYMBOL(blk_mq_rq_cpu); void blk_mq_cancel_work_sync(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; cancel_delayed_work_sync(&q->requeue_work); queue_for_each_hw_ctx(q, hctx, i) cancel_delayed_work_sync(&hctx->run_work); } static int __init blk_mq_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(blk_cpu_done, i)); for_each_possible_cpu(i) INIT_CSD(&per_cpu(blk_cpu_csd, i), __blk_mq_complete_request_remote, NULL); open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, "block/softirq:dead", NULL, blk_softirq_cpu_dead); cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", blk_mq_hctx_notify_online, blk_mq_hctx_notify_offline); return 0; } subsys_initcall(blk_mq_init); |
| 9 9 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "rsrc.h" #include "filetable.h" static int io_file_bitmap_get(struct io_ring_ctx *ctx) { struct io_file_table *table = &ctx->file_table; unsigned long nr = ctx->file_alloc_end; int ret; if (!table->bitmap) return -ENFILE; do { ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint); if (ret != nr) return ret; if (table->alloc_hint == ctx->file_alloc_start) break; nr = table->alloc_hint; table->alloc_hint = ctx->file_alloc_start; } while (1); return -ENFILE; } bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) { table->files = kvcalloc(nr_files, sizeof(table->files[0]), GFP_KERNEL_ACCOUNT); if (unlikely(!table->files)) return false; table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); if (unlikely(!table->bitmap)) { kvfree(table->files); return false; } return true; } void io_free_file_tables(struct io_file_table *table) { kvfree(table->files); bitmap_free(table->bitmap); table->files = NULL; table->bitmap = NULL; } static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, u32 slot_index) __must_hold(&req->ctx->uring_lock) { struct io_fixed_file *file_slot; int ret; if (io_is_uring_fops(file)) return -EBADF; if (!ctx->file_data) return -ENXIO; if (slot_index >= ctx->nr_user_files) return -EINVAL; slot_index = array_index_nospec(slot_index, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); if (file_slot->file_ptr) { ret = io_queue_rsrc_removal(ctx->file_data, slot_index, io_slot_file(file_slot)); if (ret) return ret; file_slot->file_ptr = 0; } else { io_file_bitmap_set(&ctx->file_table, slot_index); } *io_get_tag_slot(ctx->file_data, slot_index) = 0; io_fixed_file_set(file_slot, file); return 0; } int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file, unsigned int file_slot) { bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC; int ret; if (alloc_slot) { ret = io_file_bitmap_get(ctx); if (unlikely(ret < 0)) return ret; file_slot = ret; } else { file_slot--; } ret = io_install_fixed_file(ctx, file, file_slot); if (!ret && alloc_slot) ret = file_slot; return ret; } /* * Note when io_fixed_fd_install() returns error value, it will ensure * fput() is called correspondingly. */ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, struct file *file, unsigned int file_slot) { struct io_ring_ctx *ctx = req->ctx; int ret; io_ring_submit_lock(ctx, issue_flags); ret = __io_fixed_fd_install(ctx, file, file_slot); io_ring_submit_unlock(ctx, issue_flags); if (unlikely(ret < 0)) fput(file); return ret; } int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) { struct io_fixed_file *file_slot; int ret; if (unlikely(!ctx->file_data)) return -ENXIO; if (offset >= ctx->nr_user_files) return -EINVAL; offset = array_index_nospec(offset, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, offset); if (!file_slot->file_ptr) return -EBADF; ret = io_queue_rsrc_removal(ctx->file_data, offset, io_slot_file(file_slot)); if (ret) return ret; file_slot->file_ptr = 0; io_file_bitmap_clear(&ctx->file_table, offset); return 0; } int io_register_file_alloc_range(struct io_ring_ctx *ctx, struct io_uring_file_index_range __user *arg) { struct io_uring_file_index_range range; u32 end; if (copy_from_user(&range, arg, sizeof(range))) return -EFAULT; if (check_add_overflow(range.off, range.len, &end)) return -EOVERFLOW; if (range.resv || end > ctx->nr_user_files) return -EINVAL; io_file_table_set_alloc_range(ctx, range.off, range.len); return 0; } |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 | // SPDX-License-Identifier: GPL-2.0-or-later /* * common UDP/RAW code * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/route.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/icmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/tcp_states.h> #include <net/dsfield.h> #include <net/sock_reuseport.h> #include <linux/errqueue.h> #include <linux/uaccess.h> static bool ipv6_mapped_addr_any(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); } static void ip6_datagram_flow_key_init(struct flowi6 *fl6, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ipv6_pinfo *np = inet6_sk(sk); int oif = sk->sk_bound_dev_if; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = sk->sk_protocol; fl6->daddr = sk->sk_v6_daddr; fl6->saddr = np->saddr; fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk->sk_uid; if (!oif) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif) { if (ipv6_addr_is_multicast(&fl6->daddr)) oif = READ_ONCE(np->mcast_oif); else oif = READ_ONCE(np->ucast_oif); } fl6->flowi6_oif = oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) { struct ip6_flowlabel *flowlabel = NULL; struct in6_addr *final_p, final; struct ipv6_txoptions *opt; struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 fl6; int err = 0; if (inet6_test_bit(SNDFLOW, sk) && (np->flow_label & IPV6_FLOWLABEL_MASK)) { flowlabel = fl6_sock_lookup(sk, np->flow_label); if (IS_ERR(flowlabel)) return -EINVAL; } ip6_datagram_flow_key_init(&fl6, sk); rcu_read_lock(); opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (fix_sk_saddr) { if (ipv6_addr_any(&np->saddr)) np->saddr = fl6.saddr; if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { sk->sk_v6_rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } } ip6_sk_dst_store_flow(sk, dst, &fl6); out: fl6_sock_release(flowlabel); return err; } void ip6_datagram_release_cb(struct sock *sk) { struct dst_entry *dst; if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) return; rcu_read_lock(); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) { rcu_read_unlock(); return; } rcu_read_unlock(); ip6_datagram_dst_update(sk, false); } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *daddr, old_daddr; __be32 fl6_flowlabel = 0; __be32 old_fl6_flowlabel; __be16 old_dport; int addr_type; int err; if (usin->sin6_family == AF_INET) { if (ipv6_only_sock(sk)) return -EAFNOSUPPORT; err = __ip4_datagram_connect(sk, uaddr, addr_len); goto ipv4_connected; } if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; if (inet6_test_bit(SNDFLOW, sk)) fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; if (ipv6_addr_any(&usin->sin6_addr)) { /* * connect to self */ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); daddr = &usin->sin6_addr; if (addr_type & IPV6_ADDR_MAPPED) { struct sockaddr_in sin; if (ipv6_only_sock(sk)) { err = -ENETUNREACH; goto out; } sin.sin_family = AF_INET; sin.sin_addr.s_addr = daddr->s6_addr32[3]; sin.sin_port = usin->sin6_port; err = __ip4_datagram_connect(sk, (struct sockaddr *) &sin, sizeof(sin)); ipv4_connected: if (err) goto out; ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr); if (ipv6_addr_any(&np->saddr) || ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } goto out; } if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) { err = -EINVAL; goto out; } WRITE_ONCE(sk->sk_bound_dev_if, usin->sin6_scope_id); } if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST)) WRITE_ONCE(sk->sk_bound_dev_if, READ_ONCE(np->mcast_oif)); /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; goto out; } } /* save the current peer information before updating it */ old_daddr = sk->sk_v6_daddr; old_fl6_flowlabel = np->flow_label; old_dport = inet->inet_dport; sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the * destination cache for it. */ err = ip6_datagram_dst_update(sk, true); if (err) { /* Restore the socket peer info, to keep it consistent with * the old socket state */ sk->sk_v6_daddr = old_daddr; np->flow_label = old_fl6_flowlabel; inet->inet_dport = old_dport; goto out; } reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: return err; } EXPORT_SYMBOL_GPL(__ip6_datagram_connect); int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { int res; lock_sock(sk); res = __ip6_datagram_connect(sk, uaddr, addr_len); release_sock(sk); return res; } EXPORT_SYMBOL_GPL(ip6_datagram_connect); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, int addr_len) { DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr); if (sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; return ip6_datagram_connect(sk, uaddr, addr_len); } EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only); static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out) { switch (icmp6_hdr(skb)->icmp6_type) { case ICMPV6_TIME_EXCEED: case ICMPV6_DEST_UNREACH: ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr), icmp6_hdr(skb)->icmp6_datagram_len * 8); } } void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { struct icmp6hdr *icmph = icmp6_hdr(skb); struct sock_exterr_skb *serr; if (!inet6_test_bit(RECVERR6, sk)) return; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; skb->protocol = htons(ETH_P_IPV6); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6; serr->ee.ee_type = icmph->icmp6_type; serr->ee.ee_code = icmph->icmp6_code; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&(((struct ipv6hdr *)(icmph + 1))->daddr) - skb_network_header(skb); serr->port = port; __skb_pull(skb, payload - skb->data); if (inet6_test_bit(RECVERR6_RFC4884, sk)) ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } EXPORT_SYMBOL_GPL(ipv6_icmp_error); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { struct sock_exterr_skb *serr; struct ipv6hdr *iph; struct sk_buff *skb; if (!inet6_test_bit(RECVERR6, sk)) return; skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb) return; skb->protocol = htons(ETH_P_IPV6); skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; ip6_flow_hdr(iph, 0, 0); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_type = 0; serr->ee.ee_code = 0; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); serr->port = fl6->fl6_dport; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *iph; struct sk_buff *skb; struct ip6_mtuinfo *mtu_info; if (!np->rxopt.bits.rxpmtu) return; skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb) return; skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; mtu_info = IP6CBMTU(skb); mtu_info->ip6m_mtu = mtu; mtu_info->ip6m_addr.sin6_family = AF_INET6; mtu_info->ip6m_addr.sin6_port = 0; mtu_info->ip6m_addr.sin6_flowinfo = 0; mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif; mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); skb = xchg(&np->rxpmtu, skb); kfree_skb(skb); } /* For some errors we have valid addr_offset even with zero payload and * zero port. Also, addr_offset should be supported if port is set. */ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr) { return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 || serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port; } /* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL. * * At one point, excluding local errors was a quick test to identify icmp/icmp6 * errors. This is no longer true, but the test remained, so the v6 stack, * unlike v4, also honors cmsg requests on all wifi and timestamp errors. */ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, struct sock_exterr_skb *serr) { if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) return true; if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) return false; if (!IP6CB(skb)->iif) return false; return true; } /* * Handle MSG_ERRQUEUE */ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct sk_buff *skb; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in6 offender; } errhdr; int err; int copied; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (unlikely(err)) { kfree_skb(skb); return err; } sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); if (sin && ipv6_datagram_support_addr(serr)) { const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = serr->port; if (skb->protocol == htons(ETH_P_IPV6)) { const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset), struct ipv6hdr, daddr); sin->sin6_addr = ip6h->daddr; if (inet6_test_bit(SNDFLOW, sk)) sin->sin6_flowinfo = ip6_flowinfo(ip6h); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), &sin->sin6_addr); sin->sin6_scope_id = 0; } *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); if (ip6_datagram_support_cmsg(skb, serr)) { sin->sin6_family = AF_INET6; if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) ip6_datagram_recv_specific_ctl(sk, msg, skb); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } } put_cmsg(msg, SOL_IPV6, IPV6_RECVERR, sizeof(errhdr), &errhdr); /* Now we could try to dump offended packet options */ msg->msg_flags |= MSG_ERRQUEUE; err = copied; consume_skb(skb); out: return err; } EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct ip6_mtuinfo mtu_info; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); int err; int copied; err = -EAGAIN; skb = xchg(&np->rxpmtu, NULL); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); if (sin) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); err = copied; out_free_skb: kfree_skb(skb); out: return err; } void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6); if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; if (is_ipv6) { src_info.ipi6_ifindex = IP6CB(skb)->iif; src_info.ipi6_addr = ipv6_hdr(skb)->daddr; } else { src_info.ipi6_ifindex = PKTINFO_SKB_CB(skb)->ipi_ifindex; ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, &src_info.ipi6_addr); } if (src_info.ipi6_ifindex >= 0) put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } } void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_skb_parm *opt = IP6CB(skb); unsigned char *nh = skb_network_header(skb); if (np->rxopt.bits.rxhlim) { int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { int tclass = ipv6_get_dsfield(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxflow) { __be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh); if (flowinfo) put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } /* HbH is allowed only once */ if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) { u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } if (opt->lastopt && (np->rxopt.bits.dstopts || np->rxopt.bits.srcrt)) { /* * Silly enough, but we need to reparse in order to * report extension headers (except for HbH) * in order. * * Also note that IPV6_RECVRTHDRDSTOPTS is NOT * (and WILL NOT be) defined because * IPV6_RECVDSTOPTS is more generic. --yoshfuji */ unsigned int off = sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; while (off <= opt->lastopt) { unsigned int len; u8 *ptr = nh + off; switch (nexthdr) { case IPPROTO_DSTOPTS: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; if (np->rxopt.bits.dstopts) put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, len, ptr); break; case IPPROTO_ROUTING: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; if (np->rxopt.bits.srcrt) put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, len, ptr); break; case IPPROTO_AH: nexthdr = ptr[0]; len = (ptr[1] + 2) << 2; break; default: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; break; } off += len; } } /* socket options in old style */ if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) { u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { u8 *ptr = nh + opt->dst0; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.osrcrt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt); put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr); } if (np->rxopt.bits.odstopts && opt->dst1) { u8 *ptr = nh + opt->dst1; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; __be16 _ports[2], *ports; ports = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_ports), &_ports); if (ports) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; sin6.sin6_flowinfo = 0; sin6.sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->daddr, opt->iif); put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); } } if (np->rxopt.bits.recvfragsize && opt->frag_max_size) { int val = opt->frag_max_size; put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val); } } void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { ip6_datagram_recv_common_ctl(sk, msg, skb); ip6_datagram_recv_specific_ctl(sk, msg, skb); } EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, struct flowi6 *fl6, struct ipcm6_cookie *ipc6) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; struct ipv6_rt_hdr *rthdr; struct ipv6_opt_hdr *hdr; struct ipv6_txoptions *opt = ipc6->opt; int len; int err = 0; for_each_cmsghdr(cmsg, msg) { int addr_type; if (!CMSG_OK(msg, cmsg)) { err = -EINVAL; goto exit_f; } if (cmsg->cmsg_level == SOL_SOCKET) { err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc); if (err) return err; continue; } if (cmsg->cmsg_level != SOL_IPV6) continue; switch (cmsg->cmsg_type) { case IPV6_PKTINFO: case IPV6_2292PKTINFO: { struct net_device *dev = NULL; int src_idx; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; goto exit_f; } src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); src_idx = src_info->ipi6_ifindex; if (src_idx) { if (fl6->flowi6_oif && src_idx != fl6->flowi6_oif && (READ_ONCE(sk->sk_bound_dev_if) != fl6->flowi6_oif || !sk_dev_equal_l3scope(sk, src_idx))) return -EINVAL; fl6->flowi6_oif = src_idx; } addr_type = __ipv6_addr_type(&src_info->ipi6_addr); rcu_read_lock(); if (fl6->flowi6_oif) { dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); if (!dev) { rcu_read_unlock(); return -ENODEV; } } else if (addr_type & IPV6_ADDR_LINKLOCAL) { rcu_read_unlock(); return -EINVAL; } if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) && !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, dev, !strict, 0, IFA_F_TENTATIVE) && !ipv6_chk_acast_addr_src(net, dev, &src_info->ipi6_addr)) err = -EINVAL; else fl6->saddr = src_info->ipi6_addr; } rcu_read_unlock(); if (err) goto exit_f; break; } case IPV6_FLOWINFO: if (cmsg->cmsg_len < CMSG_LEN(4)) { err = -EINVAL; goto exit_f; } if (fl6->flowlabel&IPV6_FLOWINFO_MASK) { if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { err = -EINVAL; goto exit_f; } } fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); break; case IPV6_2292HOPOPTS: case IPV6_HOPOPTS: if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } opt->opt_nflen += len; opt->hopopt = hdr; break; case IPV6_2292DSTOPTS: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } if (opt->dst1opt) { err = -EINVAL; goto exit_f; } opt->opt_flen += len; opt->dst1opt = hdr; break; case IPV6_DSTOPTS: case IPV6_RTHDRDSTOPTS: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } if (cmsg->cmsg_type == IPV6_DSTOPTS) { opt->opt_flen += len; opt->dst1opt = hdr; } else { opt->opt_nflen += len; opt->dst0opt = hdr; } break; case IPV6_2292RTHDR: case IPV6_RTHDR: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) { err = -EINVAL; goto exit_f; } rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); switch (rthdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) { err = -EINVAL; goto exit_f; } break; #endif default: err = -EINVAL; goto exit_f; } len = ((rthdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } /* segments left must also match */ if ((rthdr->hdrlen >> 1) != rthdr->segments_left) { err = -EINVAL; goto exit_f; } opt->opt_nflen += len; opt->srcrt = rthdr; if (cmsg->cmsg_type == IPV6_2292RTHDR && opt->dst1opt) { int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3); opt->opt_nflen += dsthdrlen; opt->dst0opt = opt->dst1opt; opt->dst1opt = NULL; opt->opt_flen -= dsthdrlen; } break; case IPV6_2292HOPLIMIT: case IPV6_HOPLIMIT: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { err = -EINVAL; goto exit_f; } ipc6->hlimit = *(int *)CMSG_DATA(cmsg); if (ipc6->hlimit < -1 || ipc6->hlimit > 0xff) { err = -EINVAL; goto exit_f; } break; case IPV6_TCLASS: { int tc; err = -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; tc = *(int *)CMSG_DATA(cmsg); if (tc < -1 || tc > 0xff) goto exit_f; err = 0; ipc6->tclass = tc; break; } case IPV6_DONTFRAG: { int df; err = -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; df = *(int *)CMSG_DATA(cmsg); if (df < 0 || df > 1) goto exit_f; err = 0; ipc6->dontfrag = df; break; } default: net_dbg_ratelimited("invalid cmsg type: %d\n", cmsg->cmsg_type); err = -EINVAL; goto exit_f; } } exit_f: return err; } EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, __u16 destp, int rqueue, int bucket) { const struct in6_addr *dest, *src; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; seq_printf(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", bucket, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, sp->sk_state, sk_wmem_alloc_get(sp), rqueue, 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } |
| 81 76 25 81 70 53 85 83 76 64 49 161 161 161 9 77 77 76 67 61 66 149 113 119 3 3 3 3 83 77 76 9 9 201 1 9 155 192 9 95 1 95 2 84 84 78 77 76 5 65 73 1 9 63 3 3 52 52 52 18 1 25 1 22 19 1 2 12 27 1 2 85 85 6 6 6 6 5 6 6 6 6 1 5 13 13 5 4 6 2 1 13 13 1 12 7 6 5 92 92 10 88 8 2 12 13 6 74 9 64 48 5 65 46 1 65 13 4 9 2 6 5 2 2 2 3 2 2 2 2 2 3 1 2 3 13 1 13 91 11 11 1 4 11 11 11 118 118 109 119 1 118 1 1 1 1 1 4 4 4 1 1 79 79 79 79 79 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 | // SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/rbtree.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/ratelimit.h> #include "overlayfs.h" struct ovl_cache_entry { unsigned int len; unsigned int type; u64 real_ino; u64 ino; struct list_head l_node; struct rb_node node; struct ovl_cache_entry *next_maybe_whiteout; bool is_upper; bool is_whiteout; bool check_xwhiteout; char name[]; }; struct ovl_dir_cache { long refcount; u64 version; struct list_head entries; struct rb_root root; }; struct ovl_readdir_data { struct dir_context ctx; struct dentry *dentry; bool is_lowest; struct rb_root *root; struct list_head *list; struct list_head middle; struct ovl_cache_entry *first_maybe_whiteout; int count; int err; bool is_upper; bool d_type_supported; bool in_xwhiteouts_dir; }; struct ovl_dir_file { bool is_real; bool is_upper; struct ovl_dir_cache *cache; struct list_head *cursor; struct file *realfile; struct file *upperfile; }; static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n) { return rb_entry(n, struct ovl_cache_entry, node); } static bool ovl_cache_entry_find_link(const char *name, int len, struct rb_node ***link, struct rb_node **parent) { bool found = false; struct rb_node **newp = *link; while (!found && *newp) { int cmp; struct ovl_cache_entry *tmp; *parent = *newp; tmp = ovl_cache_entry_from_node(*newp); cmp = strncmp(name, tmp->name, len); if (cmp > 0) newp = &tmp->node.rb_right; else if (cmp < 0 || len < tmp->len) newp = &tmp->node.rb_left; else found = true; } *link = newp; return found; } static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, const char *name, int len) { struct rb_node *node = root->rb_node; int cmp; while (node) { struct ovl_cache_entry *p = ovl_cache_entry_from_node(node); cmp = strncmp(name, p->name, len); if (cmp > 0) node = p->node.rb_right; else if (cmp < 0 || len < p->len) node = p->node.rb_left; else return p; } return NULL; } static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd, struct ovl_cache_entry *p) { /* Don't care if not doing ovl_iter() */ if (!rdd->dentry) return false; /* Always recalc d_ino when remapping lower inode numbers */ if (ovl_xino_bits(OVL_FS(rdd->dentry->d_sb))) return true; /* Always recalc d_ino for parent */ if (strcmp(p->name, "..") == 0) return true; /* If this is lower, then native d_ino will do */ if (!rdd->is_upper) return false; /* * Recalc d_ino for '.' and for all entries if dir is impure (contains * copied up entries) */ if ((p->name[0] == '.' && p->len == 1) || ovl_test_flag(OVL_IMPURE, d_inode(rdd->dentry))) return true; return false; } static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd, const char *name, int len, u64 ino, unsigned int d_type) { struct ovl_cache_entry *p; size_t size = offsetof(struct ovl_cache_entry, name[len + 1]); p = kmalloc(size, GFP_KERNEL); if (!p) return NULL; memcpy(p->name, name, len); p->name[len] = '\0'; p->len = len; p->type = d_type; p->real_ino = ino; p->ino = ino; /* Defer setting d_ino for upper entry to ovl_iterate() */ if (ovl_calc_d_ino(rdd, p)) p->ino = 0; p->is_upper = rdd->is_upper; p->is_whiteout = false; /* Defer check for overlay.whiteout to ovl_iterate() */ p->check_xwhiteout = rdd->in_xwhiteouts_dir && d_type == DT_REG; if (d_type == DT_CHR) { p->next_maybe_whiteout = rdd->first_maybe_whiteout; rdd->first_maybe_whiteout = p; } return p; } static bool ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, const char *name, int len, u64 ino, unsigned int d_type) { struct rb_node **newp = &rdd->root->rb_node; struct rb_node *parent = NULL; struct ovl_cache_entry *p; if (ovl_cache_entry_find_link(name, len, &newp, &parent)) return true; p = ovl_cache_entry_new(rdd, name, len, ino, d_type); if (p == NULL) { rdd->err = -ENOMEM; return false; } list_add_tail(&p->l_node, rdd->list); rb_link_node(&p->node, parent, newp); rb_insert_color(&p->node, rdd->root); return true; } static bool ovl_fill_lowest(struct ovl_readdir_data *rdd, const char *name, int namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ovl_cache_entry *p; p = ovl_cache_entry_find(rdd->root, name, namelen); if (p) { list_move_tail(&p->l_node, &rdd->middle); } else { p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type); if (p == NULL) rdd->err = -ENOMEM; else list_add_tail(&p->l_node, &rdd->middle); } return rdd->err == 0; } void ovl_cache_free(struct list_head *list) { struct ovl_cache_entry *p; struct ovl_cache_entry *n; list_for_each_entry_safe(p, n, list, l_node) kfree(p); INIT_LIST_HEAD(list); } void ovl_dir_cache_free(struct inode *inode) { struct ovl_dir_cache *cache = ovl_dir_cache(inode); if (cache) { ovl_cache_free(&cache->entries); kfree(cache); } } static void ovl_cache_put(struct ovl_dir_file *od, struct inode *inode) { struct ovl_dir_cache *cache = od->cache; WARN_ON(cache->refcount <= 0); cache->refcount--; if (!cache->refcount) { if (ovl_dir_cache(inode) == cache) ovl_set_dir_cache(inode, NULL); ovl_cache_free(&cache->entries); kfree(cache); } } static bool ovl_fill_merge(struct dir_context *ctx, const char *name, int namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ovl_readdir_data *rdd = container_of(ctx, struct ovl_readdir_data, ctx); rdd->count++; if (!rdd->is_lowest) return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type); else return ovl_fill_lowest(rdd, name, namelen, offset, ino, d_type); } static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data *rdd) { int err; struct ovl_cache_entry *p; struct dentry *dentry, *dir = path->dentry; const struct cred *old_cred; old_cred = ovl_override_creds(rdd->dentry->d_sb); err = down_write_killable(&dir->d_inode->i_rwsem); if (!err) { while (rdd->first_maybe_whiteout) { p = rdd->first_maybe_whiteout; rdd->first_maybe_whiteout = p->next_maybe_whiteout; dentry = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); if (!IS_ERR(dentry)) { p->is_whiteout = ovl_is_whiteout(dentry); dput(dentry); } } inode_unlock(dir->d_inode); } revert_creds(old_cred); return err; } static inline int ovl_dir_read(const struct path *realpath, struct ovl_readdir_data *rdd) { struct file *realfile; int err; realfile = ovl_path_open(realpath, O_RDONLY | O_LARGEFILE); if (IS_ERR(realfile)) return PTR_ERR(realfile); rdd->first_maybe_whiteout = NULL; rdd->ctx.pos = 0; do { rdd->count = 0; rdd->err = 0; err = iterate_dir(realfile, &rdd->ctx); if (err >= 0) err = rdd->err; } while (!err && rdd->count); if (!err && rdd->first_maybe_whiteout && rdd->dentry) err = ovl_check_whiteouts(realpath, rdd); fput(realfile); return err; } static void ovl_dir_reset(struct file *file) { struct ovl_dir_file *od = file->private_data; struct ovl_dir_cache *cache = od->cache; struct inode *inode = file_inode(file); bool is_real; if (cache && ovl_inode_version_get(inode) != cache->version) { ovl_cache_put(od, inode); od->cache = NULL; od->cursor = NULL; } is_real = ovl_dir_is_real(inode); if (od->is_real != is_real) { /* is_real can only become false when dir is copied up */ if (WARN_ON(is_real)) return; od->is_real = false; } } static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list, struct rb_root *root) { int err; struct path realpath; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_merge, .dentry = dentry, .list = list, .root = root, .is_lowest = false, }; int idx, next; const struct ovl_layer *layer; for (idx = 0; idx != -1; idx = next) { next = ovl_path_next(idx, dentry, &realpath, &layer); rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry; rdd.in_xwhiteouts_dir = layer->has_xwhiteouts && ovl_dentry_has_xwhiteouts(dentry); if (next != -1) { err = ovl_dir_read(&realpath, &rdd); if (err) break; } else { /* * Insert lowest layer entries before upper ones, this * allows offsets to be reasonably constant */ list_add(&rdd.middle, rdd.list); rdd.is_lowest = true; err = ovl_dir_read(&realpath, &rdd); list_del(&rdd.middle); } } return err; } static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) { struct list_head *p; loff_t off = 0; list_for_each(p, &od->cache->entries) { if (off >= pos) break; off++; } /* Cursor is safe since the cache is stable */ od->cursor = p; } static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) { int res; struct ovl_dir_cache *cache; struct inode *inode = d_inode(dentry); cache = ovl_dir_cache(inode); if (cache && ovl_inode_version_get(inode) == cache->version) { WARN_ON(!cache->refcount); cache->refcount++; return cache; } ovl_set_dir_cache(d_inode(dentry), NULL); cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); if (!cache) return ERR_PTR(-ENOMEM); cache->refcount = 1; INIT_LIST_HEAD(&cache->entries); cache->root = RB_ROOT; res = ovl_dir_read_merged(dentry, &cache->entries, &cache->root); if (res) { ovl_cache_free(&cache->entries); kfree(cache); return ERR_PTR(res); } cache->version = ovl_inode_version_get(inode); ovl_set_dir_cache(inode, cache); return cache; } /* Map inode number to lower fs unique range */ static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid, const char *name, int namelen, bool warn) { unsigned int xinoshift = 64 - xinobits; if (unlikely(ino >> xinoshift)) { if (warn) { pr_warn_ratelimited("d_ino too big (%.*s, ino=%llu, xinobits=%d)\n", namelen, name, ino, xinobits); } return ino; } /* * The lowest xinobit is reserved for mapping the non-peresistent inode * numbers range, but this range is only exposed via st_ino, not here. */ return ino | ((u64)fsid) << (xinoshift + 1); } /* * Set d_ino for upper entries if needed. Non-upper entries should always report * the uppermost real inode ino and should not call this function. * * When not all layer are on same fs, report real ino also for upper. * * When all layers are on the same fs, and upper has a reference to * copy up origin, call vfs_getattr() on the overlay entry to make * sure that d_ino will be consistent with st_ino from stat(2). * * Also checks the overlay.whiteout xattr by doing a full lookup which will return * negative in this case. */ static int ovl_cache_update(const struct path *path, struct ovl_cache_entry *p, bool update_ino) { struct dentry *dir = path->dentry; struct ovl_fs *ofs = OVL_FS(dir->d_sb); struct dentry *this = NULL; enum ovl_path_type type; u64 ino = p->real_ino; int xinobits = ovl_xino_bits(ofs); int err = 0; if (!ovl_same_dev(ofs) && !p->check_xwhiteout) goto out; if (p->name[0] == '.') { if (p->len == 1) { this = dget(dir); goto get; } if (p->len == 2 && p->name[1] == '.') { /* we shall not be moved */ this = dget(dir->d_parent); goto get; } } /* This checks also for xwhiteouts */ this = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); if (IS_ERR_OR_NULL(this) || !this->d_inode) { /* Mark a stale entry */ p->is_whiteout = true; if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; goto fail; } goto out; } get: if (!ovl_same_dev(ofs) || !update_ino) goto out; type = ovl_path_type(this); if (OVL_TYPE_ORIGIN(type)) { struct kstat stat; struct path statpath = *path; statpath.dentry = this; err = vfs_getattr(&statpath, &stat, STATX_INO, 0); if (err) goto fail; /* * Directory inode is always on overlay st_dev. * Non-dir with ovl_same_dev() could be on pseudo st_dev in case * of xino bits overflow. */ WARN_ON_ONCE(S_ISDIR(stat.mode) && dir->d_sb->s_dev != stat.dev); ino = stat.ino; } else if (xinobits && !OVL_TYPE_UPPER(type)) { ino = ovl_remap_lower_ino(ino, xinobits, ovl_layer_lower(this)->fsid, p->name, p->len, ovl_xino_warn(ofs)); } out: p->ino = ino; dput(this); return err; fail: pr_warn_ratelimited("failed to look up (%s) for ino (%i)\n", p->name, err); goto out; } static bool ovl_fill_plain(struct dir_context *ctx, const char *name, int namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ovl_cache_entry *p; struct ovl_readdir_data *rdd = container_of(ctx, struct ovl_readdir_data, ctx); rdd->count++; p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type); if (p == NULL) { rdd->err = -ENOMEM; return false; } list_add_tail(&p->l_node, rdd->list); return true; } static int ovl_dir_read_impure(const struct path *path, struct list_head *list, struct rb_root *root) { int err; struct path realpath; struct ovl_cache_entry *p, *n; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_plain, .list = list, .root = root, }; INIT_LIST_HEAD(list); *root = RB_ROOT; ovl_path_upper(path->dentry, &realpath); err = ovl_dir_read(&realpath, &rdd); if (err) return err; list_for_each_entry_safe(p, n, list, l_node) { if (strcmp(p->name, ".") != 0 && strcmp(p->name, "..") != 0) { err = ovl_cache_update(path, p, true); if (err) return err; } if (p->ino == p->real_ino) { list_del(&p->l_node); kfree(p); } else { struct rb_node **newp = &root->rb_node; struct rb_node *parent = NULL; if (WARN_ON(ovl_cache_entry_find_link(p->name, p->len, &newp, &parent))) return -EIO; rb_link_node(&p->node, parent, newp); rb_insert_color(&p->node, root); } } return 0; } static struct ovl_dir_cache *ovl_cache_get_impure(const struct path *path) { int res; struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct ovl_dir_cache *cache; cache = ovl_dir_cache(inode); if (cache && ovl_inode_version_get(inode) == cache->version) return cache; /* Impure cache is not refcounted, free it here */ ovl_dir_cache_free(inode); ovl_set_dir_cache(inode, NULL); cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); if (!cache) return ERR_PTR(-ENOMEM); res = ovl_dir_read_impure(path, &cache->entries, &cache->root); if (res) { ovl_cache_free(&cache->entries); kfree(cache); return ERR_PTR(res); } if (list_empty(&cache->entries)) { /* * A good opportunity to get rid of an unneeded "impure" flag. * Removing the "impure" xattr is best effort. */ if (!ovl_want_write(dentry)) { ovl_removexattr(ofs, ovl_dentry_upper(dentry), OVL_XATTR_IMPURE); ovl_drop_write(dentry); } ovl_clear_flag(OVL_IMPURE, inode); kfree(cache); return NULL; } cache->version = ovl_inode_version_get(inode); ovl_set_dir_cache(inode, cache); return cache; } struct ovl_readdir_translate { struct dir_context *orig_ctx; struct ovl_dir_cache *cache; struct dir_context ctx; u64 parent_ino; int fsid; int xinobits; bool xinowarn; }; static bool ovl_fill_real(struct dir_context *ctx, const char *name, int namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ovl_readdir_translate *rdt = container_of(ctx, struct ovl_readdir_translate, ctx); struct dir_context *orig_ctx = rdt->orig_ctx; if (rdt->parent_ino && strcmp(name, "..") == 0) { ino = rdt->parent_ino; } else if (rdt->cache) { struct ovl_cache_entry *p; p = ovl_cache_entry_find(&rdt->cache->root, name, namelen); if (p) ino = p->ino; } else if (rdt->xinobits) { ino = ovl_remap_lower_ino(ino, rdt->xinobits, rdt->fsid, name, namelen, rdt->xinowarn); } return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type); } static bool ovl_is_impure_dir(struct file *file) { struct ovl_dir_file *od = file->private_data; struct inode *dir = file_inode(file); /* * Only upper dir can be impure, but if we are in the middle of * iterating a lower real dir, dir could be copied up and marked * impure. We only want the impure cache if we started iterating * a real upper dir to begin with. */ return od->is_upper && ovl_test_flag(OVL_IMPURE, dir); } static int ovl_iterate_real(struct file *file, struct dir_context *ctx) { int err; struct ovl_dir_file *od = file->private_data; struct dentry *dir = file->f_path.dentry; struct ovl_fs *ofs = OVL_FS(dir->d_sb); const struct ovl_layer *lower_layer = ovl_layer_lower(dir); struct ovl_readdir_translate rdt = { .ctx.actor = ovl_fill_real, .orig_ctx = ctx, .xinobits = ovl_xino_bits(ofs), .xinowarn = ovl_xino_warn(ofs), }; if (rdt.xinobits && lower_layer) rdt.fsid = lower_layer->fsid; if (OVL_TYPE_MERGE(ovl_path_type(dir->d_parent))) { struct kstat stat; struct path statpath = file->f_path; statpath.dentry = dir->d_parent; err = vfs_getattr(&statpath, &stat, STATX_INO, 0); if (err) return err; WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev); rdt.parent_ino = stat.ino; } if (ovl_is_impure_dir(file)) { rdt.cache = ovl_cache_get_impure(&file->f_path); if (IS_ERR(rdt.cache)) return PTR_ERR(rdt.cache); } err = iterate_dir(od->realfile, &rdt.ctx); ctx->pos = rdt.ctx.pos; return err; } static int ovl_iterate(struct file *file, struct dir_context *ctx) { struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; struct ovl_fs *ofs = OVL_FS(dentry->d_sb); struct ovl_cache_entry *p; const struct cred *old_cred; int err; old_cred = ovl_override_creds(dentry->d_sb); if (!ctx->pos) ovl_dir_reset(file); if (od->is_real) { /* * If parent is merge, then need to adjust d_ino for '..', if * dir is impure then need to adjust d_ino for copied up * entries. */ if (ovl_xino_bits(ofs) || (ovl_same_fs(ofs) && (ovl_is_impure_dir(file) || OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) { err = ovl_iterate_real(file, ctx); } else { err = iterate_dir(od->realfile, ctx); } goto out; } if (!od->cache) { struct ovl_dir_cache *cache; cache = ovl_cache_get(dentry); err = PTR_ERR(cache); if (IS_ERR(cache)) goto out; od->cache = cache; ovl_seek_cursor(od, ctx->pos); } while (od->cursor != &od->cache->entries) { p = list_entry(od->cursor, struct ovl_cache_entry, l_node); if (!p->is_whiteout) { if (!p->ino || p->check_xwhiteout) { err = ovl_cache_update(&file->f_path, p, !p->ino); if (err) goto out; } } /* ovl_cache_update() sets is_whiteout on stale entry */ if (!p->is_whiteout) { if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) break; } od->cursor = p->l_node.next; ctx->pos++; } err = 0; out: revert_creds(old_cred); return err; } static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin) { loff_t res; struct ovl_dir_file *od = file->private_data; inode_lock(file_inode(file)); if (!file->f_pos) ovl_dir_reset(file); if (od->is_real) { res = vfs_llseek(od->realfile, offset, origin); file->f_pos = od->realfile->f_pos; } else { res = -EINVAL; switch (origin) { case SEEK_CUR: offset += file->f_pos; break; case SEEK_SET: break; default: goto out_unlock; } if (offset < 0) goto out_unlock; if (offset != file->f_pos) { file->f_pos = offset; if (od->cache) ovl_seek_cursor(od, offset); } res = offset; } out_unlock: inode_unlock(file_inode(file)); return res; } static struct file *ovl_dir_open_realfile(const struct file *file, const struct path *realpath) { struct file *res; const struct cred *old_cred; old_cred = ovl_override_creds(file_inode(file)->i_sb); res = ovl_path_open(realpath, O_RDONLY | (file->f_flags & O_LARGEFILE)); revert_creds(old_cred); return res; } /* * Like ovl_real_fdget(), returns upperfile if dir was copied up since open. * Unlike ovl_real_fdget(), this caches upperfile in file->private_data. * * TODO: use same abstract type for file->private_data of dir and file so * upperfile could also be cached for files as well. */ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) { struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; struct file *old, *realfile = od->realfile; if (!OVL_TYPE_UPPER(ovl_path_type(dentry))) return want_upper ? NULL : realfile; /* * Need to check if we started out being a lower dir, but got copied up */ if (!od->is_upper) { realfile = READ_ONCE(od->upperfile); if (!realfile) { struct path upperpath; ovl_path_upper(dentry, &upperpath); realfile = ovl_dir_open_realfile(file, &upperpath); if (IS_ERR(realfile)) return realfile; old = cmpxchg_release(&od->upperfile, NULL, realfile); if (old) { fput(realfile); realfile = old; } } } return realfile; } static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct file *realfile; int err; err = ovl_sync_status(OVL_FS(file_inode(file)->i_sb)); if (err <= 0) return err; realfile = ovl_dir_real_file(file, true); err = PTR_ERR_OR_ZERO(realfile); /* Nothing to sync for lower */ if (!realfile || err) return err; return vfs_fsync_range(realfile, start, end, datasync); } static int ovl_dir_release(struct inode *inode, struct file *file) { struct ovl_dir_file *od = file->private_data; if (od->cache) { inode_lock(inode); ovl_cache_put(od, inode); inode_unlock(inode); } fput(od->realfile); if (od->upperfile) fput(od->upperfile); kfree(od); return 0; } static int ovl_dir_open(struct inode *inode, struct file *file) { struct path realpath; struct file *realfile; struct ovl_dir_file *od; enum ovl_path_type type; od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); if (!od) return -ENOMEM; type = ovl_path_real(file->f_path.dentry, &realpath); realfile = ovl_dir_open_realfile(file, &realpath); if (IS_ERR(realfile)) { kfree(od); return PTR_ERR(realfile); } od->realfile = realfile; od->is_real = ovl_dir_is_real(inode); od->is_upper = OVL_TYPE_UPPER(type); file->private_data = od; return 0; } WRAP_DIR_ITER(ovl_iterate) // FIXME! const struct file_operations ovl_dir_operations = { .read = generic_read_dir, .open = ovl_dir_open, .iterate_shared = shared_ovl_iterate, .llseek = ovl_dir_llseek, .fsync = ovl_dir_fsync, .release = ovl_dir_release, }; int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) { int err; struct ovl_cache_entry *p, *n; struct rb_root root = RB_ROOT; const struct cred *old_cred; old_cred = ovl_override_creds(dentry->d_sb); err = ovl_dir_read_merged(dentry, list, &root); revert_creds(old_cred); if (err) return err; err = 0; list_for_each_entry_safe(p, n, list, l_node) { /* * Select whiteouts in upperdir, they should * be cleared when deleting this directory. */ if (p->is_whiteout) { if (p->is_upper) continue; goto del_entry; } if (p->name[0] == '.') { if (p->len == 1) goto del_entry; if (p->len == 2 && p->name[1] == '.') goto del_entry; } err = -ENOTEMPTY; break; del_entry: list_del(&p->l_node); kfree(p); } return err; } void ovl_cleanup_whiteouts(struct ovl_fs *ofs, struct dentry *upper, struct list_head *list) { struct ovl_cache_entry *p; inode_lock_nested(upper->d_inode, I_MUTEX_CHILD); list_for_each_entry(p, list, l_node) { struct dentry *dentry; if (WARN_ON(!p->is_whiteout || !p->is_upper)) continue; dentry = ovl_lookup_upper(ofs, p->name, upper, p->len); if (IS_ERR(dentry)) { pr_err("lookup '%s/%.*s' failed (%i)\n", upper->d_name.name, p->len, p->name, (int) PTR_ERR(dentry)); continue; } if (dentry->d_inode) ovl_cleanup(ofs, upper->d_inode, dentry); dput(dentry); } inode_unlock(upper->d_inode); } static bool ovl_check_d_type(struct dir_context *ctx, const char *name, int namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ovl_readdir_data *rdd = container_of(ctx, struct ovl_readdir_data, ctx); /* Even if d_type is not supported, DT_DIR is returned for . and .. */ if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen)) return true; if (d_type != DT_UNKNOWN) rdd->d_type_supported = true; return true; } /* * Returns 1 if d_type is supported, 0 not supported/unknown. Negative values * if error is encountered. */ int ovl_check_d_type_supported(const struct path *realpath) { int err; struct ovl_readdir_data rdd = { .ctx.actor = ovl_check_d_type, .d_type_supported = false, }; err = ovl_dir_read(realpath, &rdd); if (err) return err; return rdd.d_type_supported; } #define OVL_INCOMPATDIR_NAME "incompat" static int ovl_workdir_cleanup_recurse(struct ovl_fs *ofs, const struct path *path, int level) { int err; struct inode *dir = path->dentry->d_inode; LIST_HEAD(list); struct ovl_cache_entry *p; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_plain, .list = &list, }; bool incompat = false; /* * The "work/incompat" directory is treated specially - if it is not * empty, instead of printing a generic error and mounting read-only, * we will error about incompat features and fail the mount. * * When called from ovl_indexdir_cleanup(), path->dentry->d_name.name * starts with '#'. */ if (level == 2 && !strcmp(path->dentry->d_name.name, OVL_INCOMPATDIR_NAME)) incompat = true; err = ovl_dir_read(path, &rdd); if (err) goto out; inode_lock_nested(dir, I_MUTEX_PARENT); list_for_each_entry(p, &list, l_node) { struct dentry *dentry; if (p->name[0] == '.') { if (p->len == 1) continue; if (p->len == 2 && p->name[1] == '.') continue; } else if (incompat) { pr_err("overlay with incompat feature '%s' cannot be mounted\n", p->name); err = -EINVAL; break; } dentry = ovl_lookup_upper(ofs, p->name, path->dentry, p->len); if (IS_ERR(dentry)) continue; if (dentry->d_inode) err = ovl_workdir_cleanup(ofs, dir, path->mnt, dentry, level); dput(dentry); if (err) break; } inode_unlock(dir); out: ovl_cache_free(&list); return err; } int ovl_workdir_cleanup(struct ovl_fs *ofs, struct inode *dir, struct vfsmount *mnt, struct dentry *dentry, int level) { int err; if (!d_is_dir(dentry) || level > 1) { return ovl_cleanup(ofs, dir, dentry); } err = ovl_do_rmdir(ofs, dir, dentry); if (err) { struct path path = { .mnt = mnt, .dentry = dentry }; inode_unlock(dir); err = ovl_workdir_cleanup_recurse(ofs, &path, level + 1); inode_lock_nested(dir, I_MUTEX_PARENT); if (!err) err = ovl_cleanup(ofs, dir, dentry); } return err; } int ovl_indexdir_cleanup(struct ovl_fs *ofs) { int err; struct dentry *indexdir = ofs->workdir; struct dentry *index = NULL; struct inode *dir = indexdir->d_inode; struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = indexdir }; LIST_HEAD(list); struct ovl_cache_entry *p; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_plain, .list = &list, }; err = ovl_dir_read(&path, &rdd); if (err) goto out; inode_lock_nested(dir, I_MUTEX_PARENT); list_for_each_entry(p, &list, l_node) { if (p->name[0] == '.') { if (p->len == 1) continue; if (p->len == 2 && p->name[1] == '.') continue; } index = ovl_lookup_upper(ofs, p->name, indexdir, p->len); if (IS_ERR(index)) { err = PTR_ERR(index); index = NULL; break; } /* Cleanup leftover from index create/cleanup attempt */ if (index->d_name.name[0] == '#') { err = ovl_workdir_cleanup(ofs, dir, path.mnt, index, 1); if (err) break; goto next; } err = ovl_verify_index(ofs, index); if (!err) { goto next; } else if (err == -ESTALE) { /* Cleanup stale index entries */ err = ovl_cleanup(ofs, dir, index); } else if (err != -ENOENT) { /* * Abort mount to avoid corrupting the index if * an incompatible index entry was found or on out * of memory. */ break; } else if (ofs->config.nfs_export) { /* * Whiteout orphan index to block future open by * handle after overlay nlink dropped to zero. */ err = ovl_cleanup_and_whiteout(ofs, dir, index); } else { /* Cleanup orphan index entries */ err = ovl_cleanup(ofs, dir, index); } if (err) break; next: dput(index); index = NULL; } dput(index); inode_unlock(dir); out: ovl_cache_free(&list); if (err) pr_err("failed index dir cleanup (%i)\n", err); return err; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | // SPDX-License-Identifier: GPL-2.0-only /* * vivid-meta-cap.c - meta capture support functions. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/videodev2.h> #include <media/v4l2-common.h> #include <linux/usb/video.h> #include "vivid-core.h" #include "vivid-kthread-cap.h" #include "vivid-meta-cap.h" static int meta_cap_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct vivid_dev *dev = vb2_get_drv_priv(vq); unsigned int size = sizeof(struct vivid_uvc_meta_buf); if (!vivid_is_webcam(dev)) return -EINVAL; if (*nplanes) { if (sizes[0] < size) return -EINVAL; } else { sizes[0] = size; } *nplanes = 1; return 0; } static int meta_cap_buf_prepare(struct vb2_buffer *vb) { struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue); unsigned int size = sizeof(struct vivid_uvc_meta_buf); dprintk(dev, 1, "%s\n", __func__); if (dev->buf_prepare_error) { /* * Error injection: test what happens if buf_prepare() returns * an error. */ dev->buf_prepare_error = false; return -EINVAL; } if (vb2_plane_size(vb, 0) < size) { dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n", __func__, vb2_plane_size(vb, 0), size); return -EINVAL; } vb2_set_plane_payload(vb, 0, size); return 0; } static void meta_cap_buf_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue); struct vivid_buffer *buf = container_of(vbuf, struct vivid_buffer, vb); dprintk(dev, 1, "%s\n", __func__); spin_lock(&dev->slock); list_add_tail(&buf->list, &dev->meta_cap_active); spin_unlock(&dev->slock); } static int meta_cap_start_streaming(struct vb2_queue *vq, unsigned int count) { struct vivid_dev *dev = vb2_get_drv_priv(vq); int err; dprintk(dev, 1, "%s\n", __func__); dev->meta_cap_seq_count = 0; if (dev->start_streaming_error) { dev->start_streaming_error = false; err = -EINVAL; } else { err = vivid_start_generating_vid_cap(dev, &dev->meta_cap_streaming); } if (err) { struct vivid_buffer *buf, *tmp; list_for_each_entry_safe(buf, tmp, &dev->meta_cap_active, list) { list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } } return err; } /* abort streaming and wait for last buffer */ static void meta_cap_stop_streaming(struct vb2_queue *vq) { struct vivid_dev *dev = vb2_get_drv_priv(vq); dprintk(dev, 1, "%s\n", __func__); vivid_stop_generating_vid_cap(dev, &dev->meta_cap_streaming); } static void meta_cap_buf_request_complete(struct vb2_buffer *vb) { struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue); v4l2_ctrl_request_complete(vb->req_obj.req, &dev->ctrl_hdl_meta_cap); } const struct vb2_ops vivid_meta_cap_qops = { .queue_setup = meta_cap_queue_setup, .buf_prepare = meta_cap_buf_prepare, .buf_queue = meta_cap_buf_queue, .start_streaming = meta_cap_start_streaming, .stop_streaming = meta_cap_stop_streaming, .buf_request_complete = meta_cap_buf_request_complete, .wait_prepare = vb2_ops_wait_prepare, .wait_finish = vb2_ops_wait_finish, }; int vidioc_enum_fmt_meta_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct vivid_dev *dev = video_drvdata(file); if (!vivid_is_webcam(dev)) return -EINVAL; if (f->index > 0) return -EINVAL; f->type = V4L2_BUF_TYPE_META_CAPTURE; f->pixelformat = V4L2_META_FMT_UVC; return 0; } int vidioc_g_fmt_meta_cap(struct file *file, void *priv, struct v4l2_format *f) { struct vivid_dev *dev = video_drvdata(file); struct v4l2_meta_format *meta = &f->fmt.meta; if (!vivid_is_webcam(dev) || !dev->has_meta_cap) return -EINVAL; meta->dataformat = V4L2_META_FMT_UVC; meta->buffersize = sizeof(struct vivid_uvc_meta_buf); return 0; } void vivid_meta_cap_fillbuff(struct vivid_dev *dev, struct vivid_buffer *buf, u64 soe) { struct vivid_uvc_meta_buf *meta = vb2_plane_vaddr(&buf->vb.vb2_buf, 0); int buf_off = 0; buf->vb.sequence = dev->meta_cap_seq_count; if (dev->field_cap == V4L2_FIELD_ALTERNATE) buf->vb.sequence /= 2; memset(meta, 1, vb2_plane_size(&buf->vb.vb2_buf, 0)); meta->ns = ktime_get_ns(); meta->sof = buf->vb.sequence * 30; meta->length = sizeof(*meta) - offsetof(struct vivid_uvc_meta_buf, length); meta->flags = UVC_STREAM_EOH | UVC_STREAM_EOF; if ((buf->vb.sequence % 2) == 0) meta->flags |= UVC_STREAM_FID; dprintk(dev, 2, "%s ns:%llu sof:%4d len:%u flags: 0x%02x", __func__, meta->ns, meta->sof, meta->length, meta->flags); if (dev->meta_pts) { meta->flags |= UVC_STREAM_PTS; meta->buf[0] = div_u64(soe, VIVID_META_CLOCK_UNIT); buf_off = 4; dprintk(dev, 2, " pts: %u\n", *(__u32 *)(meta->buf)); } if (dev->meta_scr) { meta->flags |= UVC_STREAM_SCR; meta->buf[buf_off] = div_u64((soe + dev->cap_frame_eof_offset), VIVID_META_CLOCK_UNIT); meta->buf[buf_off + 4] = (buf->vb.sequence * 30) % 1000; dprintk(dev, 2, " stc: %u, sof counter: %u\n", *(__u32 *)(meta->buf + buf_off), *(__u16 *)(meta->buf + buf_off + 4)); } dprintk(dev, 2, "\n"); } |
| 113 93 112 112 29 7 67 28 33 27 11 11 11 108 97 101 105 4 106 103 4 55 5 39 17 107 103 34 5 7 7 2 38 38 1 4 104 112 1 112 110 103 35 3 38 103 103 4 100 24 85 11 2 11 93 93 42 42 35 3 17 15 9 8 4 1 8 7 2 2 1 1 1 7 7 45 43 30 25 42 5 16 1 1 1 1 1 1 1 1 1 1 7 7 7 5 5 2 9 9 2 4 5 29 11 7 13 29 29 30 12 43 7 7 1 7 1 7 7 7 9 9 45 29 30 45 29 30 34 20 45 45 45 45 11 9 9 7 9 8 1 1 1 1 1 5 4 3 7 7 7 11 3 5 9 9 1 5 9 7 8 10 11 11 11 3 11 11 11 11 11 13 13 13 11 3 5 9 1 11 11 9 3 6 6 9 9 24 10 9 10 15 22 28 28 28 28 22 22 22 22 10 15 22 9 9 9 4 5 10 24 28 8 22 28 28 11 11 2 10 5 9 9 5 9 9 1 7 11 13 6 5 1 7 9 13 15 9 7 7 13 15 15 15 15 15 15 13 13 13 13 13 13 62 37 37 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Written by Koji Sato. */ #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/pagevec.h> #include "nilfs.h" #include "page.h" #include "btnode.h" #include "btree.h" #include "alloc.h" #include "dat.h" static void __nilfs_btree_init(struct nilfs_bmap *bmap); static struct nilfs_btree_path *nilfs_btree_alloc_path(void) { struct nilfs_btree_path *path; int level = NILFS_BTREE_LEVEL_DATA; path = kmem_cache_alloc(nilfs_btree_path_cache, GFP_NOFS); if (path == NULL) goto out; for (; level < NILFS_BTREE_LEVEL_MAX; level++) { path[level].bp_bh = NULL; path[level].bp_sib_bh = NULL; path[level].bp_index = 0; path[level].bp_oldreq.bpr_ptr = NILFS_BMAP_INVALID_PTR; path[level].bp_newreq.bpr_ptr = NILFS_BMAP_INVALID_PTR; path[level].bp_op = NULL; } out: return path; } static void nilfs_btree_free_path(struct nilfs_btree_path *path) { int level = NILFS_BTREE_LEVEL_DATA; for (; level < NILFS_BTREE_LEVEL_MAX; level++) brelse(path[level].bp_bh); kmem_cache_free(nilfs_btree_path_cache, path); } /* * B-tree node operations */ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); if (IS_ERR(bh)) return PTR_ERR(bh); set_buffer_nilfs_volatile(bh); *bhp = bh; return 0; } static int nilfs_btree_node_get_flags(const struct nilfs_btree_node *node) { return node->bn_flags; } static void nilfs_btree_node_set_flags(struct nilfs_btree_node *node, int flags) { node->bn_flags = flags; } static int nilfs_btree_node_root(const struct nilfs_btree_node *node) { return nilfs_btree_node_get_flags(node) & NILFS_BTREE_NODE_ROOT; } static int nilfs_btree_node_get_level(const struct nilfs_btree_node *node) { return node->bn_level; } static void nilfs_btree_node_set_level(struct nilfs_btree_node *node, int level) { node->bn_level = level; } static int nilfs_btree_node_get_nchildren(const struct nilfs_btree_node *node) { return le16_to_cpu(node->bn_nchildren); } static void nilfs_btree_node_set_nchildren(struct nilfs_btree_node *node, int nchildren) { node->bn_nchildren = cpu_to_le16(nchildren); } static int nilfs_btree_node_size(const struct nilfs_bmap *btree) { return i_blocksize(btree->b_inode); } static int nilfs_btree_nchildren_per_block(const struct nilfs_bmap *btree) { return btree->b_nchildren_per_block; } static __le64 * nilfs_btree_node_dkeys(const struct nilfs_btree_node *node) { return (__le64 *)((char *)(node + 1) + (nilfs_btree_node_root(node) ? 0 : NILFS_BTREE_NODE_EXTRA_PAD_SIZE)); } static __le64 * nilfs_btree_node_dptrs(const struct nilfs_btree_node *node, int ncmax) { return (__le64 *)(nilfs_btree_node_dkeys(node) + ncmax); } static __u64 nilfs_btree_node_get_key(const struct nilfs_btree_node *node, int index) { return le64_to_cpu(*(nilfs_btree_node_dkeys(node) + index)); } static void nilfs_btree_node_set_key(struct nilfs_btree_node *node, int index, __u64 key) { *(nilfs_btree_node_dkeys(node) + index) = cpu_to_le64(key); } static __u64 nilfs_btree_node_get_ptr(const struct nilfs_btree_node *node, int index, int ncmax) { return le64_to_cpu(*(nilfs_btree_node_dptrs(node, ncmax) + index)); } static void nilfs_btree_node_set_ptr(struct nilfs_btree_node *node, int index, __u64 ptr, int ncmax) { *(nilfs_btree_node_dptrs(node, ncmax) + index) = cpu_to_le64(ptr); } static void nilfs_btree_node_init(struct nilfs_btree_node *node, int flags, int level, int nchildren, int ncmax, const __u64 *keys, const __u64 *ptrs) { __le64 *dkeys; __le64 *dptrs; int i; nilfs_btree_node_set_flags(node, flags); nilfs_btree_node_set_level(node, level); nilfs_btree_node_set_nchildren(node, nchildren); dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); for (i = 0; i < nchildren; i++) { dkeys[i] = cpu_to_le64(keys[i]); dptrs[i] = cpu_to_le64(ptrs[i]); } } /* Assume the buffer heads corresponding to left and right are locked. */ static void nilfs_btree_node_move_left(struct nilfs_btree_node *left, struct nilfs_btree_node *right, int n, int lncmax, int rncmax) { __le64 *ldkeys, *rdkeys; __le64 *ldptrs, *rdptrs; int lnchildren, rnchildren; ldkeys = nilfs_btree_node_dkeys(left); ldptrs = nilfs_btree_node_dptrs(left, lncmax); lnchildren = nilfs_btree_node_get_nchildren(left); rdkeys = nilfs_btree_node_dkeys(right); rdptrs = nilfs_btree_node_dptrs(right, rncmax); rnchildren = nilfs_btree_node_get_nchildren(right); memcpy(ldkeys + lnchildren, rdkeys, n * sizeof(*rdkeys)); memcpy(ldptrs + lnchildren, rdptrs, n * sizeof(*rdptrs)); memmove(rdkeys, rdkeys + n, (rnchildren - n) * sizeof(*rdkeys)); memmove(rdptrs, rdptrs + n, (rnchildren - n) * sizeof(*rdptrs)); lnchildren += n; rnchildren -= n; nilfs_btree_node_set_nchildren(left, lnchildren); nilfs_btree_node_set_nchildren(right, rnchildren); } /* Assume that the buffer heads corresponding to left and right are locked. */ static void nilfs_btree_node_move_right(struct nilfs_btree_node *left, struct nilfs_btree_node *right, int n, int lncmax, int rncmax) { __le64 *ldkeys, *rdkeys; __le64 *ldptrs, *rdptrs; int lnchildren, rnchildren; ldkeys = nilfs_btree_node_dkeys(left); ldptrs = nilfs_btree_node_dptrs(left, lncmax); lnchildren = nilfs_btree_node_get_nchildren(left); rdkeys = nilfs_btree_node_dkeys(right); rdptrs = nilfs_btree_node_dptrs(right, rncmax); rnchildren = nilfs_btree_node_get_nchildren(right); memmove(rdkeys + n, rdkeys, rnchildren * sizeof(*rdkeys)); memmove(rdptrs + n, rdptrs, rnchildren * sizeof(*rdptrs)); memcpy(rdkeys, ldkeys + lnchildren - n, n * sizeof(*rdkeys)); memcpy(rdptrs, ldptrs + lnchildren - n, n * sizeof(*rdptrs)); lnchildren -= n; rnchildren += n; nilfs_btree_node_set_nchildren(left, lnchildren); nilfs_btree_node_set_nchildren(right, rnchildren); } /* Assume that the buffer head corresponding to node is locked. */ static void nilfs_btree_node_insert(struct nilfs_btree_node *node, int index, __u64 key, __u64 ptr, int ncmax) { __le64 *dkeys; __le64 *dptrs; int nchildren; dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); nchildren = nilfs_btree_node_get_nchildren(node); if (index < nchildren) { memmove(dkeys + index + 1, dkeys + index, (nchildren - index) * sizeof(*dkeys)); memmove(dptrs + index + 1, dptrs + index, (nchildren - index) * sizeof(*dptrs)); } dkeys[index] = cpu_to_le64(key); dptrs[index] = cpu_to_le64(ptr); nchildren++; nilfs_btree_node_set_nchildren(node, nchildren); } /* Assume that the buffer head corresponding to node is locked. */ static void nilfs_btree_node_delete(struct nilfs_btree_node *node, int index, __u64 *keyp, __u64 *ptrp, int ncmax) { __u64 key; __u64 ptr; __le64 *dkeys; __le64 *dptrs; int nchildren; dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); key = le64_to_cpu(dkeys[index]); ptr = le64_to_cpu(dptrs[index]); nchildren = nilfs_btree_node_get_nchildren(node); if (keyp != NULL) *keyp = key; if (ptrp != NULL) *ptrp = ptr; if (index < nchildren - 1) { memmove(dkeys + index, dkeys + index + 1, (nchildren - index - 1) * sizeof(*dkeys)); memmove(dptrs + index, dptrs + index + 1, (nchildren - index - 1) * sizeof(*dptrs)); } nchildren--; nilfs_btree_node_set_nchildren(node, nchildren); } static int nilfs_btree_node_lookup(const struct nilfs_btree_node *node, __u64 key, int *indexp) { __u64 nkey; int index, low, high, s; /* binary search */ low = 0; high = nilfs_btree_node_get_nchildren(node) - 1; index = 0; s = 0; while (low <= high) { index = (low + high) / 2; nkey = nilfs_btree_node_get_key(node, index); if (nkey == key) { s = 0; goto out; } else if (nkey < key) { low = index + 1; s = -1; } else { high = index - 1; s = 1; } } /* adjust index */ if (nilfs_btree_node_get_level(node) > NILFS_BTREE_LEVEL_NODE_MIN) { if (s > 0 && index > 0) index--; } else if (s < 0) index++; out: *indexp = index; return s == 0; } /** * nilfs_btree_node_broken - verify consistency of btree node * @node: btree node block to be examined * @size: node size (in bytes) * @inode: host inode of btree * @blocknr: block number * * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. */ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node, size_t size, struct inode *inode, sector_t blocknr) { int level, flags, nchildren; int ret = 0; level = nilfs_btree_node_get_level(node); flags = nilfs_btree_node_get_flags(node); nchildren = nilfs_btree_node_get_nchildren(node); if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX || (flags & NILFS_BTREE_NODE_ROOT) || nchildren < 0 || nchildren > NILFS_BTREE_NODE_NCHILDREN_MAX(size))) { nilfs_crit(inode->i_sb, "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d", inode->i_ino, (unsigned long long)blocknr, level, flags, nchildren); ret = 1; } return ret; } /** * nilfs_btree_root_broken - verify consistency of btree root node * @node: btree root node to be examined * @inode: host inode of btree * * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned. */ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node, struct inode *inode) { int level, flags, nchildren; int ret = 0; level = nilfs_btree_node_get_level(node); flags = nilfs_btree_node_get_flags(node); nchildren = nilfs_btree_node_get_nchildren(node); if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX || nchildren < 0 || nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) { nilfs_crit(inode->i_sb, "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d", inode->i_ino, level, flags, nchildren); ret = 1; } return ret; } int nilfs_btree_broken_node_block(struct buffer_head *bh) { struct inode *inode; int ret; if (buffer_nilfs_checked(bh)) return 0; inode = bh->b_folio->mapping->host; ret = nilfs_btree_node_broken((struct nilfs_btree_node *)bh->b_data, bh->b_size, inode, bh->b_blocknr); if (likely(!ret)) set_buffer_nilfs_checked(bh); return ret; } static struct nilfs_btree_node * nilfs_btree_get_root(const struct nilfs_bmap *btree) { return (struct nilfs_btree_node *)btree->b_u.u_data; } static struct nilfs_btree_node * nilfs_btree_get_nonroot_node(const struct nilfs_btree_path *path, int level) { return (struct nilfs_btree_node *)path[level].bp_bh->b_data; } static struct nilfs_btree_node * nilfs_btree_get_sib_node(const struct nilfs_btree_path *path, int level) { return (struct nilfs_btree_node *)path[level].bp_sib_bh->b_data; } static int nilfs_btree_height(const struct nilfs_bmap *btree) { return nilfs_btree_node_get_level(nilfs_btree_get_root(btree)) + 1; } static struct nilfs_btree_node * nilfs_btree_get_node(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, int level, int *ncmaxp) { struct nilfs_btree_node *node; if (level == nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_root(btree); *ncmaxp = NILFS_BTREE_ROOT_NCHILDREN_MAX; } else { node = nilfs_btree_get_nonroot_node(path, level); *ncmaxp = nilfs_btree_nchildren_per_block(btree); } return node; } static int nilfs_btree_bad_node(const struct nilfs_bmap *btree, struct nilfs_btree_node *node, int level) { if (unlikely(nilfs_btree_node_get_level(node) != level)) { dump_stack(); nilfs_crit(btree->b_inode->i_sb, "btree level mismatch (ino=%lu): %d != %d", btree->b_inode->i_ino, nilfs_btree_node_get_level(node), level); return 1; } return 0; } struct nilfs_btree_readahead_info { struct nilfs_btree_node *node; /* parent node */ int max_ra_blocks; /* max nof blocks to read ahead */ int index; /* current index on the parent node */ int ncmax; /* nof children in the parent node */ }; static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp, const struct nilfs_btree_readahead_info *ra) { struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh, *ra_bh; sector_t submit_ptr = 0; int ret; ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh, &submit_ptr); if (ret) { if (likely(ret == -EEXIST)) goto out_check; if (ret == -ENOENT) { /* * Block address translation failed due to invalid * value of 'ptr'. In this case, return internal code * -EINVAL (broken bmap) to notify bmap layer of fatal * metadata corruption. */ ret = -EINVAL; } return ret; } if (ra) { int i, n; __u64 ptr2; /* read ahead sibling nodes */ for (n = ra->max_ra_blocks, i = ra->index + 1; n > 0 && i < ra->ncmax; n--, i++) { ptr2 = nilfs_btree_node_get_ptr(ra->node, i, ra->ncmax); ret = nilfs_btnode_submit_block(btnc, ptr2, 0, REQ_OP_READ | REQ_RAHEAD, &ra_bh, &submit_ptr); if (likely(!ret || ret == -EEXIST)) brelse(ra_bh); else if (ret != -EBUSY) break; if (!buffer_locked(bh)) goto out_no_wait; } } wait_on_buffer(bh); out_no_wait: if (!buffer_uptodate(bh)) { nilfs_err(btree->b_inode->i_sb, "I/O error reading b-tree node block (ino=%lu, blocknr=%llu)", btree->b_inode->i_ino, (unsigned long long)ptr); brelse(bh); return -EIO; } out_check: if (nilfs_btree_broken_node_block(bh)) { clear_buffer_uptodate(bh); brelse(bh); return -EINVAL; } *bhp = bh; return 0; } static int nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { return __nilfs_btree_get_block(btree, ptr, bhp, NULL); } static int nilfs_btree_do_lookup(const struct nilfs_bmap *btree, struct nilfs_btree_path *path, __u64 key, __u64 *ptrp, int minlevel, int readahead) { struct nilfs_btree_node *node; struct nilfs_btree_readahead_info p, *ra; __u64 ptr; int level, index, found, ncmax, ret; node = nilfs_btree_get_root(btree); level = nilfs_btree_node_get_level(node); if (level < minlevel || nilfs_btree_node_get_nchildren(node) <= 0) return -ENOENT; found = nilfs_btree_node_lookup(node, key, &index); ptr = nilfs_btree_node_get_ptr(node, index, NILFS_BTREE_ROOT_NCHILDREN_MAX); path[level].bp_bh = NULL; path[level].bp_index = index; ncmax = nilfs_btree_nchildren_per_block(btree); while (--level >= minlevel) { ra = NULL; if (level == NILFS_BTREE_LEVEL_NODE_MIN && readahead) { p.node = nilfs_btree_get_node(btree, path, level + 1, &p.ncmax); p.index = index; p.max_ra_blocks = 7; ra = &p; } ret = __nilfs_btree_get_block(btree, ptr, &path[level].bp_bh, ra); if (ret < 0) return ret; node = nilfs_btree_get_nonroot_node(path, level); if (nilfs_btree_bad_node(btree, node, level)) return -EINVAL; if (!found) found = nilfs_btree_node_lookup(node, key, &index); else index = 0; if (index < ncmax) { ptr = nilfs_btree_node_get_ptr(node, index, ncmax); } else { WARN_ON(found || level != NILFS_BTREE_LEVEL_NODE_MIN); /* insert */ ptr = NILFS_BMAP_INVALID_PTR; } path[level].bp_index = index; } if (!found) return -ENOENT; if (ptrp != NULL) *ptrp = ptr; return 0; } static int nilfs_btree_do_lookup_last(const struct nilfs_bmap *btree, struct nilfs_btree_path *path, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node; __u64 ptr; int index, level, ncmax, ret; node = nilfs_btree_get_root(btree); index = nilfs_btree_node_get_nchildren(node) - 1; if (index < 0) return -ENOENT; level = nilfs_btree_node_get_level(node); ptr = nilfs_btree_node_get_ptr(node, index, NILFS_BTREE_ROOT_NCHILDREN_MAX); path[level].bp_bh = NULL; path[level].bp_index = index; ncmax = nilfs_btree_nchildren_per_block(btree); for (level--; level > 0; level--) { ret = nilfs_btree_get_block(btree, ptr, &path[level].bp_bh); if (ret < 0) return ret; node = nilfs_btree_get_nonroot_node(path, level); if (nilfs_btree_bad_node(btree, node, level)) return -EINVAL; index = nilfs_btree_node_get_nchildren(node) - 1; ptr = nilfs_btree_node_get_ptr(node, index, ncmax); path[level].bp_index = index; } if (keyp != NULL) *keyp = nilfs_btree_node_get_key(node, index); if (ptrp != NULL) *ptrp = ptr; return 0; } /** * nilfs_btree_get_next_key - get next valid key from btree path array * @btree: bmap struct of btree * @path: array of nilfs_btree_path struct * @minlevel: start level * @nextkey: place to store the next valid key * * Return Value: If a next key was found, 0 is returned. Otherwise, * -ENOENT is returned. */ static int nilfs_btree_get_next_key(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, int minlevel, __u64 *nextkey) { struct nilfs_btree_node *node; int maxlevel = nilfs_btree_height(btree) - 1; int index, next_adj, level; /* Next index is already set to bp_index for leaf nodes. */ next_adj = 0; for (level = minlevel; level <= maxlevel; level++) { if (level == maxlevel) node = nilfs_btree_get_root(btree); else node = nilfs_btree_get_nonroot_node(path, level); index = path[level].bp_index + next_adj; if (index < nilfs_btree_node_get_nchildren(node)) { /* Next key is in this node */ *nextkey = nilfs_btree_node_get_key(node, index); return 0; } /* For non-leaf nodes, next index is stored at bp_index + 1. */ next_adj = 1; } return -ENOENT; } static int nilfs_btree_lookup(const struct nilfs_bmap *btree, __u64 key, int level, __u64 *ptrp) { struct nilfs_btree_path *path; int ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, ptrp, level, 0); nilfs_btree_free_path(path); return ret; } static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, __u64 key, __u64 *ptrp, unsigned int maxblocks) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; struct inode *dat = NULL; __u64 ptr, ptr2; sector_t blocknr; int level = NILFS_BTREE_LEVEL_NODE_MIN; int ret, cnt, index, maxlevel, ncmax; struct nilfs_btree_readahead_info p; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, &ptr, level, 1); if (ret < 0) goto out; if (NILFS_BMAP_USE_VBN(btree)) { dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) goto dat_error; ptr = blocknr; } cnt = 1; if (cnt == maxblocks) goto end; maxlevel = nilfs_btree_height(btree) - 1; node = nilfs_btree_get_node(btree, path, level, &ncmax); index = path[level].bp_index + 1; for (;;) { while (index < nilfs_btree_node_get_nchildren(node)) { if (nilfs_btree_node_get_key(node, index) != key + cnt) goto end; ptr2 = nilfs_btree_node_get_ptr(node, index, ncmax); if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) goto end; index++; } if (level == maxlevel) break; /* look-up right sibling node */ p.node = nilfs_btree_get_node(btree, path, level + 1, &p.ncmax); p.index = path[level + 1].bp_index + 1; p.max_ra_blocks = 7; if (p.index >= nilfs_btree_node_get_nchildren(p.node) || nilfs_btree_node_get_key(p.node, p.index) != key + cnt) break; ptr2 = nilfs_btree_node_get_ptr(p.node, p.index, p.ncmax); path[level + 1].bp_index = p.index; brelse(path[level].bp_bh); path[level].bp_bh = NULL; ret = __nilfs_btree_get_block(btree, ptr2, &path[level].bp_bh, &p); if (ret < 0) goto out; node = nilfs_btree_get_nonroot_node(path, level); ncmax = nilfs_btree_nchildren_per_block(btree); index = 0; path[level].bp_index = index; } end: *ptrp = ptr; ret = cnt; out: nilfs_btree_free_path(path); return ret; dat_error: if (ret == -ENOENT) ret = -EINVAL; /* Notify bmap layer of metadata corruption */ goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 key) { if (level < nilfs_btree_height(btree) - 1) { do { nilfs_btree_node_set_key( nilfs_btree_get_nonroot_node(path, level), path[level].bp_index, key); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); } while ((path[level].bp_index == 0) && (++level < nilfs_btree_height(btree) - 1)); } /* root */ if (level == nilfs_btree_height(btree) - 1) { nilfs_btree_node_set_key(nilfs_btree_get_root(btree), path[level].bp_index, key); } } static void nilfs_btree_do_insert(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node; int ncblk; if (level < nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_nonroot_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_insert(node, path[level].bp_index, *keyp, *ptrp, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (path[level].bp_index == 0) nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); } else { node = nilfs_btree_get_root(btree); nilfs_btree_node_insert(node, path[level].bp_index, *keyp, *ptrp, NILFS_BTREE_ROOT_NCHILDREN_MAX); } } static void nilfs_btree_carry_left(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *left; int nchildren, lnchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); left = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); lnchildren = nilfs_btree_node_get_nchildren(left); ncblk = nilfs_btree_nchildren_per_block(btree); move = 0; n = (nchildren + lnchildren + 1) / 2 - lnchildren; if (n > path[level].bp_index) { /* move insert point */ n--; move = 1; } nilfs_btree_node_move_left(left, node, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); if (move) { brelse(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; path[level].bp_index += lnchildren; path[level + 1].bp_index--; } else { brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; path[level].bp_index -= n; } nilfs_btree_do_insert(btree, path, level, keyp, ptrp); } static void nilfs_btree_carry_right(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int nchildren, rnchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); rnchildren = nilfs_btree_node_get_nchildren(right); ncblk = nilfs_btree_nchildren_per_block(btree); move = 0; n = (nchildren + rnchildren + 1) / 2 - rnchildren; if (n > nchildren - path[level].bp_index) { /* move insert point */ n--; move = 1; } nilfs_btree_node_move_right(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); path[level + 1].bp_index++; nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(right, 0)); path[level + 1].bp_index--; if (move) { brelse(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; path[level].bp_index -= nilfs_btree_node_get_nchildren(node); path[level + 1].bp_index++; } else { brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; } nilfs_btree_do_insert(btree, path, level, keyp, ptrp); } static void nilfs_btree_split(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int nchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); ncblk = nilfs_btree_nchildren_per_block(btree); move = 0; n = (nchildren + 1) / 2; if (n > nchildren - path[level].bp_index) { n--; move = 1; } nilfs_btree_node_move_right(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); if (move) { path[level].bp_index -= nilfs_btree_node_get_nchildren(node); nilfs_btree_node_insert(right, path[level].bp_index, *keyp, *ptrp, ncblk); *keyp = nilfs_btree_node_get_key(right, 0); *ptrp = path[level].bp_newreq.bpr_ptr; brelse(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; } else { nilfs_btree_do_insert(btree, path, level, keyp, ptrp); *keyp = nilfs_btree_node_get_key(right, 0); *ptrp = path[level].bp_newreq.bpr_ptr; brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; } path[level + 1].bp_index++; } static void nilfs_btree_grow(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *root, *child; int n, ncblk; root = nilfs_btree_get_root(btree); child = nilfs_btree_get_sib_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); n = nilfs_btree_node_get_nchildren(root); nilfs_btree_node_move_right(root, child, n, NILFS_BTREE_ROOT_NCHILDREN_MAX, ncblk); nilfs_btree_node_set_level(root, level + 1); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; nilfs_btree_do_insert(btree, path, level, keyp, ptrp); *keyp = nilfs_btree_node_get_key(child, 0); *ptrp = path[level].bp_newreq.bpr_ptr; } static __u64 nilfs_btree_find_near(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path) { struct nilfs_btree_node *node; int level, ncmax; if (path == NULL) return NILFS_BMAP_INVALID_PTR; /* left sibling */ level = NILFS_BTREE_LEVEL_NODE_MIN; if (path[level].bp_index > 0) { node = nilfs_btree_get_node(btree, path, level, &ncmax); return nilfs_btree_node_get_ptr(node, path[level].bp_index - 1, ncmax); } /* parent */ level = NILFS_BTREE_LEVEL_NODE_MIN + 1; if (level <= nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_node(btree, path, level, &ncmax); return nilfs_btree_node_get_ptr(node, path[level].bp_index, ncmax); } return NILFS_BMAP_INVALID_PTR; } static __u64 nilfs_btree_find_target_v(const struct nilfs_bmap *btree, const struct nilfs_btree_path *path, __u64 key) { __u64 ptr; ptr = nilfs_bmap_find_target_seq(btree, key); if (ptr != NILFS_BMAP_INVALID_PTR) /* sequential access */ return ptr; ptr = nilfs_btree_find_near(btree, path); if (ptr != NILFS_BMAP_INVALID_PTR) /* near */ return ptr; /* block group */ return nilfs_bmap_find_target_in_group(btree); } static int nilfs_btree_prepare_insert(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int *levelp, __u64 key, __u64 ptr, struct nilfs_bmap_stats *stats) { struct buffer_head *bh; struct nilfs_btree_node *node, *parent, *sib; __u64 sibptr; int pindex, level, ncmax, ncblk, ret; struct inode *dat = NULL; stats->bs_nblocks = 0; level = NILFS_BTREE_LEVEL_DATA; /* allocate a new ptr for data block */ if (NILFS_BMAP_USE_VBN(btree)) { path[level].bp_newreq.bpr_ptr = nilfs_btree_find_target_v(btree, path, key); dat = nilfs_bmap_get_dat(btree); } ret = nilfs_bmap_prepare_alloc_ptr(btree, &path[level].bp_newreq, dat); if (ret < 0) goto err_out_data; ncblk = nilfs_btree_nchildren_per_block(btree); for (level = NILFS_BTREE_LEVEL_NODE_MIN; level < nilfs_btree_height(btree) - 1; level++) { node = nilfs_btree_get_nonroot_node(path, level); if (nilfs_btree_node_get_nchildren(node) < ncblk) { path[level].bp_op = nilfs_btree_do_insert; stats->bs_nblocks++; goto out; } parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); pindex = path[level + 1].bp_index; /* left sibling */ if (pindex > 0) { sibptr = nilfs_btree_node_get_ptr(parent, pindex - 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_child_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) < ncblk) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_carry_left; stats->bs_nblocks++; goto out; } else { brelse(bh); } } /* right sibling */ if (pindex < nilfs_btree_node_get_nchildren(parent) - 1) { sibptr = nilfs_btree_node_get_ptr(parent, pindex + 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_child_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) < ncblk) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_carry_right; stats->bs_nblocks++; goto out; } else { brelse(bh); } } /* split */ path[level].bp_newreq.bpr_ptr = path[level - 1].bp_newreq.bpr_ptr + 1; ret = nilfs_bmap_prepare_alloc_ptr(btree, &path[level].bp_newreq, dat); if (ret < 0) goto err_out_child_node; ret = nilfs_btree_get_new_block(btree, path[level].bp_newreq.bpr_ptr, &bh); if (ret < 0) goto err_out_curr_node; stats->bs_nblocks++; sib = (struct nilfs_btree_node *)bh->b_data; nilfs_btree_node_init(sib, 0, level, 0, ncblk, NULL, NULL); path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_split; } /* root */ node = nilfs_btree_get_root(btree); if (nilfs_btree_node_get_nchildren(node) < NILFS_BTREE_ROOT_NCHILDREN_MAX) { path[level].bp_op = nilfs_btree_do_insert; stats->bs_nblocks++; goto out; } /* grow */ path[level].bp_newreq.bpr_ptr = path[level - 1].bp_newreq.bpr_ptr + 1; ret = nilfs_bmap_prepare_alloc_ptr(btree, &path[level].bp_newreq, dat); if (ret < 0) goto err_out_child_node; ret = nilfs_btree_get_new_block(btree, path[level].bp_newreq.bpr_ptr, &bh); if (ret < 0) goto err_out_curr_node; nilfs_btree_node_init((struct nilfs_btree_node *)bh->b_data, 0, level, 0, ncblk, NULL, NULL); path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_grow; level++; path[level].bp_op = nilfs_btree_do_insert; /* a newly-created node block and a data block are added */ stats->bs_nblocks += 2; /* success */ out: *levelp = level; return ret; /* error */ err_out_curr_node: nilfs_bmap_abort_alloc_ptr(btree, &path[level].bp_newreq, dat); err_out_child_node: for (level--; level > NILFS_BTREE_LEVEL_DATA; level--) { nilfs_btnode_delete(path[level].bp_sib_bh); nilfs_bmap_abort_alloc_ptr(btree, &path[level].bp_newreq, dat); } nilfs_bmap_abort_alloc_ptr(btree, &path[level].bp_newreq, dat); err_out_data: *levelp = level; stats->bs_nblocks = 0; return ret; } static void nilfs_btree_commit_insert(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int maxlevel, __u64 key, __u64 ptr) { struct inode *dat = NULL; int level; set_buffer_nilfs_volatile((struct buffer_head *)((unsigned long)ptr)); ptr = path[NILFS_BTREE_LEVEL_DATA].bp_newreq.bpr_ptr; if (NILFS_BMAP_USE_VBN(btree)) { nilfs_bmap_set_target_v(btree, key, ptr); dat = nilfs_bmap_get_dat(btree); } for (level = NILFS_BTREE_LEVEL_NODE_MIN; level <= maxlevel; level++) { nilfs_bmap_commit_alloc_ptr(btree, &path[level - 1].bp_newreq, dat); path[level].bp_op(btree, path, level, &key, &ptr); } if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); } static int nilfs_btree_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr) { struct nilfs_btree_path *path; struct nilfs_bmap_stats stats; int level, ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, NULL, NILFS_BTREE_LEVEL_NODE_MIN, 0); if (ret != -ENOENT) { if (ret == 0) ret = -EEXIST; goto out; } ret = nilfs_btree_prepare_insert(btree, path, &level, key, ptr, &stats); if (ret < 0) goto out; nilfs_btree_commit_insert(btree, path, level, key, ptr); nilfs_inode_add_blocks(btree->b_inode, stats.bs_nblocks); out: nilfs_btree_free_path(path); return ret; } static void nilfs_btree_do_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node; int ncblk; if (level < nilfs_btree_height(btree) - 1) { node = nilfs_btree_get_nonroot_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_delete(node, path[level].bp_index, keyp, ptrp, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (path[level].bp_index == 0) nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); } else { node = nilfs_btree_get_root(btree); nilfs_btree_node_delete(node, path[level].bp_index, keyp, ptrp, NILFS_BTREE_ROOT_NCHILDREN_MAX); } } static void nilfs_btree_borrow_left(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *left; int nchildren, lnchildren, n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); left = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); lnchildren = nilfs_btree_node_get_nchildren(left); ncblk = nilfs_btree_nchildren_per_block(btree); n = (nchildren + lnchildren) / 2 - nchildren; nilfs_btree_node_move_right(left, node, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(node, 0)); brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; path[level].bp_index += n; } static void nilfs_btree_borrow_right(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int nchildren, rnchildren, n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); nchildren = nilfs_btree_node_get_nchildren(node); rnchildren = nilfs_btree_node_get_nchildren(right); ncblk = nilfs_btree_nchildren_per_block(btree); n = (nchildren + rnchildren) / 2 - nchildren; nilfs_btree_node_move_left(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); path[level + 1].bp_index++; nilfs_btree_promote_key(btree, path, level + 1, nilfs_btree_node_get_key(right, 0)); path[level + 1].bp_index--; brelse(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; } static void nilfs_btree_concat_left(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *left; int n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); left = nilfs_btree_get_sib_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); n = nilfs_btree_node_get_nchildren(node); nilfs_btree_node_move_left(left, node, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); nilfs_btnode_delete(path[level].bp_bh); path[level].bp_bh = path[level].bp_sib_bh; path[level].bp_sib_bh = NULL; path[level].bp_index += nilfs_btree_node_get_nchildren(left); } static void nilfs_btree_concat_right(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; int n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); node = nilfs_btree_get_nonroot_node(path, level); right = nilfs_btree_get_sib_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); n = nilfs_btree_node_get_nchildren(right); nilfs_btree_node_move_left(node, right, n, ncblk, ncblk); if (!buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); nilfs_btnode_delete(path[level].bp_sib_bh); path[level].bp_sib_bh = NULL; path[level + 1].bp_index++; } static void nilfs_btree_shrink(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *root, *child; int n, ncblk; nilfs_btree_do_delete(btree, path, level, keyp, ptrp); root = nilfs_btree_get_root(btree); child = nilfs_btree_get_nonroot_node(path, level); ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_delete(root, 0, NULL, NULL, NILFS_BTREE_ROOT_NCHILDREN_MAX); nilfs_btree_node_set_level(root, level); n = nilfs_btree_node_get_nchildren(child); nilfs_btree_node_move_left(root, child, n, NILFS_BTREE_ROOT_NCHILDREN_MAX, ncblk); nilfs_btnode_delete(path[level].bp_bh); path[level].bp_bh = NULL; } static void nilfs_btree_nop(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) { } static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int *levelp, struct nilfs_bmap_stats *stats, struct inode *dat) { struct buffer_head *bh; struct nilfs_btree_node *node, *parent, *sib; __u64 sibptr; int pindex, dindex, level, ncmin, ncmax, ncblk, ret; ret = 0; stats->bs_nblocks = 0; ncmin = NILFS_BTREE_NODE_NCHILDREN_MIN(nilfs_btree_node_size(btree)); ncblk = nilfs_btree_nchildren_per_block(btree); for (level = NILFS_BTREE_LEVEL_NODE_MIN, dindex = path[level].bp_index; level < nilfs_btree_height(btree) - 1; level++) { node = nilfs_btree_get_nonroot_node(path, level); path[level].bp_oldreq.bpr_ptr = nilfs_btree_node_get_ptr(node, dindex, ncblk); ret = nilfs_bmap_prepare_end_ptr(btree, &path[level].bp_oldreq, dat); if (ret < 0) goto err_out_child_node; if (nilfs_btree_node_get_nchildren(node) > ncmin) { path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; goto out; } parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); pindex = path[level + 1].bp_index; dindex = pindex; if (pindex > 0) { /* left sibling */ sibptr = nilfs_btree_node_get_ptr(parent, pindex - 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_curr_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) > ncmin) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_borrow_left; stats->bs_nblocks++; goto out; } else { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_concat_left; stats->bs_nblocks++; /* continue; */ } } else if (pindex < nilfs_btree_node_get_nchildren(parent) - 1) { /* right sibling */ sibptr = nilfs_btree_node_get_ptr(parent, pindex + 1, ncmax); ret = nilfs_btree_get_block(btree, sibptr, &bh); if (ret < 0) goto err_out_curr_node; sib = (struct nilfs_btree_node *)bh->b_data; if (nilfs_btree_node_get_nchildren(sib) > ncmin) { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_borrow_right; stats->bs_nblocks++; goto out; } else { path[level].bp_sib_bh = bh; path[level].bp_op = nilfs_btree_concat_right; stats->bs_nblocks++; /* * When merging right sibling node * into the current node, pointer to * the right sibling node must be * terminated instead. The adjustment * below is required for that. */ dindex = pindex + 1; /* continue; */ } } else { /* no siblings */ /* the only child of the root node */ WARN_ON(level != nilfs_btree_height(btree) - 2); if (nilfs_btree_node_get_nchildren(node) - 1 <= NILFS_BTREE_ROOT_NCHILDREN_MAX) { path[level].bp_op = nilfs_btree_shrink; stats->bs_nblocks += 2; level++; path[level].bp_op = nilfs_btree_nop; goto shrink_root_child; } else { path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; goto out; } } } /* child of the root node is deleted */ path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; shrink_root_child: node = nilfs_btree_get_root(btree); path[level].bp_oldreq.bpr_ptr = nilfs_btree_node_get_ptr(node, dindex, NILFS_BTREE_ROOT_NCHILDREN_MAX); ret = nilfs_bmap_prepare_end_ptr(btree, &path[level].bp_oldreq, dat); if (ret < 0) goto err_out_child_node; /* success */ out: *levelp = level; return ret; /* error */ err_out_curr_node: nilfs_bmap_abort_end_ptr(btree, &path[level].bp_oldreq, dat); err_out_child_node: for (level--; level >= NILFS_BTREE_LEVEL_NODE_MIN; level--) { brelse(path[level].bp_sib_bh); nilfs_bmap_abort_end_ptr(btree, &path[level].bp_oldreq, dat); } *levelp = level; stats->bs_nblocks = 0; return ret; } static void nilfs_btree_commit_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int maxlevel, struct inode *dat) { int level; for (level = NILFS_BTREE_LEVEL_NODE_MIN; level <= maxlevel; level++) { nilfs_bmap_commit_end_ptr(btree, &path[level].bp_oldreq, dat); path[level].bp_op(btree, path, level, NULL, NULL); } if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); } static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key) { struct nilfs_btree_path *path; struct nilfs_bmap_stats stats; struct inode *dat; int level, ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, NULL, NILFS_BTREE_LEVEL_NODE_MIN, 0); if (ret < 0) goto out; dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; ret = nilfs_btree_prepare_delete(btree, path, &level, &stats, dat); if (ret < 0) goto out; nilfs_btree_commit_delete(btree, path, level, dat); nilfs_inode_sub_blocks(btree->b_inode, stats.bs_nblocks); out: nilfs_btree_free_path(path); return ret; } static int nilfs_btree_seek_key(const struct nilfs_bmap *btree, __u64 start, __u64 *keyp) { struct nilfs_btree_path *path; const int minlevel = NILFS_BTREE_LEVEL_NODE_MIN; int ret; path = nilfs_btree_alloc_path(); if (!path) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, start, NULL, minlevel, 0); if (!ret) *keyp = start; else if (ret == -ENOENT) ret = nilfs_btree_get_next_key(btree, path, minlevel, keyp); nilfs_btree_free_path(path); return ret; } static int nilfs_btree_last_key(const struct nilfs_bmap *btree, __u64 *keyp) { struct nilfs_btree_path *path; int ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup_last(btree, path, keyp, NULL); nilfs_btree_free_path(path); return ret; } static int nilfs_btree_check_delete(struct nilfs_bmap *btree, __u64 key) { struct buffer_head *bh; struct nilfs_btree_node *root, *node; __u64 maxkey, nextmaxkey; __u64 ptr; int nchildren, ret; root = nilfs_btree_get_root(btree); switch (nilfs_btree_height(btree)) { case 2: bh = NULL; node = root; break; case 3: nchildren = nilfs_btree_node_get_nchildren(root); if (nchildren > 1) return 0; ptr = nilfs_btree_node_get_ptr(root, nchildren - 1, NILFS_BTREE_ROOT_NCHILDREN_MAX); ret = nilfs_btree_get_block(btree, ptr, &bh); if (ret < 0) return ret; node = (struct nilfs_btree_node *)bh->b_data; break; default: return 0; } nchildren = nilfs_btree_node_get_nchildren(node); maxkey = nilfs_btree_node_get_key(node, nchildren - 1); nextmaxkey = (nchildren > 1) ? nilfs_btree_node_get_key(node, nchildren - 2) : 0; brelse(bh); return (maxkey == key) && (nextmaxkey < NILFS_BMAP_LARGE_LOW); } static int nilfs_btree_gather_data(struct nilfs_bmap *btree, __u64 *keys, __u64 *ptrs, int nitems) { struct buffer_head *bh; struct nilfs_btree_node *node, *root; __le64 *dkeys; __le64 *dptrs; __u64 ptr; int nchildren, ncmax, i, ret; root = nilfs_btree_get_root(btree); switch (nilfs_btree_height(btree)) { case 2: bh = NULL; node = root; ncmax = NILFS_BTREE_ROOT_NCHILDREN_MAX; break; case 3: nchildren = nilfs_btree_node_get_nchildren(root); WARN_ON(nchildren > 1); ptr = nilfs_btree_node_get_ptr(root, nchildren - 1, NILFS_BTREE_ROOT_NCHILDREN_MAX); ret = nilfs_btree_get_block(btree, ptr, &bh); if (ret < 0) return ret; node = (struct nilfs_btree_node *)bh->b_data; ncmax = nilfs_btree_nchildren_per_block(btree); break; default: node = NULL; return -EINVAL; } nchildren = nilfs_btree_node_get_nchildren(node); if (nchildren < nitems) nitems = nchildren; dkeys = nilfs_btree_node_dkeys(node); dptrs = nilfs_btree_node_dptrs(node, ncmax); for (i = 0; i < nitems; i++) { keys[i] = le64_to_cpu(dkeys[i]); ptrs[i] = le64_to_cpu(dptrs[i]); } brelse(bh); return nitems; } static int nilfs_btree_prepare_convert_and_insert(struct nilfs_bmap *btree, __u64 key, union nilfs_bmap_ptr_req *dreq, union nilfs_bmap_ptr_req *nreq, struct buffer_head **bhp, struct nilfs_bmap_stats *stats) { struct buffer_head *bh; struct inode *dat = NULL; int ret; stats->bs_nblocks = 0; /* for data */ /* cannot find near ptr */ if (NILFS_BMAP_USE_VBN(btree)) { dreq->bpr_ptr = nilfs_btree_find_target_v(btree, NULL, key); dat = nilfs_bmap_get_dat(btree); } ret = nilfs_attach_btree_node_cache(&NILFS_BMAP_I(btree)->vfs_inode); if (ret < 0) return ret; ret = nilfs_bmap_prepare_alloc_ptr(btree, dreq, dat); if (ret < 0) return ret; *bhp = NULL; stats->bs_nblocks++; if (nreq != NULL) { nreq->bpr_ptr = dreq->bpr_ptr + 1; ret = nilfs_bmap_prepare_alloc_ptr(btree, nreq, dat); if (ret < 0) goto err_out_dreq; ret = nilfs_btree_get_new_block(btree, nreq->bpr_ptr, &bh); if (ret < 0) goto err_out_nreq; *bhp = bh; stats->bs_nblocks++; } /* success */ return 0; /* error */ err_out_nreq: nilfs_bmap_abort_alloc_ptr(btree, nreq, dat); err_out_dreq: nilfs_bmap_abort_alloc_ptr(btree, dreq, dat); stats->bs_nblocks = 0; return ret; } static void nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n, union nilfs_bmap_ptr_req *dreq, union nilfs_bmap_ptr_req *nreq, struct buffer_head *bh) { struct nilfs_btree_node *node; struct inode *dat; __u64 tmpptr; int ncblk; /* free resources */ if (btree->b_ops->bop_clear != NULL) btree->b_ops->bop_clear(btree); /* ptr must be a pointer to a buffer head. */ set_buffer_nilfs_volatile((struct buffer_head *)((unsigned long)ptr)); /* convert and insert */ dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; __nilfs_btree_init(btree); if (nreq != NULL) { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); nilfs_bmap_commit_alloc_ptr(btree, nreq, dat); /* create child node at level 1 */ node = (struct nilfs_btree_node *)bh->b_data; ncblk = nilfs_btree_nchildren_per_block(btree); nilfs_btree_node_init(node, 0, 1, n, ncblk, keys, ptrs); nilfs_btree_node_insert(node, n, key, dreq->bpr_ptr, ncblk); if (!buffer_dirty(bh)) mark_buffer_dirty(bh); if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); brelse(bh); /* create root node at level 2 */ node = nilfs_btree_get_root(btree); tmpptr = nreq->bpr_ptr; nilfs_btree_node_init(node, NILFS_BTREE_NODE_ROOT, 2, 1, NILFS_BTREE_ROOT_NCHILDREN_MAX, &keys[0], &tmpptr); } else { nilfs_bmap_commit_alloc_ptr(btree, dreq, dat); /* create root node at level 1 */ node = nilfs_btree_get_root(btree); nilfs_btree_node_init(node, NILFS_BTREE_NODE_ROOT, 1, n, NILFS_BTREE_ROOT_NCHILDREN_MAX, keys, ptrs); nilfs_btree_node_insert(node, n, key, dreq->bpr_ptr, NILFS_BTREE_ROOT_NCHILDREN_MAX); if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); } if (NILFS_BMAP_USE_VBN(btree)) nilfs_bmap_set_target_v(btree, key, dreq->bpr_ptr); } /** * nilfs_btree_convert_and_insert - Convert and insert entries into a B-tree * @btree: NILFS B-tree structure * @key: Key of the new entry to be inserted * @ptr: Pointer (block number) associated with the key to be inserted * @keys: Array of keys to be inserted in addition to @key * @ptrs: Array of pointers associated with @keys * @n: Number of keys and pointers in @keys and @ptrs * * This function is used to insert a new entry specified by @key and @ptr, * along with additional entries specified by @keys and @ptrs arrays, into a * NILFS B-tree. * It prepares the necessary changes by allocating the required blocks and any * necessary intermediate nodes. It converts configurations from other forms of * block mapping (the one that currently exists is direct mapping) to a B-tree. * * Return: 0 on success or a negative error code on failure. */ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n) { struct buffer_head *bh = NULL; union nilfs_bmap_ptr_req dreq, nreq, *di, *ni; struct nilfs_bmap_stats stats; int ret; if (n + 1 <= NILFS_BTREE_ROOT_NCHILDREN_MAX) { di = &dreq; ni = NULL; } else if ((n + 1) <= NILFS_BTREE_NODE_NCHILDREN_MAX( nilfs_btree_node_size(btree))) { di = &dreq; ni = &nreq; } else { di = NULL; ni = NULL; BUG(); } ret = nilfs_btree_prepare_convert_and_insert(btree, key, di, ni, &bh, &stats); if (ret < 0) return ret; nilfs_btree_commit_convert_and_insert(btree, key, ptr, keys, ptrs, n, di, ni, bh); nilfs_inode_add_blocks(btree->b_inode, stats.bs_nblocks); return 0; } static int nilfs_btree_propagate_p(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head *bh) { while ((++level < nilfs_btree_height(btree) - 1) && !buffer_dirty(path[level].bp_bh)) mark_buffer_dirty(path[level].bp_bh); return 0; } static int nilfs_btree_prepare_update_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct inode *dat) { struct nilfs_btree_node *parent; int ncmax, ret; parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); path[level].bp_oldreq.bpr_ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); path[level].bp_newreq.bpr_ptr = path[level].bp_oldreq.bpr_ptr + 1; ret = nilfs_dat_prepare_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req); if (ret < 0) return ret; if (buffer_nilfs_node(path[level].bp_bh)) { path[level].bp_ctxt.oldkey = path[level].bp_oldreq.bpr_ptr; path[level].bp_ctxt.newkey = path[level].bp_newreq.bpr_ptr; path[level].bp_ctxt.bh = path[level].bp_bh; ret = nilfs_btnode_prepare_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) { nilfs_dat_abort_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req); return ret; } } return 0; } static void nilfs_btree_commit_update_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct inode *dat) { struct nilfs_btree_node *parent; int ncmax; nilfs_dat_commit_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req, btree->b_ptr_type == NILFS_BMAP_PTR_VS); if (buffer_nilfs_node(path[level].bp_bh)) { nilfs_btnode_commit_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); path[level].bp_bh = path[level].bp_ctxt.bh; } set_buffer_nilfs_volatile(path[level].bp_bh); parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); nilfs_btree_node_set_ptr(parent, path[level + 1].bp_index, path[level].bp_newreq.bpr_ptr, ncmax); } static void nilfs_btree_abort_update_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct inode *dat) { nilfs_dat_abort_update(dat, &path[level].bp_oldreq.bpr_req, &path[level].bp_newreq.bpr_req); if (buffer_nilfs_node(path[level].bp_bh)) nilfs_btnode_abort_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); } static int nilfs_btree_prepare_propagate_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int minlevel, int *maxlevelp, struct inode *dat) { int level, ret; level = minlevel; if (!buffer_nilfs_volatile(path[level].bp_bh)) { ret = nilfs_btree_prepare_update_v(btree, path, level, dat); if (ret < 0) return ret; } while ((++level < nilfs_btree_height(btree) - 1) && !buffer_dirty(path[level].bp_bh)) { WARN_ON(buffer_nilfs_volatile(path[level].bp_bh)); ret = nilfs_btree_prepare_update_v(btree, path, level, dat); if (ret < 0) goto out; } /* success */ *maxlevelp = level - 1; return 0; /* error */ out: while (--level > minlevel) nilfs_btree_abort_update_v(btree, path, level, dat); if (!buffer_nilfs_volatile(path[level].bp_bh)) nilfs_btree_abort_update_v(btree, path, level, dat); return ret; } static void nilfs_btree_commit_propagate_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int minlevel, int maxlevel, struct buffer_head *bh, struct inode *dat) { int level; if (!buffer_nilfs_volatile(path[minlevel].bp_bh)) nilfs_btree_commit_update_v(btree, path, minlevel, dat); for (level = minlevel + 1; level <= maxlevel; level++) nilfs_btree_commit_update_v(btree, path, level, dat); } static int nilfs_btree_propagate_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head *bh) { int maxlevel = 0, ret; struct nilfs_btree_node *parent; struct inode *dat = nilfs_bmap_get_dat(btree); __u64 ptr; int ncmax; get_bh(bh); path[level].bp_bh = bh; ret = nilfs_btree_prepare_propagate_v(btree, path, level, &maxlevel, dat); if (ret < 0) goto out; if (buffer_nilfs_volatile(path[level].bp_bh)) { parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); ret = nilfs_dat_mark_dirty(dat, ptr); if (ret < 0) goto out; } nilfs_btree_commit_propagate_v(btree, path, level, maxlevel, bh, dat); out: brelse(path[level].bp_bh); path[level].bp_bh = NULL; return ret; } static int nilfs_btree_propagate(struct nilfs_bmap *btree, struct buffer_head *bh) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; __u64 key; int level, ret; WARN_ON(!buffer_dirty(bh)); path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; if (buffer_nilfs_node(bh)) { node = (struct nilfs_btree_node *)bh->b_data; key = nilfs_btree_node_get_key(node, 0); level = nilfs_btree_node_get_level(node); } else { key = nilfs_bmap_data_get_key(btree, bh); level = NILFS_BTREE_LEVEL_DATA; } ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0); if (ret < 0) { if (unlikely(ret == -ENOENT)) nilfs_crit(btree->b_inode->i_sb, "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d", btree->b_inode->i_ino, (unsigned long long)key, level); goto out; } ret = NILFS_BMAP_USE_VBN(btree) ? nilfs_btree_propagate_v(btree, path, level, bh) : nilfs_btree_propagate_p(btree, path, level, bh); out: nilfs_btree_free_path(path); return ret; } static int nilfs_btree_propagate_gc(struct nilfs_bmap *btree, struct buffer_head *bh) { return nilfs_dat_mark_dirty(nilfs_bmap_get_dat(btree), bh->b_blocknr); } static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, struct list_head *lists, struct buffer_head *bh) { struct list_head *head; struct buffer_head *cbh; struct nilfs_btree_node *node, *cnode; __u64 key, ckey; int level; get_bh(bh); node = (struct nilfs_btree_node *)bh->b_data; key = nilfs_btree_node_get_key(node, 0); level = nilfs_btree_node_get_level(node); if (level < NILFS_BTREE_LEVEL_NODE_MIN || level >= NILFS_BTREE_LEVEL_MAX) { dump_stack(); nilfs_warn(btree->b_inode->i_sb, "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)", level, (unsigned long long)key, btree->b_inode->i_ino, (unsigned long long)bh->b_blocknr); return; } list_for_each(head, &lists[level]) { cbh = list_entry(head, struct buffer_head, b_assoc_buffers); cnode = (struct nilfs_btree_node *)cbh->b_data; ckey = nilfs_btree_node_get_key(cnode, 0); if (key < ckey) break; } list_add_tail(&bh->b_assoc_buffers, head); } static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, struct list_head *listp) { struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; struct address_space *btcache = btnc_inode->i_mapping; struct list_head lists[NILFS_BTREE_LEVEL_MAX]; struct folio_batch fbatch; struct buffer_head *bh, *head; pgoff_t index = 0; int level, i; for (level = NILFS_BTREE_LEVEL_NODE_MIN; level < NILFS_BTREE_LEVEL_MAX; level++) INIT_LIST_HEAD(&lists[level]); folio_batch_init(&fbatch); while (filemap_get_folios_tag(btcache, &index, (pgoff_t)-1, PAGECACHE_TAG_DIRTY, &fbatch)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { bh = head = folio_buffers(fbatch.folios[i]); do { if (buffer_dirty(bh)) nilfs_btree_add_dirty_buffer(btree, lists, bh); } while ((bh = bh->b_this_page) != head); } folio_batch_release(&fbatch); cond_resched(); } for (level = NILFS_BTREE_LEVEL_NODE_MIN; level < NILFS_BTREE_LEVEL_MAX; level++) list_splice_tail(&lists[level], listp); } static int nilfs_btree_assign_p(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_node *parent; __u64 key; __u64 ptr; int ncmax, ret; parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); if (buffer_nilfs_node(*bh)) { path[level].bp_ctxt.oldkey = ptr; path[level].bp_ctxt.newkey = blocknr; path[level].bp_ctxt.bh = *bh; ret = nilfs_btnode_prepare_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) return ret; nilfs_btnode_commit_change_key( NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); *bh = path[level].bp_ctxt.bh; } nilfs_btree_node_set_ptr(parent, path[level + 1].bp_index, blocknr, ncmax); key = nilfs_btree_node_get_key(parent, path[level + 1].bp_index); /* on-disk format */ binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = level; memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } static int nilfs_btree_assign_v(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_node *parent; struct inode *dat = nilfs_bmap_get_dat(btree); __u64 key; __u64 ptr; union nilfs_bmap_ptr_req req; int ncmax, ret; parent = nilfs_btree_get_node(btree, path, level + 1, &ncmax); ptr = nilfs_btree_node_get_ptr(parent, path[level + 1].bp_index, ncmax); req.bpr_ptr = ptr; ret = nilfs_dat_prepare_start(dat, &req.bpr_req); if (ret < 0) return ret; nilfs_dat_commit_start(dat, &req.bpr_req, blocknr); key = nilfs_btree_node_get_key(parent, path[level + 1].bp_index); /* on-disk format */ binfo->bi_v.bi_vblocknr = cpu_to_le64(ptr); binfo->bi_v.bi_blkoff = cpu_to_le64(key); return 0; } static int nilfs_btree_assign(struct nilfs_bmap *btree, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_path *path; struct nilfs_btree_node *node; __u64 key; int level, ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; if (buffer_nilfs_node(*bh)) { node = (struct nilfs_btree_node *)(*bh)->b_data; key = nilfs_btree_node_get_key(node, 0); level = nilfs_btree_node_get_level(node); } else { key = nilfs_bmap_data_get_key(btree, *bh); level = NILFS_BTREE_LEVEL_DATA; } ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0); if (ret < 0) { WARN_ON(ret == -ENOENT); goto out; } ret = NILFS_BMAP_USE_VBN(btree) ? nilfs_btree_assign_v(btree, path, level, bh, blocknr, binfo) : nilfs_btree_assign_p(btree, path, level, bh, blocknr, binfo); out: nilfs_btree_free_path(path); return ret; } static int nilfs_btree_assign_gc(struct nilfs_bmap *btree, struct buffer_head **bh, sector_t blocknr, union nilfs_binfo *binfo) { struct nilfs_btree_node *node; __u64 key; int ret; ret = nilfs_dat_move(nilfs_bmap_get_dat(btree), (*bh)->b_blocknr, blocknr); if (ret < 0) return ret; if (buffer_nilfs_node(*bh)) { node = (struct nilfs_btree_node *)(*bh)->b_data; key = nilfs_btree_node_get_key(node, 0); } else key = nilfs_bmap_data_get_key(btree, *bh); /* on-disk format */ binfo->bi_v.bi_vblocknr = cpu_to_le64((*bh)->b_blocknr); binfo->bi_v.bi_blkoff = cpu_to_le64(key); return 0; } static int nilfs_btree_mark(struct nilfs_bmap *btree, __u64 key, int level) { struct buffer_head *bh; struct nilfs_btree_path *path; __u64 ptr; int ret; path = nilfs_btree_alloc_path(); if (path == NULL) return -ENOMEM; ret = nilfs_btree_do_lookup(btree, path, key, &ptr, level + 1, 0); if (ret < 0) { WARN_ON(ret == -ENOENT); goto out; } ret = nilfs_btree_get_block(btree, ptr, &bh); if (ret < 0) { WARN_ON(ret == -ENOENT); goto out; } if (!buffer_dirty(bh)) mark_buffer_dirty(bh); brelse(bh); if (!nilfs_bmap_dirty(btree)) nilfs_bmap_set_dirty(btree); out: nilfs_btree_free_path(path); return ret; } static const struct nilfs_bmap_operations nilfs_btree_ops = { .bop_lookup = nilfs_btree_lookup, .bop_lookup_contig = nilfs_btree_lookup_contig, .bop_insert = nilfs_btree_insert, .bop_delete = nilfs_btree_delete, .bop_clear = NULL, .bop_propagate = nilfs_btree_propagate, .bop_lookup_dirty_buffers = nilfs_btree_lookup_dirty_buffers, .bop_assign = nilfs_btree_assign, .bop_mark = nilfs_btree_mark, .bop_seek_key = nilfs_btree_seek_key, .bop_last_key = nilfs_btree_last_key, .bop_check_insert = NULL, .bop_check_delete = nilfs_btree_check_delete, .bop_gather_data = nilfs_btree_gather_data, }; static const struct nilfs_bmap_operations nilfs_btree_ops_gc = { .bop_lookup = NULL, .bop_lookup_contig = NULL, .bop_insert = NULL, .bop_delete = NULL, .bop_clear = NULL, .bop_propagate = nilfs_btree_propagate_gc, .bop_lookup_dirty_buffers = nilfs_btree_lookup_dirty_buffers, .bop_assign = nilfs_btree_assign_gc, .bop_mark = NULL, .bop_seek_key = NULL, .bop_last_key = NULL, .bop_check_insert = NULL, .bop_check_delete = NULL, .bop_gather_data = NULL, }; static void __nilfs_btree_init(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); } int nilfs_btree_init(struct nilfs_bmap *bmap) { int ret = 0; __nilfs_btree_init(bmap); if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode)) ret = -EIO; else ret = nilfs_attach_btree_node_cache( &NILFS_BMAP_I(bmap)->vfs_inode); return ret; } void nilfs_btree_init_gc(struct nilfs_bmap *bmap) { bmap->b_ops = &nilfs_btree_ops_gc; bmap->b_nchildren_per_block = NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap)); } |
| 3 1 1 1 4 1 3 4 1 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 | /* * LZ4 - Fast LZ compression algorithm * Copyright (C) 2011 - 2016, Yann Collet. * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php) * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are * met: * * Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * * Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following disclaimer * in the documentation and/or other materials provided with the * distribution. * 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. * You can contact the author at : * - LZ4 homepage : http://www.lz4.org * - LZ4 source repository : https://github.com/lz4/lz4 * * Changed for kernel usage by: * Sven Schmidt <4sschmid@informatik.uni-hamburg.de> */ /*-************************************ * Dependencies **************************************/ #include <linux/lz4.h> #include "lz4defs.h" #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <asm/unaligned.h> /*-***************************** * Decompression functions *******************************/ #define DEBUGLOG(l, ...) {} /* disabled */ #ifndef assert #define assert(condition) ((void)0) #endif /* * LZ4_decompress_generic() : * This generic decompression function covers all use cases. * It shall be instantiated several times, using different sets of directives. * Note that it is important for performance that this function really get inlined, * in order to remove useless branches during compilation optimization. */ static FORCE_INLINE int LZ4_decompress_generic( const char * const src, char * const dst, int srcSize, /* * If endOnInput == endOnInputSize, * this value is `dstCapacity` */ int outputSize, /* endOnOutputSize, endOnInputSize */ endCondition_directive endOnInput, /* full, partial */ earlyEnd_directive partialDecoding, /* noDict, withPrefix64k, usingExtDict */ dict_directive dict, /* always <= dst, == dst when no prefix */ const BYTE * const lowPrefix, /* only if dict == usingExtDict */ const BYTE * const dictStart, /* note : = 0 if noDict */ const size_t dictSize ) { const BYTE *ip = (const BYTE *) src; const BYTE * const iend = ip + srcSize; BYTE *op = (BYTE *) dst; BYTE * const oend = op + outputSize; BYTE *cpy; const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize; static const unsigned int inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4}; static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3}; const int safeDecode = (endOnInput == endOnInputSize); const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB))); /* Set up the "end" pointers for the shortcut. */ const BYTE *const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/; const BYTE *const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/; DEBUGLOG(5, "%s (srcSize:%i, dstSize:%i)", __func__, srcSize, outputSize); /* Special cases */ assert(lowPrefix <= op); assert(src != NULL); /* Empty output buffer */ if ((endOnInput) && (unlikely(outputSize == 0))) return ((srcSize == 1) && (*ip == 0)) ? 0 : -1; if ((!endOnInput) && (unlikely(outputSize == 0))) return (*ip == 0 ? 1 : -1); if ((endOnInput) && unlikely(srcSize == 0)) return -1; /* Main Loop : decode sequences */ while (1) { size_t length; const BYTE *match; size_t offset; /* get literal length */ unsigned int const token = *ip++; length = token>>ML_BITS; /* ip < iend before the increment */ assert(!endOnInput || ip <= iend); /* * A two-stage shortcut for the most common case: * 1) If the literal length is 0..14, and there is enough * space, enter the shortcut and copy 16 bytes on behalf * of the literals (in the fast mode, only 8 bytes can be * safely copied this way). * 2) Further if the match length is 4..18, copy 18 bytes * in a similar manner; but we ensure that there's enough * space in the output for those 18 bytes earlier, upon * entering the shortcut (in other words, there is a * combined check for both stages). * * The & in the likely() below is intentionally not && so that * some compilers can produce better parallelized runtime code */ if ((endOnInput ? length != RUN_MASK : length <= 8) /* * strictly "less than" on input, to re-enter * the loop with at least one byte */ && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend))) { /* Copy the literals */ LZ4_memcpy(op, ip, endOnInput ? 16 : 8); op += length; ip += length; /* * The second stage: * prepare for match copying, decode full info. * If it doesn't work out, the info won't be wasted. */ length = token & ML_MASK; /* match length */ offset = LZ4_readLE16(ip); ip += 2; match = op - offset; assert(match <= op); /* check overflow */ /* Do not deal with overlapping matches. */ if ((length != ML_MASK) && (offset >= 8) && (dict == withPrefix64k || match >= lowPrefix)) { /* Copy the match. */ LZ4_memcpy(op + 0, match + 0, 8); LZ4_memcpy(op + 8, match + 8, 8); LZ4_memcpy(op + 16, match + 16, 2); op += length + MINMATCH; /* Both stages worked, load the next token. */ continue; } /* * The second stage didn't work out, but the info * is ready. Propel it right to the point of match * copying. */ goto _copy_match; } /* decode literal length */ if (length == RUN_MASK) { unsigned int s; if (unlikely(endOnInput ? ip >= iend - RUN_MASK : 0)) { /* overflow detection */ goto _output_error; } do { s = *ip++; length += s; } while (likely(endOnInput ? ip < iend - RUN_MASK : 1) & (s == 255)); if ((safeDecode) && unlikely((uptrval)(op) + length < (uptrval)(op))) { /* overflow detection */ goto _output_error; } if ((safeDecode) && unlikely((uptrval)(ip) + length < (uptrval)(ip))) { /* overflow detection */ goto _output_error; } } /* copy literals */ cpy = op + length; LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); if (((endOnInput) && ((cpy > oend - MFLIMIT) || (ip + length > iend - (2 + 1 + LASTLITERALS)))) || ((!endOnInput) && (cpy > oend - WILDCOPYLENGTH))) { if (partialDecoding) { if (cpy > oend) { /* * Partial decoding : * stop in the middle of literal segment */ cpy = oend; length = oend - op; } if ((endOnInput) && (ip + length > iend)) { /* * Error : * read attempt beyond * end of input buffer */ goto _output_error; } } else { if ((!endOnInput) && (cpy != oend)) { /* * Error : * block decoding must * stop exactly there */ goto _output_error; } if ((endOnInput) && ((ip + length != iend) || (cpy > oend))) { /* * Error : * input must be consumed */ goto _output_error; } } /* * supports overlapping memory regions; only matters * for in-place decompression scenarios */ LZ4_memmove(op, ip, length); ip += length; op += length; /* Necessarily EOF when !partialDecoding. * When partialDecoding, it is EOF if we've either * filled the output buffer or * can't proceed with reading an offset for following match. */ if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2))) break; } else { /* may overwrite up to WILDCOPYLENGTH beyond cpy */ LZ4_wildCopy(op, ip, cpy); ip += length; op = cpy; } /* get offset */ offset = LZ4_readLE16(ip); ip += 2; match = op - offset; /* get matchlength */ length = token & ML_MASK; _copy_match: if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { /* Error : offset outside buffers */ goto _output_error; } /* costs ~1%; silence an msan warning when offset == 0 */ /* * note : when partialDecoding, there is no guarantee that * at least 4 bytes remain available in output buffer */ if (!partialDecoding) { assert(oend > op); assert(oend - op >= 4); LZ4_write32(op, (U32)offset); } if (length == ML_MASK) { unsigned int s; do { s = *ip++; if ((endOnInput) && (ip > iend - LASTLITERALS)) goto _output_error; length += s; } while (s == 255); if ((safeDecode) && unlikely( (uptrval)(op) + length < (uptrval)op)) { /* overflow detection */ goto _output_error; } } length += MINMATCH; /* match starting within external dictionary */ if ((dict == usingExtDict) && (match < lowPrefix)) { if (unlikely(op + length > oend - LASTLITERALS)) { /* doesn't respect parsing restriction */ if (!partialDecoding) goto _output_error; length = min(length, (size_t)(oend - op)); } if (length <= (size_t)(lowPrefix - match)) { /* * match fits entirely within external * dictionary : just copy */ memmove(op, dictEnd - (lowPrefix - match), length); op += length; } else { /* * match stretches into both external * dictionary and current block */ size_t const copySize = (size_t)(lowPrefix - match); size_t const restSize = length - copySize; LZ4_memcpy(op, dictEnd - copySize, copySize); op += copySize; if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ BYTE * const endOfMatch = op + restSize; const BYTE *copyFrom = lowPrefix; while (op < endOfMatch) *op++ = *copyFrom++; } else { LZ4_memcpy(op, lowPrefix, restSize); op += restSize; } } continue; } /* copy match within block */ cpy = op + length; /* * partialDecoding : * may not respect endBlock parsing restrictions */ assert(op <= oend); if (partialDecoding && (cpy > oend - MATCH_SAFEGUARD_DISTANCE)) { size_t const mlen = min(length, (size_t)(oend - op)); const BYTE * const matchEnd = match + mlen; BYTE * const copyEnd = op + mlen; if (matchEnd > op) { /* overlap copy */ while (op < copyEnd) *op++ = *match++; } else { LZ4_memcpy(op, match, mlen); } op = copyEnd; if (op == oend) break; continue; } if (unlikely(offset < 8)) { op[0] = match[0]; op[1] = match[1]; op[2] = match[2]; op[3] = match[3]; match += inc32table[offset]; LZ4_memcpy(op + 4, match, 4); match -= dec64table[offset]; } else { LZ4_copy8(op, match); match += 8; } op += 8; if (unlikely(cpy > oend - MATCH_SAFEGUARD_DISTANCE)) { BYTE * const oCopyLimit = oend - (WILDCOPYLENGTH - 1); if (cpy > oend - LASTLITERALS) { /* * Error : last LASTLITERALS bytes * must be literals (uncompressed) */ goto _output_error; } if (op < oCopyLimit) { LZ4_wildCopy(op, match, oCopyLimit); match += oCopyLimit - op; op = oCopyLimit; } while (op < cpy) *op++ = *match++; } else { LZ4_copy8(op, match); if (length > 16) LZ4_wildCopy(op + 8, match + 8, cpy); } op = cpy; /* wildcopy correction */ } /* end of decoding */ if (endOnInput) { /* Nb of output bytes decoded */ return (int) (((char *)op) - dst); } else { /* Nb of input bytes read */ return (int) (((const char *)ip) - src); } /* Overflow error detected */ _output_error: return (int) (-(((const char *)ip) - src)) - 1; } int LZ4_decompress_safe(const char *source, char *dest, int compressedSize, int maxDecompressedSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, decode_full_block, noDict, (BYTE *)dest, NULL, 0); } int LZ4_decompress_safe_partial(const char *src, char *dst, int compressedSize, int targetOutputSize, int dstCapacity) { dstCapacity = min(targetOutputSize, dstCapacity); return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, endOnInputSize, partial_decode, noDict, (BYTE *)dst, NULL, 0); } int LZ4_decompress_fast(const char *source, char *dest, int originalSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, decode_full_block, withPrefix64k, (BYTE *)dest - 64 * KB, NULL, 0); } /* ===== Instantiate a few more decoding cases, used more than once. ===== */ static int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest, int compressedSize, int maxOutputSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, decode_full_block, withPrefix64k, (BYTE *)dest - 64 * KB, NULL, 0); } static int LZ4_decompress_safe_withSmallPrefix(const char *source, char *dest, int compressedSize, int maxOutputSize, size_t prefixSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, decode_full_block, noDict, (BYTE *)dest - prefixSize, NULL, 0); } static int LZ4_decompress_safe_forceExtDict(const char *source, char *dest, int compressedSize, int maxOutputSize, const void *dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, decode_full_block, usingExtDict, (BYTE *)dest, (const BYTE *)dictStart, dictSize); } static int LZ4_decompress_fast_extDict(const char *source, char *dest, int originalSize, const void *dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, decode_full_block, usingExtDict, (BYTE *)dest, (const BYTE *)dictStart, dictSize); } /* * The "double dictionary" mode, for use with e.g. ring buffers: the first part * of the dictionary is passed as prefix, and the second via dictStart + dictSize. * These routines are used only once, in LZ4_decompress_*_continue(). */ static FORCE_INLINE int LZ4_decompress_safe_doubleDict(const char *source, char *dest, int compressedSize, int maxOutputSize, size_t prefixSize, const void *dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, decode_full_block, usingExtDict, (BYTE *)dest - prefixSize, (const BYTE *)dictStart, dictSize); } static FORCE_INLINE int LZ4_decompress_fast_doubleDict(const char *source, char *dest, int originalSize, size_t prefixSize, const void *dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, decode_full_block, usingExtDict, (BYTE *)dest - prefixSize, (const BYTE *)dictStart, dictSize); } /* ===== streaming decompression functions ===== */ int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode, const char *dictionary, int dictSize) { LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse; lz4sd->prefixSize = (size_t) dictSize; lz4sd->prefixEnd = (const BYTE *) dictionary + dictSize; lz4sd->externalDict = NULL; lz4sd->extDictSize = 0; return 1; } /* * *_continue() : * These decoding functions allow decompression of multiple blocks * in "streaming" mode. * Previously decoded blocks must still be available at the memory * position where they were decoded. * If it's not possible, save the relevant part of * decoded data into a safe buffer, * and indicate where it stands using LZ4_setStreamDecode() */ int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode, const char *source, char *dest, int compressedSize, int maxOutputSize) { LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse; int result; if (lz4sd->prefixSize == 0) { /* The first call, no dictionary yet. */ assert(lz4sd->extDictSize == 0); result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); if (result <= 0) return result; lz4sd->prefixSize = result; lz4sd->prefixEnd = (BYTE *)dest + result; } else if (lz4sd->prefixEnd == (BYTE *)dest) { /* They're rolling the current segment. */ if (lz4sd->prefixSize >= 64 * KB - 1) result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); else if (lz4sd->extDictSize == 0) result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, lz4sd->prefixSize); else result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize, lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize += result; lz4sd->prefixEnd += result; } else { /* * The buffer wraps around, or they're * switching to another buffer. */ lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize = result; lz4sd->prefixEnd = (BYTE *)dest + result; } return result; } int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode, const char *source, char *dest, int originalSize) { LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse; int result; if (lz4sd->prefixSize == 0) { assert(lz4sd->extDictSize == 0); result = LZ4_decompress_fast(source, dest, originalSize); if (result <= 0) return result; lz4sd->prefixSize = originalSize; lz4sd->prefixEnd = (BYTE *)dest + originalSize; } else if (lz4sd->prefixEnd == (BYTE *)dest) { if (lz4sd->prefixSize >= 64 * KB - 1 || lz4sd->extDictSize == 0) result = LZ4_decompress_fast(source, dest, originalSize); else result = LZ4_decompress_fast_doubleDict(source, dest, originalSize, lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize += originalSize; lz4sd->prefixEnd += originalSize; } else { lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; result = LZ4_decompress_fast_extDict(source, dest, originalSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize = originalSize; lz4sd->prefixEnd = (BYTE *)dest + originalSize; } return result; } int LZ4_decompress_safe_usingDict(const char *source, char *dest, int compressedSize, int maxOutputSize, const char *dictStart, int dictSize) { if (dictSize == 0) return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); if (dictStart+dictSize == dest) { if (dictSize >= 64 * KB - 1) return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize); } return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize); } int LZ4_decompress_fast_usingDict(const char *source, char *dest, int originalSize, const char *dictStart, int dictSize) { if (dictSize == 0 || dictStart + dictSize == dest) return LZ4_decompress_fast(source, dest, originalSize); return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, dictSize); } #ifndef STATIC EXPORT_SYMBOL(LZ4_decompress_safe); EXPORT_SYMBOL(LZ4_decompress_safe_partial); EXPORT_SYMBOL(LZ4_decompress_fast); EXPORT_SYMBOL(LZ4_setStreamDecode); EXPORT_SYMBOL(LZ4_decompress_safe_continue); EXPORT_SYMBOL(LZ4_decompress_fast_continue); EXPORT_SYMBOL(LZ4_decompress_safe_usingDict); EXPORT_SYMBOL(LZ4_decompress_fast_usingDict); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4 decompressor"); #endif |
| 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/key/af_key.c An implementation of PF_KEYv2 sockets. * * Authors: Maxim Giryaev <gem@asplinux.ru> * David S. Miller <davem@redhat.com> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * Kazunori MIYAZAWA / USAGI Project <miyazawa@linux-ipv6.org> * Derek Atkins <derek@ihtfp.com> */ #include <linux/capability.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/socket.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/xfrm.h> #include <net/sock.h> #define _X2KEY(x) ((x) == XFRM_INF ? 0 : (x)) #define _KEY2X(x) ((x) == 0 ? XFRM_INF : (x)) static unsigned int pfkey_net_id __read_mostly; struct netns_pfkey { /* List of all pfkey sockets. */ struct hlist_head table; atomic_t socks_nr; }; static DEFINE_MUTEX(pfkey_mutex); #define DUMMY_MARK 0 static const struct xfrm_mark dummy_mark = {0, 0}; struct pfkey_sock { /* struct sock must be the first member of struct pfkey_sock */ struct sock sk; int registered; int promisc; struct { uint8_t msg_version; uint32_t msg_portid; int (*dump)(struct pfkey_sock *sk); void (*done)(struct pfkey_sock *sk); union { struct xfrm_policy_walk policy; struct xfrm_state_walk state; } u; struct sk_buff *skb; } dump; struct mutex dump_lock; }; static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, xfrm_address_t *saddr, xfrm_address_t *daddr, u16 *family); static inline struct pfkey_sock *pfkey_sk(struct sock *sk) { return (struct pfkey_sock *)sk; } static int pfkey_can_dump(const struct sock *sk) { if (3 * atomic_read(&sk->sk_rmem_alloc) <= 2 * sk->sk_rcvbuf) return 1; return 0; } static void pfkey_terminate_dump(struct pfkey_sock *pfk) { if (pfk->dump.dump) { if (pfk->dump.skb) { kfree_skb(pfk->dump.skb); pfk->dump.skb = NULL; } pfk->dump.done(pfk); pfk->dump.dump = NULL; pfk->dump.done = NULL; } } static void pfkey_sock_destruct(struct sock *sk) { struct net *net = sock_net(sk); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_terminate_dump(pfkey_sk(sk)); skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive pfkey socket: %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); atomic_dec(&net_pfkey->socks_nr); } static const struct proto_ops pfkey_ops; static void pfkey_insert(struct sock *sk) { struct net *net = sock_net(sk); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); mutex_lock(&pfkey_mutex); sk_add_node_rcu(sk, &net_pfkey->table); mutex_unlock(&pfkey_mutex); } static void pfkey_remove(struct sock *sk) { mutex_lock(&pfkey_mutex); sk_del_node_init_rcu(sk); mutex_unlock(&pfkey_mutex); } static struct proto key_proto = { .name = "KEY", .owner = THIS_MODULE, .obj_size = sizeof(struct pfkey_sock), }; static int pfkey_create(struct net *net, struct socket *sock, int protocol, int kern) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; struct pfkey_sock *pfk; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (protocol != PF_KEY_V2) return -EPROTONOSUPPORT; sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern); if (sk == NULL) return -ENOMEM; pfk = pfkey_sk(sk); mutex_init(&pfk->dump_lock); sock->ops = &pfkey_ops; sock_init_data(sock, sk); sk->sk_family = PF_KEY; sk->sk_destruct = pfkey_sock_destruct; atomic_inc(&net_pfkey->socks_nr); pfkey_insert(sk); return 0; } static int pfkey_release(struct socket *sock) { struct sock *sk = sock->sk; if (!sk) return 0; pfkey_remove(sk); sock_orphan(sk); sock->sk = NULL; skb_queue_purge(&sk->sk_write_queue); synchronize_rcu(); sock_put(sk); return 0; } static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, struct sock *sk) { int err = -ENOBUFS; if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) return err; skb = skb_clone(skb, allocation); if (skb) { skb_set_owner_r(skb, sk); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); err = 0; } return err; } /* Send SKB to all pfkey sockets matching selected criteria. */ #define BROADCAST_ALL 0 #define BROADCAST_ONE 1 #define BROADCAST_REGISTERED 2 #define BROADCAST_PROMISC_ONLY 4 static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, int broadcast_flags, struct sock *one_sk, struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think * XXX PF_KEY socket apps will not mind current behavior. */ if (!skb) return -ENOMEM; rcu_read_lock(); sk_for_each_rcu(sk, &net_pfkey->table) { struct pfkey_sock *pfk = pfkey_sk(sk); int err2; /* Yes, it means that if you are meant to receive this * pfkey message you receive it twice as promiscuous * socket. */ if (pfk->promisc) pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) continue; if (broadcast_flags != BROADCAST_ALL) { if (broadcast_flags & BROADCAST_PROMISC_ONLY) continue; if ((broadcast_flags & BROADCAST_REGISTERED) && !pfk->registered) continue; if (broadcast_flags & BROADCAST_ONE) continue; } err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ if ((broadcast_flags & BROADCAST_REGISTERED) && err) err = err2; } rcu_read_unlock(); if (one_sk != NULL) err = pfkey_broadcast_one(skb, allocation, one_sk); kfree_skb(skb); return err; } static int pfkey_do_dump(struct pfkey_sock *pfk) { struct sadb_msg *hdr; int rc; mutex_lock(&pfk->dump_lock); if (!pfk->dump.dump) { rc = 0; goto out; } rc = pfk->dump.dump(pfk); if (rc == -ENOBUFS) { rc = 0; goto out; } if (pfk->dump.skb) { if (!pfkey_can_dump(&pfk->sk)) { rc = 0; goto out; } hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; hdr->sadb_msg_errno = rc; pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = NULL; } pfkey_terminate_dump(pfk); out: mutex_unlock(&pfk->dump_lock); return rc; } static inline void pfkey_hdr_dup(struct sadb_msg *new, const struct sadb_msg *orig) { *new = *orig; } static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) { struct sk_buff *skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); struct sadb_msg *hdr; if (!skb) return -ENOBUFS; /* Woe be to the platform trying to support PFKEY yet * having normal errnos outside the 1-255 range, inclusive. */ err = -err; if (err == ERESTARTSYS || err == ERESTARTNOHAND || err == ERESTARTNOINTR) err = EINTR; if (err >= 512) err = EINVAL; BUG_ON(err <= 0 || err >= 256); hdr = skb_put(skb, sizeof(struct sadb_msg)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = (uint8_t) err; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk)); return 0; } static const u8 sadb_ext_min_len[] = { [SADB_EXT_RESERVED] = (u8) 0, [SADB_EXT_SA] = (u8) sizeof(struct sadb_sa), [SADB_EXT_LIFETIME_CURRENT] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_LIFETIME_HARD] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_LIFETIME_SOFT] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_ADDRESS_SRC] = (u8) sizeof(struct sadb_address), [SADB_EXT_ADDRESS_DST] = (u8) sizeof(struct sadb_address), [SADB_EXT_ADDRESS_PROXY] = (u8) sizeof(struct sadb_address), [SADB_EXT_KEY_AUTH] = (u8) sizeof(struct sadb_key), [SADB_EXT_KEY_ENCRYPT] = (u8) sizeof(struct sadb_key), [SADB_EXT_IDENTITY_SRC] = (u8) sizeof(struct sadb_ident), [SADB_EXT_IDENTITY_DST] = (u8) sizeof(struct sadb_ident), [SADB_EXT_SENSITIVITY] = (u8) sizeof(struct sadb_sens), [SADB_EXT_PROPOSAL] = (u8) sizeof(struct sadb_prop), [SADB_EXT_SUPPORTED_AUTH] = (u8) sizeof(struct sadb_supported), [SADB_EXT_SUPPORTED_ENCRYPT] = (u8) sizeof(struct sadb_supported), [SADB_EXT_SPIRANGE] = (u8) sizeof(struct sadb_spirange), [SADB_X_EXT_KMPRIVATE] = (u8) sizeof(struct sadb_x_kmprivate), [SADB_X_EXT_POLICY] = (u8) sizeof(struct sadb_x_policy), [SADB_X_EXT_SA2] = (u8) sizeof(struct sadb_x_sa2), [SADB_X_EXT_NAT_T_TYPE] = (u8) sizeof(struct sadb_x_nat_t_type), [SADB_X_EXT_NAT_T_SPORT] = (u8) sizeof(struct sadb_x_nat_t_port), [SADB_X_EXT_NAT_T_DPORT] = (u8) sizeof(struct sadb_x_nat_t_port), [SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address), [SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx), [SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress), [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter), }; /* Verify sadb_address_{len,prefixlen} against sa_family. */ static int verify_address_len(const void *p) { const struct sadb_address *sp = p; const struct sockaddr *addr = (const struct sockaddr *)(sp + 1); const struct sockaddr_in *sin; #if IS_ENABLED(CONFIG_IPV6) const struct sockaddr_in6 *sin6; #endif int len; if (sp->sadb_address_len < DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family), sizeof(uint64_t))) return -EINVAL; switch (addr->sa_family) { case AF_INET: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t)); if (sp->sadb_address_len != len || sp->sadb_address_prefixlen > 32) return -EINVAL; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin6), sizeof(uint64_t)); if (sp->sadb_address_len != len || sp->sadb_address_prefixlen > 128) return -EINVAL; break; #endif default: /* It is user using kernel to keep track of security * associations for another protocol, such as * OSPF/RSVP/RIPV2/MIP. It is user's job to verify * lengths. * * XXX Actually, association/policy database is not yet * XXX able to cope with arbitrary sockaddr families. * XXX When it can, remove this -EINVAL. -DaveM */ return -EINVAL; } return 0; } static inline int sadb_key_len(const struct sadb_key *key) { int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8); return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes, sizeof(uint64_t)); } static int verify_key_len(const void *p) { const struct sadb_key *key = p; if (sadb_key_len(key) > key->sadb_key_len) return -EINVAL; return 0; } static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx) { return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) + sec_ctx->sadb_x_ctx_len, sizeof(uint64_t)); } static inline int verify_sec_ctx_len(const void *p) { const struct sadb_x_sec_ctx *sec_ctx = p; int len = sec_ctx->sadb_x_ctx_len; if (len > PAGE_SIZE) return -EINVAL; len = pfkey_sec_ctx_len(sec_ctx); if (sec_ctx->sadb_x_sec_len != len) return -EINVAL; return 0; } static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx, gfp_t gfp) { struct xfrm_user_sec_ctx *uctx = NULL; int ctx_size = sec_ctx->sadb_x_ctx_len; uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp); if (!uctx) return NULL; uctx->len = pfkey_sec_ctx_len(sec_ctx); uctx->exttype = sec_ctx->sadb_x_sec_exttype; uctx->ctx_doi = sec_ctx->sadb_x_ctx_doi; uctx->ctx_alg = sec_ctx->sadb_x_ctx_alg; uctx->ctx_len = sec_ctx->sadb_x_ctx_len; memcpy(uctx + 1, sec_ctx + 1, uctx->ctx_len); return uctx; } static int present_and_same_family(const struct sadb_address *src, const struct sadb_address *dst) { const struct sockaddr *s_addr, *d_addr; if (!src || !dst) return 0; s_addr = (const struct sockaddr *)(src + 1); d_addr = (const struct sockaddr *)(dst + 1); if (s_addr->sa_family != d_addr->sa_family) return 0; if (s_addr->sa_family != AF_INET #if IS_ENABLED(CONFIG_IPV6) && s_addr->sa_family != AF_INET6 #endif ) return 0; return 1; } static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void **ext_hdrs) { const char *p = (char *) hdr; int len = skb->len; len -= sizeof(*hdr); p += sizeof(*hdr); while (len > 0) { const struct sadb_ext *ehdr = (const struct sadb_ext *) p; uint16_t ext_type; int ext_len; if (len < sizeof(*ehdr)) return -EINVAL; ext_len = ehdr->sadb_ext_len; ext_len *= sizeof(uint64_t); ext_type = ehdr->sadb_ext_type; if (ext_len < sizeof(uint64_t) || ext_len > len || ext_type == SADB_EXT_RESERVED) return -EINVAL; if (ext_type <= SADB_EXT_MAX) { int min = (int) sadb_ext_min_len[ext_type]; if (ext_len < min) return -EINVAL; if (ext_hdrs[ext_type-1] != NULL) return -EINVAL; switch (ext_type) { case SADB_EXT_ADDRESS_SRC: case SADB_EXT_ADDRESS_DST: case SADB_EXT_ADDRESS_PROXY: case SADB_X_EXT_NAT_T_OA: if (verify_address_len(p)) return -EINVAL; break; case SADB_X_EXT_SEC_CTX: if (verify_sec_ctx_len(p)) return -EINVAL; break; case SADB_EXT_KEY_AUTH: case SADB_EXT_KEY_ENCRYPT: if (verify_key_len(p)) return -EINVAL; break; default: break; } ext_hdrs[ext_type-1] = (void *) p; } p += ext_len; len -= ext_len; } return 0; } static uint16_t pfkey_satype2proto(uint8_t satype) { switch (satype) { case SADB_SATYPE_UNSPEC: return IPSEC_PROTO_ANY; case SADB_SATYPE_AH: return IPPROTO_AH; case SADB_SATYPE_ESP: return IPPROTO_ESP; case SADB_X_SATYPE_IPCOMP: return IPPROTO_COMP; default: return 0; } /* NOTREACHED */ } static uint8_t pfkey_proto2satype(uint16_t proto) { switch (proto) { case IPPROTO_AH: return SADB_SATYPE_AH; case IPPROTO_ESP: return SADB_SATYPE_ESP; case IPPROTO_COMP: return SADB_X_SATYPE_IPCOMP; default: return 0; } /* NOTREACHED */ } /* BTW, this scheme means that there is no way with PFKEY2 sockets to * say specifically 'just raw sockets' as we encode them as 255. */ static uint8_t pfkey_proto_to_xfrm(uint8_t proto) { return proto == IPSEC_PROTO_ANY ? 0 : proto; } static uint8_t pfkey_proto_from_xfrm(uint8_t proto) { return proto ? proto : IPSEC_PROTO_ANY; } static inline int pfkey_sockaddr_len(sa_family_t family) { switch (family) { case AF_INET: return sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return sizeof(struct sockaddr_in6); #endif } return 0; } static int pfkey_sockaddr_extract(const struct sockaddr *sa, xfrm_address_t *xaddr) { switch (sa->sa_family) { case AF_INET: xaddr->a4 = ((struct sockaddr_in *)sa)->sin_addr.s_addr; return AF_INET; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: memcpy(xaddr->a6, &((struct sockaddr_in6 *)sa)->sin6_addr, sizeof(struct in6_addr)); return AF_INET6; #endif } return 0; } static int pfkey_sadb_addr2xfrm_addr(const struct sadb_address *addr, xfrm_address_t *xaddr) { return pfkey_sockaddr_extract((struct sockaddr *)(addr + 1), xaddr); } static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs) { const struct sadb_sa *sa; const struct sadb_address *addr; uint16_t proto; unsigned short family; xfrm_address_t *xaddr; sa = ext_hdrs[SADB_EXT_SA - 1]; if (sa == NULL) return NULL; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return NULL; /* sadb_address_len should be checked by caller */ addr = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; if (addr == NULL) return NULL; family = ((const struct sockaddr *)(addr + 1))->sa_family; switch (family) { case AF_INET: xaddr = (xfrm_address_t *)&((const struct sockaddr_in *)(addr + 1))->sin_addr; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: xaddr = (xfrm_address_t *)&((const struct sockaddr_in6 *)(addr + 1))->sin6_addr; break; #endif default: xaddr = NULL; } if (!xaddr) return NULL; return xfrm_state_lookup(net, DUMMY_MARK, xaddr, sa->sadb_sa_spi, proto, family); } #define PFKEY_ALIGN8(a) (1 + (((a) - 1) | (8 - 1))) static int pfkey_sockaddr_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family)); } static inline int pfkey_mode_from_xfrm(int mode) { switch(mode) { case XFRM_MODE_TRANSPORT: return IPSEC_MODE_TRANSPORT; case XFRM_MODE_TUNNEL: return IPSEC_MODE_TUNNEL; case XFRM_MODE_BEET: return IPSEC_MODE_BEET; default: return -1; } } static inline int pfkey_mode_to_xfrm(int mode) { switch(mode) { case IPSEC_MODE_ANY: /*XXX*/ case IPSEC_MODE_TRANSPORT: return XFRM_MODE_TRANSPORT; case IPSEC_MODE_TUNNEL: return XFRM_MODE_TUNNEL; case IPSEC_MODE_BEET: return XFRM_MODE_BEET; default: return -1; } } static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port, struct sockaddr *sa, unsigned short family) { switch (family) { case AF_INET: { struct sockaddr_in *sin = (struct sockaddr_in *)sa; sin->sin_family = AF_INET; sin->sin_port = port; sin->sin_addr.s_addr = xaddr->a4; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return 32; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa; sin6->sin6_family = AF_INET6; sin6->sin6_port = port; sin6->sin6_flowinfo = 0; sin6->sin6_addr = xaddr->in6; sin6->sin6_scope_id = 0; return 128; } #endif } return 0; } static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, int add_keys, int hsc) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_sa *sa; struct sadb_lifetime *lifetime; struct sadb_address *addr; struct sadb_key *key; struct sadb_x_sa2 *sa2; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; int size; int auth_key_size = 0; int encrypt_key_size = 0; int sockaddr_size; struct xfrm_encap_tmpl *natt = NULL; int mode; /* address family check */ sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return ERR_PTR(-EINVAL); /* base, SA, (lifetime (HSC),) address(SD), (address(P),) key(AE), (identity(SD),) (sensitivity)> */ size = sizeof(struct sadb_msg) +sizeof(struct sadb_sa) + sizeof(struct sadb_lifetime) + ((hsc & 1) ? sizeof(struct sadb_lifetime) : 0) + ((hsc & 2) ? sizeof(struct sadb_lifetime) : 0) + sizeof(struct sadb_address)*2 + sockaddr_size*2 + sizeof(struct sadb_x_sa2); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } /* identity & sensitivity */ if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) size += sizeof(struct sadb_address) + sockaddr_size; if (add_keys) { if (x->aalg && x->aalg->alg_key_len) { auth_key_size = PFKEY_ALIGN8((x->aalg->alg_key_len + 7) / 8); size += sizeof(struct sadb_key) + auth_key_size; } if (x->ealg && x->ealg->alg_key_len) { encrypt_key_size = PFKEY_ALIGN8((x->ealg->alg_key_len+7) / 8); size += sizeof(struct sadb_key) + encrypt_key_size; } } if (x->encap) natt = x->encap; if (natt && natt->encap_type) { size += sizeof(struct sadb_x_nat_t_type); size += sizeof(struct sadb_x_nat_t_port); size += sizeof(struct sadb_x_nat_t_port); } skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return ERR_PTR(-ENOBUFS); /* call should fill header later */ hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ hdr->sadb_msg_len = size / sizeof(uint64_t); /* sa */ sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = x->props.replay_window; switch (x->km.state) { case XFRM_STATE_VALID: sa->sadb_sa_state = x->km.dying ? SADB_SASTATE_DYING : SADB_SASTATE_MATURE; break; case XFRM_STATE_ACQ: sa->sadb_sa_state = SADB_SASTATE_LARVAL; break; default: sa->sadb_sa_state = SADB_SASTATE_DEAD; break; } sa->sadb_sa_auth = 0; if (x->aalg) { struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0); sa->sadb_sa_auth = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } sa->sadb_sa_encrypt = 0; BUG_ON(x->ealg && x->calg); if (x->ealg) { struct xfrm_algo_desc *a = xfrm_ealg_get_byname(x->ealg->alg_name, 0); sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } /* KAME compatible: sadb_sa_encrypt is overloaded with calg id */ if (x->calg) { struct xfrm_algo_desc *a = xfrm_calg_get_byname(x->calg->alg_name, 0); sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } sa->sadb_sa_flags = 0; if (x->props.flags & XFRM_STATE_NOECN) sa->sadb_sa_flags |= SADB_SAFLAGS_NOECN; if (x->props.flags & XFRM_STATE_DECAP_DSCP) sa->sadb_sa_flags |= SADB_SAFLAGS_DECAP_DSCP; if (x->props.flags & XFRM_STATE_NOPMTUDISC) sa->sadb_sa_flags |= SADB_SAFLAGS_NOPMTUDISC; /* hard time */ if (hsc & 2) { lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.hard_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.hard_byte_limit); lifetime->sadb_lifetime_addtime = x->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = x->lft.hard_use_expires_seconds; } /* soft time */ if (hsc & 1) { lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.soft_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.soft_byte_limit); lifetime->sadb_lifetime_addtime = x->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = x->lft.soft_use_expires_seconds; } /* current time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; lifetime->sadb_lifetime_allocations = x->curlft.packets; lifetime->sadb_lifetime_bytes = x->curlft.bytes; lifetime->sadb_lifetime_addtime = x->curlft.add_time; lifetime->sadb_lifetime_usetime = x->curlft.use_time; /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; /* "if the ports are non-zero, then the sadb_address_proto field, normally zero, MUST be filled in with the transport protocol's number." - RFC2367 */ addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); BUG_ON(!addr->sadb_address_prefixlen); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); BUG_ON(!addr->sadb_address_prefixlen); if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_PROXY; addr->sadb_address_proto = pfkey_proto_from_xfrm(x->sel.proto); addr->sadb_address_prefixlen = x->sel.prefixlen_s; addr->sadb_address_reserved = 0; pfkey_sockaddr_fill(&x->sel.saddr, x->sel.sport, (struct sockaddr *) (addr + 1), x->props.family); } /* auth key */ if (add_keys && auth_key_size) { key = skb_put(skb, sizeof(struct sadb_key) + auth_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + auth_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_AUTH; key->sadb_key_bits = x->aalg->alg_key_len; key->sadb_key_reserved = 0; memcpy(key + 1, x->aalg->alg_key, (x->aalg->alg_key_len+7)/8); } /* encrypt key */ if (add_keys && encrypt_key_size) { key = skb_put(skb, sizeof(struct sadb_key) + encrypt_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + encrypt_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_ENCRYPT; key->sadb_key_bits = x->ealg->alg_key_len; key->sadb_key_reserved = 0; memcpy(key + 1, x->ealg->alg_key, (x->ealg->alg_key_len+7)/8); } /* sa */ sa2 = skb_put(skb, sizeof(struct sadb_x_sa2)); sa2->sadb_x_sa2_len = sizeof(struct sadb_x_sa2)/sizeof(uint64_t); sa2->sadb_x_sa2_exttype = SADB_X_EXT_SA2; if ((mode = pfkey_mode_from_xfrm(x->props.mode)) < 0) { kfree_skb(skb); return ERR_PTR(-EINVAL); } sa2->sadb_x_sa2_mode = mode; sa2->sadb_x_sa2_reserved1 = 0; sa2->sadb_x_sa2_reserved2 = 0; sa2->sadb_x_sa2_sequence = 0; sa2->sadb_x_sa2_reqid = x->props.reqid; if (natt && natt->encap_type) { struct sadb_x_nat_t_type *n_type; struct sadb_x_nat_t_port *n_port; /* type */ n_type = skb_put(skb, sizeof(*n_type)); n_type->sadb_x_nat_t_type_len = sizeof(*n_type)/sizeof(uint64_t); n_type->sadb_x_nat_t_type_exttype = SADB_X_EXT_NAT_T_TYPE; n_type->sadb_x_nat_t_type_type = natt->encap_type; n_type->sadb_x_nat_t_type_reserved[0] = 0; n_type->sadb_x_nat_t_type_reserved[1] = 0; n_type->sadb_x_nat_t_type_reserved[2] = 0; /* source port */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* dest port */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = natt->encap_dport; n_port->sadb_x_nat_t_port_reserved = 0; } /* security context */ if (xfrm_ctx) { sec_ctx = skb_put(skb, sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } return skb; } static inline struct sk_buff *pfkey_xfrm_state2msg(const struct xfrm_state *x) { struct sk_buff *skb; skb = __pfkey_xfrm_state2msg(x, 1, 3); return skb; } static inline struct sk_buff *pfkey_xfrm_state2msg_expire(const struct xfrm_state *x, int hsc) { return __pfkey_xfrm_state2msg(x, 0, hsc); } static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct xfrm_state *x; const struct sadb_lifetime *lifetime; const struct sadb_sa *sa; const struct sadb_key *key; const struct sadb_x_sec_ctx *sec_ctx; uint16_t proto; int err; sa = ext_hdrs[SADB_EXT_SA - 1]; if (!sa || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return ERR_PTR(-EINVAL); if (hdr->sadb_msg_satype == SADB_SATYPE_ESP && !ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]) return ERR_PTR(-EINVAL); if (hdr->sadb_msg_satype == SADB_SATYPE_AH && !ext_hdrs[SADB_EXT_KEY_AUTH-1]) return ERR_PTR(-EINVAL); if (!!ext_hdrs[SADB_EXT_LIFETIME_HARD-1] != !!ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]) return ERR_PTR(-EINVAL); proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return ERR_PTR(-EINVAL); /* default error is no buffer space */ err = -ENOBUFS; /* RFC2367: Only SADB_SASTATE_MATURE SAs may be submitted in an SADB_ADD message. SADB_SASTATE_LARVAL SAs are created by SADB_GETSPI and it is not sensible to add a new SA in the DYING or SADB_SASTATE_DEAD state. Therefore, the sadb_sa_state field of all submitted SAs MUST be SADB_SASTATE_MATURE and the kernel MUST return an error if this is not true. However, KAME setkey always uses SADB_SASTATE_LARVAL. Hence, we have to _ignore_ sadb_sa_state, which is also reasonable. */ if (sa->sadb_sa_auth > SADB_AALG_MAX || (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP && sa->sadb_sa_encrypt > SADB_X_CALG_MAX) || sa->sadb_sa_encrypt > SADB_EALG_MAX) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key != NULL && sa->sadb_sa_encrypt != SADB_EALG_NULL && key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); x = xfrm_state_alloc(net); if (x == NULL) return ERR_PTR(-ENOBUFS); x->id.proto = proto; x->id.spi = sa->sadb_sa_spi; x->props.replay_window = min_t(unsigned int, sa->sadb_sa_replay, (sizeof(x->replay.bitmap) * 8)); if (sa->sadb_sa_flags & SADB_SAFLAGS_NOECN) x->props.flags |= XFRM_STATE_NOECN; if (sa->sadb_sa_flags & SADB_SAFLAGS_DECAP_DSCP) x->props.flags |= XFRM_STATE_DECAP_DSCP; if (sa->sadb_sa_flags & SADB_SAFLAGS_NOPMTUDISC) x->props.flags |= XFRM_STATE_NOPMTUDISC; lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD - 1]; if (lifetime != NULL) { x->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT - 1]; if (lifetime != NULL) { x->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.soft_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) goto out; err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) goto out; } err = -ENOBUFS; key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (sa->sadb_sa_auth) { int keysize = 0; struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } if (key) keysize = (key->sadb_key_bits + 7) / 8; x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL); if (!x->aalg) { err = -ENOMEM; goto out; } strcpy(x->aalg->alg_name, a->name); x->aalg->alg_key_len = 0; if (key) { x->aalg->alg_key_len = key->sadb_key_bits; memcpy(x->aalg->alg_key, key+1, keysize); } x->aalg->alg_trunc_len = a->uinfo.auth.icv_truncbits; x->props.aalgo = sa->sadb_sa_auth; /* x->algo.flags = sa->sadb_sa_flags; */ } if (sa->sadb_sa_encrypt) { if (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP) { struct xfrm_algo_desc *a = xfrm_calg_get_byid(sa->sadb_sa_encrypt); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL); if (!x->calg) { err = -ENOMEM; goto out; } strcpy(x->calg->alg_name, a->name); x->props.calgo = sa->sadb_sa_encrypt; } else { int keysize = 0; struct xfrm_algo_desc *a = xfrm_ealg_get_byid(sa->sadb_sa_encrypt); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } key = (struct sadb_key*) ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key) keysize = (key->sadb_key_bits + 7) / 8; x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL); if (!x->ealg) { err = -ENOMEM; goto out; } strcpy(x->ealg->alg_name, a->name); x->ealg->alg_key_len = 0; if (key) { x->ealg->alg_key_len = key->sadb_key_bits; memcpy(x->ealg->alg_key, key+1, keysize); } x->props.ealgo = sa->sadb_sa_encrypt; x->geniv = a->uinfo.encr.geniv; } } /* x->algo.flags = sa->sadb_sa_flags; */ x->props.family = pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_SRC-1], &x->props.saddr); pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_DST-1], &x->id.daddr); if (ext_hdrs[SADB_X_EXT_SA2-1]) { const struct sadb_x_sa2 *sa2 = ext_hdrs[SADB_X_EXT_SA2-1]; int mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode); if (mode < 0) { err = -EINVAL; goto out; } x->props.mode = mode; x->props.reqid = sa2->sadb_x_sa2_reqid; } if (ext_hdrs[SADB_EXT_ADDRESS_PROXY-1]) { const struct sadb_address *addr = ext_hdrs[SADB_EXT_ADDRESS_PROXY-1]; /* Nobody uses this, but we try. */ x->sel.family = pfkey_sadb_addr2xfrm_addr(addr, &x->sel.saddr); x->sel.prefixlen_s = addr->sadb_address_prefixlen; } if (!x->sel.family) x->sel.family = x->props.family; if (ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]) { const struct sadb_x_nat_t_type* n_type; struct xfrm_encap_tmpl *natt; x->encap = kzalloc(sizeof(*x->encap), GFP_KERNEL); if (!x->encap) { err = -ENOMEM; goto out; } natt = x->encap; n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]; natt->encap_type = n_type->sadb_x_nat_t_type_type; if (ext_hdrs[SADB_X_EXT_NAT_T_SPORT-1]) { const struct sadb_x_nat_t_port *n_port = ext_hdrs[SADB_X_EXT_NAT_T_SPORT-1]; natt->encap_sport = n_port->sadb_x_nat_t_port_port; } if (ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]) { const struct sadb_x_nat_t_port *n_port = ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]; natt->encap_dport = n_port->sadb_x_nat_t_port_port; } } err = xfrm_init_state(x); if (err) goto out; x->km.seq = hdr->sadb_msg_seq; return x; out: x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); return ERR_PTR(err); } static int pfkey_reserved(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { return -EOPNOTSUPP; } static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct sk_buff *resp_skb; struct sadb_x_sa2 *sa2; struct sadb_address *saddr, *daddr; struct sadb_msg *out_hdr; struct sadb_spirange *range; struct xfrm_state *x = NULL; int mode; int err; u32 min_spi, max_spi; u32 reqid; u8 proto; unsigned short family; xfrm_address_t *xsaddr = NULL, *xdaddr = NULL; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; if ((sa2 = ext_hdrs[SADB_X_EXT_SA2-1]) != NULL) { mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode); if (mode < 0) return -EINVAL; reqid = sa2->sadb_x_sa2_reqid; } else { mode = 0; reqid = 0; } saddr = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; daddr = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; family = ((struct sockaddr *)(saddr + 1))->sa_family; switch (family) { case AF_INET: xdaddr = (xfrm_address_t *)&((struct sockaddr_in *)(daddr + 1))->sin_addr.s_addr; xsaddr = (xfrm_address_t *)&((struct sockaddr_in *)(saddr + 1))->sin_addr.s_addr; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: xdaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(daddr + 1))->sin6_addr; xsaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(saddr + 1))->sin6_addr; break; #endif } if (hdr->sadb_msg_seq) { x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq); if (x && !xfrm_addr_equal(&x->id.daddr, xdaddr, family)) { xfrm_state_put(x); x = NULL; } } if (!x) x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family); if (x == NULL) return -ENOENT; min_spi = 0x100; max_spi = 0x0fffffff; range = ext_hdrs[SADB_EXT_SPIRANGE-1]; if (range) { min_spi = range->sadb_spirange_min; max_spi = range->sadb_spirange_max; } err = verify_spi_info(x->id.proto, min_spi, max_spi, NULL); if (err) { xfrm_state_put(x); return err; } err = xfrm_alloc_spi(x, min_spi, max_spi, NULL); resp_skb = err ? ERR_PTR(err) : pfkey_xfrm_state2msg(x); if (IS_ERR(resp_skb)) { xfrm_state_put(x); return PTR_ERR(resp_skb); } out_hdr = (struct sadb_msg *) resp_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = SADB_GETSPI; out_hdr->sadb_msg_satype = pfkey_proto2satype(proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; xfrm_state_put(x); pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net); return 0; } static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; if (hdr->sadb_msg_len != sizeof(struct sadb_msg)/8) return -EOPNOTSUPP; if (hdr->sadb_msg_seq == 0 || hdr->sadb_msg_errno == 0) return 0; x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq); if (x == NULL) return 0; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_ACQ) x->km.state = XFRM_STATE_ERROR; spin_unlock_bh(&x->lock); xfrm_state_put(x); return 0; } static inline int event2poltype(int event) { switch (event) { case XFRM_MSG_DELPOLICY: return SADB_X_SPDDELETE; case XFRM_MSG_NEWPOLICY: return SADB_X_SPDADD; case XFRM_MSG_UPDPOLICY: return SADB_X_SPDUPDATE; case XFRM_MSG_POLEXPIRE: // return SADB_X_SPDEXPIRE; default: pr_err("pfkey: Unknown policy event %d\n", event); break; } return 0; } static inline int event2keytype(int event) { switch (event) { case XFRM_MSG_DELSA: return SADB_DELETE; case XFRM_MSG_NEWSA: return SADB_ADD; case XFRM_MSG_UPDSA: return SADB_UPDATE; case XFRM_MSG_EXPIRE: return SADB_EXPIRE; default: pr_err("pfkey: Unknown SA event %d\n", event); break; } return 0; } /* ADD/UPD/DEL */ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; skb = pfkey_xfrm_state2msg(x); if (IS_ERR(skb)) return PTR_ERR(skb); hdr = (struct sadb_msg *) skb->data; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = event2keytype(c->event); hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); return 0; } static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; int err; struct km_event c; x = pfkey_msg2xfrm_state(net, hdr, ext_hdrs); if (IS_ERR(x)) return PTR_ERR(x); xfrm_state_hold(x); if (hdr->sadb_msg_type == SADB_ADD) err = xfrm_state_add(x); else err = xfrm_state_update(x); xfrm_audit_state_add(x, err ? 0 : 1, true); if (err < 0) { x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); goto out; } if (hdr->sadb_msg_type == SADB_ADD) c.event = XFRM_MSG_NEWSA; else c.event = XFRM_MSG_UPDSA; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; km_state_notify(x, &c); out: xfrm_state_put(x); return err; } static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; struct km_event c; int err; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; x = pfkey_xfrm_state_lookup(net, hdr, ext_hdrs); if (x == NULL) return -ESRCH; if ((err = security_xfrm_state_delete(x))) goto out; if (xfrm_state_kern(x)) { err = -EPERM; goto out; } err = xfrm_state_delete(x); if (err < 0) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_DELSA; km_state_notify(x, &c); out: xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; } static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); __u8 proto; struct sk_buff *out_skb; struct sadb_msg *out_hdr; struct xfrm_state *x; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; x = pfkey_xfrm_state_lookup(net, hdr, ext_hdrs); if (x == NULL) return -ESRCH; out_skb = pfkey_xfrm_state2msg(x); proto = x->id.proto; xfrm_state_put(x); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = SADB_GET; out_hdr->sadb_msg_satype = pfkey_proto2satype(proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); return 0; } static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, gfp_t allocation) { struct sk_buff *skb; struct sadb_msg *hdr; int len, auth_len, enc_len, i; auth_len = xfrm_count_pfkey_auth_supported(); if (auth_len) { auth_len *= sizeof(struct sadb_alg); auth_len += sizeof(struct sadb_supported); } enc_len = xfrm_count_pfkey_enc_supported(); if (enc_len) { enc_len *= sizeof(struct sadb_alg); enc_len += sizeof(struct sadb_supported); } len = enc_len + auth_len + sizeof(struct sadb_msg); skb = alloc_skb(len + 16, allocation); if (!skb) goto out_put_algs; hdr = skb_put(skb, sizeof(*hdr)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = 0; hdr->sadb_msg_len = len / sizeof(uint64_t); if (auth_len) { struct sadb_supported *sp; struct sadb_alg *ap; sp = skb_put(skb, auth_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = auth_len / sizeof(uint64_t); sp->sadb_supported_exttype = SADB_EXT_SUPPORTED_AUTH; for (i = 0; ; i++) { struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg->available) *ap++ = aalg->desc; } } if (enc_len) { struct sadb_supported *sp; struct sadb_alg *ap; sp = skb_put(skb, enc_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = enc_len / sizeof(uint64_t); sp->sadb_supported_exttype = SADB_EXT_SUPPORTED_ENCRYPT; for (i = 0; ; i++) { struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (ealg->available) *ap++ = ealg->desc; } } out_put_algs: return skb; } static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); struct sk_buff *supp_skb; if (hdr->sadb_msg_satype > SADB_SATYPE_MAX) return -EINVAL; if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) { if (pfk->registered&(1<<hdr->sadb_msg_satype)) return -EEXIST; pfk->registered |= (1<<hdr->sadb_msg_satype); } mutex_lock(&pfkey_mutex); xfrm_probe_algs(); supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); mutex_unlock(&pfkey_mutex); if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<<hdr->sadb_msg_satype); return -ENOBUFS; } pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk, sock_net(sk)); return 0; } static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) { struct sk_buff *skb; struct sadb_msg *hdr; skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; hdr = skb_put_data(skb, ihdr, sizeof(struct sadb_msg)); hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); } static int key_notify_sa_flush(const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); hdr->sadb_msg_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); unsigned int proto; struct km_event c; int err, err2; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ err = 0; return err ? err : err2; } c.data.proto = proto; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_FLUSHSA; c.net = net; km_state_notify(NULL, &c); return 0; } static int dump_sa(struct xfrm_state *x, int count, void *ptr) { struct pfkey_sock *pfk = ptr; struct sk_buff *out_skb; struct sadb_msg *out_hdr; if (!pfkey_can_dump(&pfk->sk)) return -ENOBUFS; out_skb = pfkey_xfrm_state2msg(x); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; out_hdr->sadb_msg_type = SADB_DUMP; out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = count + 1; out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; return 0; } static int pfkey_dump_sa(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); return xfrm_state_walk(net, &pfk->dump.u.state, dump_sa, (void *) pfk); } static void pfkey_dump_sa_done(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); xfrm_state_walk_done(&pfk->dump.u.state, net); } static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { u8 proto; struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); mutex_lock(&pfk->dump_lock); if (pfk->dump.dump != NULL) { mutex_unlock(&pfk->dump_lock); return -EBUSY; } proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) { mutex_unlock(&pfk->dump_lock); return -EINVAL; } if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); return -ENOMEM; } memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, sizeof(xfrm_address_t)); memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr, sizeof(xfrm_address_t)); filter->family = xfilter->sadb_x_filter_family; filter->splen = xfilter->sadb_x_filter_splen; filter->dplen = xfilter->sadb_x_filter_dplen; } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); int satype = hdr->sadb_msg_satype; bool reset_errno = false; if (hdr->sadb_msg_len == (sizeof(*hdr) / sizeof(uint64_t))) { reset_errno = true; if (satype != 0 && satype != 1) return -EINVAL; pfk->promisc = satype; } if (reset_errno && skb_cloned(skb)) skb = skb_copy(skb, GFP_KERNEL); else skb = skb_clone(skb, GFP_KERNEL); if (reset_errno && skb) { struct sadb_msg *new_hdr = (struct sadb_msg *) skb->data; new_hdr->sadb_msg_errno = 0; } pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk)); return 0; } static int check_reqid(struct xfrm_policy *xp, int dir, int count, void *ptr) { int i; u32 reqid = *(u32*)ptr; for (i=0; i<xp->xfrm_nr; i++) { if (xp->xfrm_vec[i].reqid == reqid) return -EEXIST; } return 0; } static u32 gen_reqid(struct net *net) { struct xfrm_policy_walk walk; u32 start; int rc; static u32 reqid = IPSEC_MANUAL_REQID_MAX; start = reqid; do { ++reqid; if (reqid == 0) reqid = IPSEC_MANUAL_REQID_MAX+1; xfrm_policy_walk_init(&walk, XFRM_POLICY_TYPE_MAIN); rc = xfrm_policy_walk(net, &walk, check_reqid, (void*)&reqid); xfrm_policy_walk_done(&walk, net); if (rc != -EEXIST) return reqid; } while (reqid != start); return 0; } static int parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; int mode; if (xp->xfrm_nr >= XFRM_MAX_DEPTH) return -ELOOP; if (rq->sadb_x_ipsecrequest_mode == 0) return -EINVAL; if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto)) return -EINVAL; t->id.proto = rq->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) return -EINVAL; t->optional = 1; } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; if (!t->reqid && !(t->reqid = gen_reqid(net))) return -ENOBUFS; } /* addresses present only in tunnel mode */ if (t->mode == XFRM_MODE_TUNNEL) { int err; err = parse_sockaddr_pair( (struct sockaddr *)(rq + 1), rq->sadb_x_ipsecrequest_len - sizeof(*rq), &t->saddr, &t->id.daddr, &t->encap_family); if (err) return err; } else t->encap_family = xp->family; /* No way to set this via kame pfkey */ t->allalgs = 1; xp->xfrm_nr++; return 0; } static int parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) { int err; int len = pol->sadb_x_policy_len*8 - sizeof(struct sadb_x_policy); struct sadb_x_ipsecrequest *rq = (void*)(pol+1); if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy)) return -EINVAL; while (len >= sizeof(*rq)) { if (len < rq->sadb_x_ipsecrequest_len || rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); } return 0; } static inline int pfkey_xfrm_policy2sec_ctx_size(const struct xfrm_policy *xp) { struct xfrm_sec_ctx *xfrm_ctx = xp->security; if (xfrm_ctx) { int len = sizeof(struct sadb_x_sec_ctx); len += xfrm_ctx->ctx_len; return PFKEY_ALIGN8(len); } return 0; } static int pfkey_xfrm_policy2msg_size(const struct xfrm_policy *xp) { const struct xfrm_tmpl *t; int sockaddr_size = pfkey_sockaddr_size(xp->family); int socklen = 0; int i; for (i=0; i<xp->xfrm_nr; i++) { t = xp->xfrm_vec + i; socklen += pfkey_sockaddr_len(t->encap_family); } return sizeof(struct sadb_msg) + (sizeof(struct sadb_lifetime) * 3) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + sizeof(struct sadb_x_policy) + (xp->xfrm_nr * sizeof(struct sadb_x_ipsecrequest)) + (socklen * 2) + pfkey_xfrm_policy2sec_ctx_size(xp); } static struct sk_buff * pfkey_xfrm_policy2msg_prep(const struct xfrm_policy *xp) { struct sk_buff *skb; int size; size = pfkey_xfrm_policy2msg_size(xp); skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return ERR_PTR(-ENOBUFS); return skb; } static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy *xp, int dir) { struct sadb_msg *hdr; struct sadb_address *addr; struct sadb_lifetime *lifetime; struct sadb_x_policy *pol; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int i; int size; int sockaddr_size = pfkey_sockaddr_size(xp->family); int socklen = pfkey_sockaddr_len(xp->family); size = pfkey_xfrm_policy2msg_size(xp); /* call should fill header later */ hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = pfkey_proto_from_xfrm(xp->selector.proto); addr->sadb_address_prefixlen = xp->selector.prefixlen_s; addr->sadb_address_reserved = 0; if (!pfkey_sockaddr_fill(&xp->selector.saddr, xp->selector.sport, (struct sockaddr *) (addr + 1), xp->family)) BUG(); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = pfkey_proto_from_xfrm(xp->selector.proto); addr->sadb_address_prefixlen = xp->selector.prefixlen_d; addr->sadb_address_reserved = 0; pfkey_sockaddr_fill(&xp->selector.daddr, xp->selector.dport, (struct sockaddr *) (addr + 1), xp->family); /* hard time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; lifetime->sadb_lifetime_allocations = _X2KEY(xp->lft.hard_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(xp->lft.hard_byte_limit); lifetime->sadb_lifetime_addtime = xp->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.hard_use_expires_seconds; /* soft time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; lifetime->sadb_lifetime_allocations = _X2KEY(xp->lft.soft_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(xp->lft.soft_byte_limit); lifetime->sadb_lifetime_addtime = xp->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.soft_use_expires_seconds; /* current time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; lifetime->sadb_lifetime_allocations = xp->curlft.packets; lifetime->sadb_lifetime_bytes = xp->curlft.bytes; lifetime->sadb_lifetime_addtime = xp->curlft.add_time; lifetime->sadb_lifetime_usetime = xp->curlft.use_time; pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_DISCARD; if (xp->action == XFRM_POLICY_ALLOW) { if (xp->xfrm_nr) pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; else pol->sadb_x_policy_type = IPSEC_POLICY_NONE; } pol->sadb_x_policy_dir = dir+1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; for (i=0; i<xp->xfrm_nr; i++) { const struct xfrm_tmpl *t = xp->xfrm_vec + i; struct sadb_x_ipsecrequest *rq; int req_size; int mode; req_size = sizeof(struct sadb_x_ipsecrequest); if (t->mode == XFRM_MODE_TUNNEL) { socklen = pfkey_sockaddr_len(t->encap_family); req_size += socklen * 2; } else { size -= 2*socklen; } rq = skb_put(skb, req_size); pol->sadb_x_policy_len += req_size/8; memset(rq, 0, sizeof(*rq)); rq->sadb_x_ipsecrequest_len = req_size; rq->sadb_x_ipsecrequest_proto = t->id.proto; if ((mode = pfkey_mode_from_xfrm(t->mode)) < 0) return -EINVAL; rq->sadb_x_ipsecrequest_mode = mode; rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_REQUIRE; if (t->reqid) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_UNIQUE; if (t->optional) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_USE; rq->sadb_x_ipsecrequest_reqid = t->reqid; if (t->mode == XFRM_MODE_TUNNEL) { u8 *sa = (void *)(rq + 1); pfkey_sockaddr_fill(&t->saddr, 0, (struct sockaddr *)sa, t->encap_family); pfkey_sockaddr_fill(&t->id.daddr, 0, (struct sockaddr *) (sa + socklen), t->encap_family); } } /* security context */ if ((xfrm_ctx = xp->security)) { int ctx_size = pfkey_xfrm_policy2sec_ctx_size(xp); sec_ctx = skb_put(skb, ctx_size); sec_ctx->sadb_x_sec_len = ctx_size / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_reserved = refcount_read(&xp->refcnt); return 0; } static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; int err; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); return err; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; if (c->data.byid && c->event == XFRM_MSG_DELPOLICY) out_hdr->sadb_msg_type = SADB_X_SPDDELETE2; else out_hdr->sadb_msg_type = event2poltype(c->event); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; out_hdr->sadb_msg_pid = c->portid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); return 0; } static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); int err = 0; struct sadb_lifetime *lifetime; struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct km_event c; struct sadb_x_sec_ctx *sec_ctx; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || !ext_hdrs[SADB_X_EXT_POLICY-1]) return -EINVAL; pol = ext_hdrs[SADB_X_EXT_POLICY-1]; if (pol->sadb_x_policy_type > IPSEC_POLICY_IPSEC) return -EINVAL; if (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) return -EINVAL; xp = xfrm_policy_alloc(net, GFP_KERNEL); if (xp == NULL) return -ENOBUFS; xp->action = (pol->sadb_x_policy_type == IPSEC_POLICY_DISCARD ? XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->priority = pol->sadb_x_policy_priority; sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; xp->family = pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.saddr); xp->selector.family = xp->family; xp->selector.prefixlen_s = sa->sadb_address_prefixlen; xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.sport) xp->selector.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.daddr); xp->selector.prefixlen_d = sa->sadb_address_prefixlen; /* Amusing, we set this twice. KAME apps appear to set same value * in both addresses. */ xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.dport) xp->selector.dport_mask = htons(0xffff); sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) { err = -ENOBUFS; goto out; } err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL); kfree(uctx); if (err) goto out; } xp->lft.soft_byte_limit = XFRM_INF; xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; if ((lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD-1]) != NULL) { xp->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); xp->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); xp->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; xp->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } if ((lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]) != NULL) { xp->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); xp->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); xp->lft.soft_add_expires_seconds = lifetime->sadb_lifetime_addtime; xp->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && (err = parse_ipsecrequests(xp, pol)) < 0) goto out; err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp, hdr->sadb_msg_type != SADB_X_SPDUPDATE); xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) goto out; if (hdr->sadb_msg_type == SADB_X_SPDUPDATE) c.event = XFRM_MSG_UPDPOLICY; else c.event = XFRM_MSG_NEWPOLICY; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); xfrm_pol_put(xp); return 0; out: xp->walk.dead = 1; xfrm_policy_destroy(xp); return err; } static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); int err; struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct xfrm_selector sel; struct km_event c; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *pol_ctx = NULL; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || !ext_hdrs[SADB_X_EXT_POLICY-1]) return -EINVAL; pol = ext_hdrs[SADB_X_EXT_POLICY-1]; if (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) return -EINVAL; memset(&sel, 0, sizeof(sel)); sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.sport) sel.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.dport) sel.dport_mask = htons(0xffff); sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) return -ENOMEM; err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL); kfree(uctx); if (err) return err; } xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); if (xp == NULL) return -ENOENT; xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.data.byid = 0; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); out: xfrm_pol_put(xp); return err; } static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struct sadb_msg *hdr, int dir) { int err; struct sk_buff *out_skb; struct sadb_msg *out_hdr; err = 0; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) { err = PTR_ERR(out_skb); goto out; } err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); goto out; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = hdr->sadb_msg_type; out_hdr->sadb_msg_satype = 0; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp)); err = 0; out: return err; } static int pfkey_sockaddr_pair_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2); } static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, xfrm_address_t *saddr, xfrm_address_t *daddr, u16 *family) { int af, socklen; if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) return -EINVAL; af = pfkey_sockaddr_extract(sa, saddr); if (!af) return -EINVAL; socklen = pfkey_sockaddr_len(af); if (pfkey_sockaddr_extract((struct sockaddr *) (((u8 *)sa) + socklen), daddr) != af) return -EINVAL; *family = af; return 0; } #ifdef CONFIG_NET_KEY_MIGRATE static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct xfrm_migrate *m) { int err; struct sadb_x_ipsecrequest *rq2; int mode; if (len < sizeof(*rq1) || len < rq1->sadb_x_ipsecrequest_len || rq1->sadb_x_ipsecrequest_len < sizeof(*rq1)) return -EINVAL; /* old endoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1), rq1->sadb_x_ipsecrequest_len - sizeof(*rq1), &m->old_saddr, &m->old_daddr, &m->old_family); if (err) return err; rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len); len -= rq1->sadb_x_ipsecrequest_len; if (len <= sizeof(*rq2) || len < rq2->sadb_x_ipsecrequest_len || rq2->sadb_x_ipsecrequest_len < sizeof(*rq2)) return -EINVAL; /* new endpoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1), rq2->sadb_x_ipsecrequest_len - sizeof(*rq2), &m->new_saddr, &m->new_daddr, &m->new_family); if (err) return err; if (rq1->sadb_x_ipsecrequest_proto != rq2->sadb_x_ipsecrequest_proto || rq1->sadb_x_ipsecrequest_mode != rq2->sadb_x_ipsecrequest_mode || rq1->sadb_x_ipsecrequest_reqid != rq2->sadb_x_ipsecrequest_reqid) return -EINVAL; m->proto = rq1->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq1->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; m->mode = mode; m->reqid = rq1->sadb_x_ipsecrequest_reqid; return ((int)(rq1->sadb_x_ipsecrequest_len + rq2->sadb_x_ipsecrequest_len)); } static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { int i, len, ret, err = -EINVAL; u8 dir; struct sadb_address *sa; struct sadb_x_kmaddress *kma; struct sadb_x_policy *pol; struct sadb_x_ipsecrequest *rq; struct xfrm_selector sel; struct xfrm_migrate m[XFRM_MAX_DEPTH]; struct xfrm_kmaddress k; struct net *net = sock_net(sk); if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC - 1], ext_hdrs[SADB_EXT_ADDRESS_DST - 1]) || !ext_hdrs[SADB_X_EXT_POLICY - 1]) { err = -EINVAL; goto out; } kma = ext_hdrs[SADB_X_EXT_KMADDRESS - 1]; pol = ext_hdrs[SADB_X_EXT_POLICY - 1]; if (pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) { err = -EINVAL; goto out; } if (kma) { /* convert sadb_x_kmaddress to xfrm_kmaddress */ k.reserved = kma->sadb_x_kmaddress_reserved; ret = parse_sockaddr_pair((struct sockaddr *)(kma + 1), 8*(kma->sadb_x_kmaddress_len) - sizeof(*kma), &k.local, &k.remote, &k.family); if (ret < 0) { err = ret; goto out; } } dir = pol->sadb_x_policy_dir - 1; memset(&sel, 0, sizeof(sel)); /* set source address info of selector */ sa = ext_hdrs[SADB_EXT_ADDRESS_SRC - 1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa + 1))->sin_port; if (sel.sport) sel.sport_mask = htons(0xffff); /* set destination address info of selector */ sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa + 1))->sin_port; if (sel.dport) sel.dport_mask = htons(0xffff); rq = (struct sadb_x_ipsecrequest *)(pol + 1); /* extract ipsecrequests */ i = 0; len = pol->sadb_x_policy_len * 8 - sizeof(struct sadb_x_policy); while (len > 0 && i < XFRM_MAX_DEPTH) { ret = ipsecrequests_to_migrate(rq, len, &m[i]); if (ret < 0) { err = ret; goto out; } else { rq = (struct sadb_x_ipsecrequest *)((u8 *)rq + ret); len -= ret; i++; } } if (!i || len > 0) { err = -EINVAL; goto out; } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, kma ? &k : NULL, net, NULL, 0, NULL); out: return err; } #else static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { return -ENOPROTOOPT; } #endif static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); unsigned int dir; int err = 0, delete; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct km_event c; if ((pol = ext_hdrs[SADB_X_EXT_POLICY-1]) == NULL) return -EINVAL; dir = xfrm_policy_id2dir(pol->sadb_x_policy_id); if (dir >= XFRM_POLICY_MAX) return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; if (delete) { xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.data.byid = 1; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, dir, &c); } else { err = key_pol_get_resp(sk, xp, hdr, dir); } out: xfrm_pol_put(xp); return err; } static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) { struct pfkey_sock *pfk = ptr; struct sk_buff *out_skb; struct sadb_msg *out_hdr; int err; if (!pfkey_can_dump(&pfk->sk)) return -ENOBUFS; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); return err; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; out_hdr->sadb_msg_type = SADB_X_SPDDUMP; out_hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = count + 1; out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; return 0; } static int pfkey_dump_sp(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); return xfrm_policy_walk(net, &pfk->dump.u.policy, dump_sp, (void *) pfk); } static void pfkey_dump_sp_done(struct pfkey_sock *pfk) { struct net *net = sock_net((struct sock *)pfk); xfrm_policy_walk_done(&pfk->dump.u.policy, net); } static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); mutex_lock(&pfk->dump_lock); if (pfk->dump.dump != NULL) { mutex_unlock(&pfk->dump_lock); return -EBUSY; } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } static int key_notify_policy_flush(const struct km_event *c) { struct sk_buff *skb_out; struct sadb_msg *hdr; skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb_out) return -ENOBUFS; hdr = skb_put(skb_out, sizeof(struct sadb_msg)); hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct km_event c; int err, err2; err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - old silent behavior */ return 0; return err; } c.data.type = XFRM_POLICY_TYPE_MAIN; c.event = XFRM_MSG_FLUSHPOLICY; c.portid = hdr->sadb_msg_pid; c.seq = hdr->sadb_msg_seq; c.net = net; km_policy_notify(NULL, 0, &c); return 0; } typedef int (*pfkey_handler)(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs); static const pfkey_handler pfkey_funcs[SADB_MAX + 1] = { [SADB_RESERVED] = pfkey_reserved, [SADB_GETSPI] = pfkey_getspi, [SADB_UPDATE] = pfkey_add, [SADB_ADD] = pfkey_add, [SADB_DELETE] = pfkey_delete, [SADB_GET] = pfkey_get, [SADB_ACQUIRE] = pfkey_acquire, [SADB_REGISTER] = pfkey_register, [SADB_EXPIRE] = NULL, [SADB_FLUSH] = pfkey_flush, [SADB_DUMP] = pfkey_dump, [SADB_X_PROMISC] = pfkey_promisc, [SADB_X_PCHANGE] = NULL, [SADB_X_SPDUPDATE] = pfkey_spdadd, [SADB_X_SPDADD] = pfkey_spdadd, [SADB_X_SPDDELETE] = pfkey_spddelete, [SADB_X_SPDGET] = pfkey_spdget, [SADB_X_SPDACQUIRE] = NULL, [SADB_X_SPDDUMP] = pfkey_spddump, [SADB_X_SPDFLUSH] = pfkey_spdflush, [SADB_X_SPDSETIDX] = pfkey_spdadd, [SADB_X_SPDDELETE2] = pfkey_spdget, [SADB_X_MIGRATE] = pfkey_migrate, }; static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr) { void *ext_hdrs[SADB_EXT_MAX]; int err; /* Non-zero return value of pfkey_broadcast() does not always signal * an error and even on an actual error we may still want to process * the message so rather ignore the return value. */ pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); if (!err) { err = -EOPNOTSUPP; if (pfkey_funcs[hdr->sadb_msg_type]) err = pfkey_funcs[hdr->sadb_msg_type](sk, skb, hdr, ext_hdrs); } return err; } static struct sadb_msg *pfkey_get_base_msg(struct sk_buff *skb, int *errp) { struct sadb_msg *hdr = NULL; if (skb->len < sizeof(*hdr)) { *errp = -EMSGSIZE; } else { hdr = (struct sadb_msg *) skb->data; if (hdr->sadb_msg_version != PF_KEY_V2 || hdr->sadb_msg_reserved != 0 || (hdr->sadb_msg_type <= SADB_RESERVED || hdr->sadb_msg_type > SADB_MAX)) { hdr = NULL; *errp = -EINVAL; } else if (hdr->sadb_msg_len != (skb->len / sizeof(uint64_t)) || hdr->sadb_msg_len < (sizeof(struct sadb_msg) / sizeof(uint64_t))) { hdr = NULL; *errp = -EMSGSIZE; } else { *errp = 0; } } return hdr; } static inline int aalg_tmpl_set(const struct xfrm_tmpl *t, const struct xfrm_algo_desc *d) { unsigned int id = d->desc.sadb_alg_id; if (id >= sizeof(t->aalgos) * 8) return 0; return (t->aalgos >> id) & 1; } static inline int ealg_tmpl_set(const struct xfrm_tmpl *t, const struct xfrm_algo_desc *d) { unsigned int id = d->desc.sadb_alg_id; if (id >= sizeof(t->ealgos) * 8) return 0; return (t->ealgos >> id) & 1; } static int count_ah_combs(const struct xfrm_tmpl *t) { int i, sz = 0; for (i = 0; ; i++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); } static int count_esp_combs(const struct xfrm_tmpl *t) { int i, k, sz = 0; for (i = 0; ; i++) { const struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; memset(p->sadb_prop_reserved, 0, sizeof(p->sadb_prop_reserved)); for (i = 0; ; i++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg) && aalg->available) { struct sadb_comb *c; c = skb_put_zero(skb, sizeof(struct sadb_comb)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; c->sadb_comb_auth_maxbits = aalg->desc.sadb_alg_maxbits; c->sadb_comb_hard_addtime = 24*60*60; c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; sz += sizeof(*c); } } return sz + sizeof(*p); } static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; memset(p->sadb_prop_reserved, 0, sizeof(p->sadb_prop_reserved)); for (i=0; ; i++) { const struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { struct sadb_comb *c; const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (!(aalg_tmpl_set(t, aalg) && aalg->available)) continue; c = skb_put(skb, sizeof(struct sadb_comb)); memset(c, 0, sizeof(*c)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; c->sadb_comb_auth_maxbits = aalg->desc.sadb_alg_maxbits; c->sadb_comb_encrypt = ealg->desc.sadb_alg_id; c->sadb_comb_encrypt_minbits = ealg->desc.sadb_alg_minbits; c->sadb_comb_encrypt_maxbits = ealg->desc.sadb_alg_maxbits; c->sadb_comb_hard_addtime = 24*60*60; c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; sz += sizeof(*c); } } return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) { return 0; } static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; int hard; int hsc; hard = c->data.hard; if (hard) hsc = 2; else hsc = 1; out_skb = pfkey_xfrm_state2msg_expire(x, hsc); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; out_hdr->sadb_msg_type = SADB_EXPIRE; out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = 0; out_hdr->sadb_msg_pid = 0; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); return 0; } static int pfkey_send_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = x ? xs_net(x) : c->net; struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); if (atomic_read(&net_pfkey->socks_nr) == 0) return 0; switch (c->event) { case XFRM_MSG_EXPIRE: return key_notify_sa_expire(x, c); case XFRM_MSG_DELSA: case XFRM_MSG_NEWSA: case XFRM_MSG_UPDSA: return key_notify_sa(x, c); case XFRM_MSG_FLUSHSA: return key_notify_sa_flush(c); case XFRM_MSG_NEWAE: /* not yet supported */ break; default: pr_err("pfkey: Unknown SA event %d\n", c->event); break; } return 0; } static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { if (xp && xp->type != XFRM_POLICY_TYPE_MAIN) return 0; switch (c->event) { case XFRM_MSG_POLEXPIRE: return key_notify_policy_expire(xp, c); case XFRM_MSG_DELPOLICY: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDPOLICY: return key_notify_policy(xp, dir, c); case XFRM_MSG_FLUSHPOLICY: if (c->data.type != XFRM_POLICY_TYPE_MAIN) break; return key_notify_policy_flush(c); default: pr_err("pfkey: Unknown policy event %d\n", c->event); break; } return 0; } static u32 get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } static bool pfkey_is_alive(const struct km_event *c) { struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id); struct sock *sk; bool is_alive = false; rcu_read_lock(); sk_for_each_rcu(sk, &net_pfkey->table) { if (pfkey_sk(sk)->registered) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_address *addr; struct sadb_x_policy *pol; int sockaddr_size; int size; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return -EINVAL; size = sizeof(struct sadb_msg) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_ACQUIRE; hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = x->km.seq = get_acqseq(); hdr->sadb_msg_pid = 0; /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = XFRM_POLICY_OUT + 1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ alg_size = 0; if (x->id.proto == IPPROTO_AH) alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) alg_size = dump_esp_combs(skb, t); hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { sec_ctx = skb_put(skb, sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); } static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { struct net *net = sock_net(sk); struct xfrm_policy *xp; struct sadb_x_policy *pol = (struct sadb_x_policy*)data; struct sadb_x_sec_ctx *sec_ctx; switch (sk->sk_family) { case AF_INET: if (opt != IP_IPSEC_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (opt != IPV6_IPSEC_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #endif default: *dir = -EINVAL; return NULL; } *dir = -EINVAL; if (len < sizeof(struct sadb_x_policy) || pol->sadb_x_policy_len*8 > len || pol->sadb_x_policy_type > IPSEC_POLICY_BYPASS || (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir > IPSEC_DIR_OUTBOUND)) return NULL; xp = xfrm_policy_alloc(net, GFP_ATOMIC); if (xp == NULL) { *dir = -ENOBUFS; return NULL; } xp->action = (pol->sadb_x_policy_type == IPSEC_POLICY_DISCARD ? XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->lft.soft_byte_limit = XFRM_INF; xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; xp->family = sk->sk_family; xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && (*dir = parse_ipsecrequests(xp, pol)) < 0) goto out; /* security context too */ if (len >= (pol->sadb_x_policy_len*8 + sizeof(struct sadb_x_sec_ctx))) { char *p = (char *)pol; struct xfrm_user_sec_ctx *uctx; p += pol->sadb_x_policy_len*8; sec_ctx = (struct sadb_x_sec_ctx *)p; if (len < pol->sadb_x_policy_len*8 + sec_ctx->sadb_x_sec_len*8) { *dir = -EINVAL; goto out; } if ((*dir = verify_sec_ctx_len(p))) goto out; uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC); *dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC); kfree(uctx); if (*dir) goto out; } *dir = pol->sadb_x_policy_dir-1; return xp; out: xp->walk.dead = 1; xfrm_policy_destroy(xp); return NULL; } static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_sa *sa; struct sadb_address *addr; struct sadb_x_nat_t_port *n_port; int sockaddr_size; int size; __u8 satype = (x->id.proto == IPPROTO_ESP ? SADB_SATYPE_ESP : 0); struct xfrm_encap_tmpl *natt = NULL; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return -EINVAL; if (!satype) return -EINVAL; if (!x->encap) return -EINVAL; natt = x->encap; /* Build an SADB_X_NAT_T_NEW_MAPPING message: * * HDR | SA | ADDRESS_SRC (old addr) | NAT_T_SPORT (old port) | * ADDRESS_DST (new addr) | NAT_T_DPORT (new port) */ size = sizeof(struct sadb_msg) + sizeof(struct sadb_sa) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + (sizeof(struct sadb_x_nat_t_port) * 2); skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_NAT_T_NEW_MAPPING; hdr->sadb_msg_satype = satype; hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0; /* SA */ sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = 0; sa->sadb_sa_state = 0; sa->sadb_sa_auth = 0; sa->sadb_sa_encrypt = 0; sa->sadb_sa_flags = 0; /* ADDRESS_SRC (old addr) */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* NAT_T_SPORT (old port) */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* ADDRESS_DST (new addr) */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(ipaddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* NAT_T_DPORT (new port) */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = sport; n_port->sadb_x_nat_t_port_reserved = 0; return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); } #ifdef CONFIG_NET_KEY_MIGRATE static int set_sadb_address(struct sk_buff *skb, int sasize, int type, const struct xfrm_selector *sel) { struct sadb_address *addr; addr = skb_put(skb, sizeof(struct sadb_address) + sasize); addr->sadb_address_len = (sizeof(struct sadb_address) + sasize)/8; addr->sadb_address_exttype = type; addr->sadb_address_proto = sel->proto; addr->sadb_address_reserved = 0; switch (type) { case SADB_EXT_ADDRESS_SRC: addr->sadb_address_prefixlen = sel->prefixlen_s; pfkey_sockaddr_fill(&sel->saddr, 0, (struct sockaddr *)(addr + 1), sel->family); break; case SADB_EXT_ADDRESS_DST: addr->sadb_address_prefixlen = sel->prefixlen_d; pfkey_sockaddr_fill(&sel->daddr, 0, (struct sockaddr *)(addr + 1), sel->family); break; default: return -EINVAL; } return 0; } static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress *k) { struct sadb_x_kmaddress *kma; u8 *sa; int family = k->family; int socklen = pfkey_sockaddr_len(family); int size_req; size_req = (sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(family)); kma = skb_put_zero(skb, size_req); kma->sadb_x_kmaddress_len = size_req / 8; kma->sadb_x_kmaddress_exttype = SADB_X_EXT_KMADDRESS; kma->sadb_x_kmaddress_reserved = k->reserved; sa = (u8 *)(kma + 1); if (!pfkey_sockaddr_fill(&k->local, 0, (struct sockaddr *)sa, family) || !pfkey_sockaddr_fill(&k->remote, 0, (struct sockaddr *)(sa+socklen), family)) return -EINVAL; return 0; } static int set_ipsecrequest(struct sk_buff *skb, uint8_t proto, uint8_t mode, int level, uint32_t reqid, uint8_t family, const xfrm_address_t *src, const xfrm_address_t *dst) { struct sadb_x_ipsecrequest *rq; u8 *sa; int socklen = pfkey_sockaddr_len(family); int size_req; size_req = sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(family); rq = skb_put_zero(skb, size_req); rq->sadb_x_ipsecrequest_len = size_req; rq->sadb_x_ipsecrequest_proto = proto; rq->sadb_x_ipsecrequest_mode = mode; rq->sadb_x_ipsecrequest_level = level; rq->sadb_x_ipsecrequest_reqid = reqid; sa = (u8 *) (rq + 1); if (!pfkey_sockaddr_fill(src, 0, (struct sockaddr *)sa, family) || !pfkey_sockaddr_fill(dst, 0, (struct sockaddr *)(sa + socklen), family)) return -EINVAL; return 0; } #endif #ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { int i; int sasize_sel; int size = 0; int size_pol = 0; struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_x_policy *pol; const struct xfrm_migrate *mp; if (type != XFRM_POLICY_TYPE_MAIN) return 0; if (num_bundles <= 0 || num_bundles > XFRM_MAX_DEPTH) return -EINVAL; if (k != NULL) { /* addresses for KM */ size += PFKEY_ALIGN8(sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(k->family)); } /* selector */ sasize_sel = pfkey_sockaddr_size(sel->family); if (!sasize_sel) return -EINVAL; size += (sizeof(struct sadb_address) + sasize_sel) * 2; /* policy info */ size_pol += sizeof(struct sadb_x_policy); /* ipsecrequests */ for (i = 0, mp = m; i < num_bundles; i++, mp++) { /* old locator pair */ size_pol += sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(mp->old_family); /* new locator pair */ size_pol += sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(mp->new_family); } size += sizeof(struct sadb_msg) + size_pol; /* alloc buffer */ skb = alloc_skb(size, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_MIGRATE; hdr->sadb_msg_satype = pfkey_proto2satype(m->proto); hdr->sadb_msg_len = size / 8; hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = 0; hdr->sadb_msg_pid = 0; /* Addresses to be used by KM for negotiation, if ext is available */ if (k != NULL && (set_sadb_kmaddress(skb, k) < 0)) goto err; /* selector src */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_SRC, sel); /* selector dst */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_DST, sel); /* policy information */ pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = size_pol / 8; pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir + 1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = 0; pol->sadb_x_policy_priority = 0; for (i = 0, mp = m; i < num_bundles; i++, mp++) { /* old ipsecrequest */ int mode = pfkey_mode_from_xfrm(mp->mode); if (mode < 0) goto err; if (set_ipsecrequest(skb, mp->proto, mode, (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE), mp->reqid, mp->old_family, &mp->old_saddr, &mp->old_daddr) < 0) goto err; /* new ipsecrequest */ if (set_ipsecrequest(skb, mp->proto, mode, (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE), mp->reqid, mp->new_family, &mp->new_saddr, &mp->new_daddr) < 0) goto err; } /* broadcast migrate message to sockets */ pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); return 0; err: kfree_skb(skb); return -EINVAL; } #else static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } #endif static int pfkey_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb = NULL; struct sadb_msg *hdr = NULL; int err; struct net *net = sock_net(sk); err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) goto out; err = -EMSGSIZE; if ((unsigned int)len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = alloc_skb(len, GFP_KERNEL); if (skb == NULL) goto out; err = -EFAULT; if (memcpy_from_msg(skb_put(skb,len), msg, len)) goto out; hdr = pfkey_get_base_msg(skb, &err); if (!hdr) goto out; mutex_lock(&net->xfrm.xfrm_cfg_mutex); err = pfkey_process(sk, skb, hdr); mutex_unlock(&net->xfrm.xfrm_cfg_mutex); out: if (err && hdr && pfkey_error(hdr, err, sk) == 0) err = 0; kfree_skb(skb); return err ? : len; } static int pfkey_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct pfkey_sock *pfk = pfkey_sk(sk); struct sk_buff *skb; int copied, err; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) goto out; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; sock_recv_cmsgs(msg, sk, skb); err = (flags & MSG_TRUNC) ? skb->len : copied; if (pfk->dump.dump != NULL && 3 * atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) pfkey_do_dump(pfk); out_free: skb_free_datagram(sk, skb); out: return err; } static const struct proto_ops pfkey_ops = { .family = PF_KEY, .owner = THIS_MODULE, /* Operations that make no sense on pfkey sockets. */ .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, /* Now the operations that really occur. */ .release = pfkey_release, .poll = datagram_poll, .sendmsg = pfkey_sendmsg, .recvmsg = pfkey_recvmsg, }; static const struct net_proto_family pfkey_family_ops = { .family = PF_KEY, .create = pfkey_create, .owner = THIS_MODULE, }; #ifdef CONFIG_PROC_FS static int pfkey_seq_show(struct seq_file *f, void *v) { struct sock *s = sk_entry(v); if (v == SEQ_START_TOKEN) seq_printf(f ,"sk RefCnt Rmem Wmem User Inode\n"); else seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), from_kuid_munged(seq_user_ns(f), sock_i_uid(s)), sock_i_ino(s) ); return 0; } static void *pfkey_seq_start(struct seq_file *f, loff_t *ppos) __acquires(rcu) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); rcu_read_lock(); return seq_hlist_start_head_rcu(&net_pfkey->table, *ppos); } static void *pfkey_seq_next(struct seq_file *f, void *v, loff_t *ppos) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); return seq_hlist_next_rcu(v, &net_pfkey->table, ppos); } static void pfkey_seq_stop(struct seq_file *f, void *v) __releases(rcu) { rcu_read_unlock(); } static const struct seq_operations pfkey_seq_ops = { .start = pfkey_seq_start, .next = pfkey_seq_next, .stop = pfkey_seq_stop, .show = pfkey_seq_show, }; static int __net_init pfkey_init_proc(struct net *net) { struct proc_dir_entry *e; e = proc_create_net("pfkey", 0, net->proc_net, &pfkey_seq_ops, sizeof(struct seq_net_private)); if (e == NULL) return -ENOMEM; return 0; } static void __net_exit pfkey_exit_proc(struct net *net) { remove_proc_entry("pfkey", net->proc_net); } #else static inline int pfkey_init_proc(struct net *net) { return 0; } static inline void pfkey_exit_proc(struct net *net) { } #endif static struct xfrm_mgr pfkeyv2_mgr = { .notify = pfkey_send_notify, .acquire = pfkey_send_acquire, .compile_policy = pfkey_compile_policy, .new_mapping = pfkey_send_new_mapping, .notify_policy = pfkey_send_policy_notify, .migrate = pfkey_send_migrate, .is_alive = pfkey_is_alive, }; static int __net_init pfkey_net_init(struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); int rv; INIT_HLIST_HEAD(&net_pfkey->table); atomic_set(&net_pfkey->socks_nr, 0); rv = pfkey_init_proc(net); return rv; } static void __net_exit pfkey_net_exit(struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_exit_proc(net); WARN_ON(!hlist_empty(&net_pfkey->table)); } static struct pernet_operations pfkey_net_ops = { .init = pfkey_net_init, .exit = pfkey_net_exit, .id = &pfkey_net_id, .size = sizeof(struct netns_pfkey), }; static void __exit ipsec_pfkey_exit(void) { xfrm_unregister_km(&pfkeyv2_mgr); sock_unregister(PF_KEY); unregister_pernet_subsys(&pfkey_net_ops); proto_unregister(&key_proto); } static int __init ipsec_pfkey_init(void) { int err = proto_register(&key_proto, 0); if (err != 0) goto out; err = register_pernet_subsys(&pfkey_net_ops); if (err != 0) goto out_unregister_key_proto; err = sock_register(&pfkey_family_ops); if (err != 0) goto out_unregister_pernet; xfrm_register_km(&pfkeyv2_mgr); out: return err; out_unregister_pernet: unregister_pernet_subsys(&pfkey_net_ops); out_unregister_key_proto: proto_unregister(&key_proto); goto out; } module_init(ipsec_pfkey_init); module_exit(ipsec_pfkey_exit); MODULE_DESCRIPTION("PF_KEY socket helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_KEY); |
| 2 1 2 1 1 1 3 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 | // SPDX-License-Identifier: GPL-2.0 /* * super.c * * Copyright (c) 1999 Al Smith * * Portions derived from work (c) 1995,1996 Christian Vogelgsang. */ #include <linux/init.h> #include <linux/module.h> #include <linux/exportfs.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "efs.h" #include <linux/efs_vh.h> #include <linux/efs_fs_sb.h> static int efs_statfs(struct dentry *dentry, struct kstatfs *buf); static int efs_init_fs_context(struct fs_context *fc); static void efs_kill_sb(struct super_block *s) { struct efs_sb_info *sbi = SUPER_INFO(s); kill_block_super(s); kfree(sbi); } static struct pt_types sgi_pt_types[] = { {0x00, "SGI vh"}, {0x01, "SGI trkrepl"}, {0x02, "SGI secrepl"}, {0x03, "SGI raw"}, {0x04, "SGI bsd"}, {SGI_SYSV, "SGI sysv"}, {0x06, "SGI vol"}, {SGI_EFS, "SGI efs"}, {0x08, "SGI lv"}, {0x09, "SGI rlv"}, {0x0A, "SGI xfs"}, {0x0B, "SGI xfslog"}, {0x0C, "SGI xlv"}, {0x82, "Linux swap"}, {0x83, "Linux native"}, {0, NULL} }; enum { Opt_explicit_open, }; static const struct fs_parameter_spec efs_param_spec[] = { fsparam_flag ("explicit-open", Opt_explicit_open), {} }; /* * File system definition and registration. */ static struct file_system_type efs_fs_type = { .owner = THIS_MODULE, .name = "efs", .kill_sb = efs_kill_sb, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = efs_init_fs_context, .parameters = efs_param_spec, }; MODULE_ALIAS_FS("efs"); static struct kmem_cache * efs_inode_cachep; static struct inode *efs_alloc_inode(struct super_block *sb) { struct efs_inode_info *ei; ei = alloc_inode_sb(sb, efs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void efs_free_inode(struct inode *inode) { kmem_cache_free(efs_inode_cachep, INODE_INFO(inode)); } static void init_once(void *foo) { struct efs_inode_info *ei = (struct efs_inode_info *) foo; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", sizeof(struct efs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, init_once); if (efs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(efs_inode_cachep); } static const struct super_operations efs_superblock_operations = { .alloc_inode = efs_alloc_inode, .free_inode = efs_free_inode, .statfs = efs_statfs, }; static const struct export_operations efs_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = efs_fh_to_dentry, .fh_to_parent = efs_fh_to_parent, .get_parent = efs_get_parent, }; static int __init init_efs_fs(void) { int err; pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); err = init_inodecache(); if (err) goto out1; err = register_filesystem(&efs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_efs_fs(void) { unregister_filesystem(&efs_fs_type); destroy_inodecache(); } module_init(init_efs_fs) module_exit(exit_efs_fs) static efs_block_t efs_validate_vh(struct volume_header *vh) { int i; __be32 cs, *ui; int csum; efs_block_t sblock = 0; /* shuts up gcc */ struct pt_types *pt_entry; int pt_type, slice = -1; if (be32_to_cpu(vh->vh_magic) != VHMAGIC) { /* * assume that we're dealing with a partition and allow * read_super() to try and detect a valid superblock * on the next block. */ return 0; } ui = ((__be32 *) (vh + 1)) - 1; for(csum = 0; ui >= ((__be32 *) vh);) { cs = *ui--; csum += be32_to_cpu(cs); } if (csum) { pr_warn("SGI disklabel: checksum bad, label corrupted\n"); return 0; } #ifdef DEBUG pr_debug("bf: \"%16s\"\n", vh->vh_bootfile); for(i = 0; i < NVDIR; i++) { int j; char name[VDNAMESIZE+1]; for(j = 0; j < VDNAMESIZE; j++) { name[j] = vh->vh_vd[i].vd_name[j]; } name[j] = (char) 0; if (name[0]) { pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n", name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn), (int) be32_to_cpu(vh->vh_vd[i].vd_nbytes)); } } #endif for(i = 0; i < NPARTAB; i++) { pt_type = (int) be32_to_cpu(vh->vh_pt[i].pt_type); for(pt_entry = sgi_pt_types; pt_entry->pt_name; pt_entry++) { if (pt_type == pt_entry->pt_type) break; } #ifdef DEBUG if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) { pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n", i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn), (int)be32_to_cpu(vh->vh_pt[i].pt_nblks), pt_type, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown"); } #endif if (IS_EFS(pt_type)) { sblock = be32_to_cpu(vh->vh_pt[i].pt_firstlbn); slice = i; } } if (slice == -1) { pr_notice("partition table contained no EFS partitions\n"); #ifdef DEBUG } else { pr_info("using slice %d (type %s, offset 0x%x)\n", slice, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown", sblock); #endif } return sblock; } static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) { if (!IS_EFS_MAGIC(be32_to_cpu(super->fs_magic))) return -1; sb->fs_magic = be32_to_cpu(super->fs_magic); sb->total_blocks = be32_to_cpu(super->fs_size); sb->first_block = be32_to_cpu(super->fs_firstcg); sb->group_size = be32_to_cpu(super->fs_cgfsize); sb->data_free = be32_to_cpu(super->fs_tfree); sb->inode_free = be32_to_cpu(super->fs_tinode); sb->inode_blocks = be16_to_cpu(super->fs_cgisize); sb->total_groups = be16_to_cpu(super->fs_ncg); return 0; } static int efs_fill_super(struct super_block *s, struct fs_context *fc) { struct efs_sb_info *sb; struct buffer_head *bh; struct inode *root; sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL); if (!sb) return -ENOMEM; s->s_fs_info = sb; s->s_time_min = 0; s->s_time_max = U32_MAX; s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { pr_err("device does not support %d byte blocks\n", EFS_BLOCKSIZE); return -EINVAL; } /* read the vh (volume header) block */ bh = sb_bread(s, 0); if (!bh) { pr_err("cannot read volume header\n"); return -EIO; } /* * if this returns zero then we didn't find any partition table. * this isn't (yet) an error - just assume for the moment that * the device is valid and go on to search for a superblock. */ sb->fs_start = efs_validate_vh((struct volume_header *) bh->b_data); brelse(bh); if (sb->fs_start == -1) { return -EINVAL; } bh = sb_bread(s, sb->fs_start + EFS_SUPER); if (!bh) { pr_err("cannot read superblock\n"); return -EIO; } if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) { #ifdef DEBUG pr_warn("invalid superblock at block %u\n", sb->fs_start + EFS_SUPER); #endif brelse(bh); return -EINVAL; } brelse(bh); if (!sb_rdonly(s)) { #ifdef DEBUG pr_info("forcing read-only mode\n"); #endif s->s_flags |= SB_RDONLY; } s->s_op = &efs_superblock_operations; s->s_export_op = &efs_export_ops; root = efs_iget(s, EFS_ROOTINODE); if (IS_ERR(root)) { pr_err("get root inode failed\n"); return PTR_ERR(root); } s->s_root = d_make_root(root); if (!(s->s_root)) { pr_err("get root dentry failed\n"); return -ENOMEM; } return 0; } static void efs_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static int efs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, efs_fill_super); } static int efs_parse_param(struct fs_context *fc, struct fs_parameter *param) { int token; struct fs_parse_result result; token = fs_parse(fc, efs_param_spec, param, &result); if (token < 0) return token; return 0; } static int efs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); return 0; } struct efs_context { unsigned long s_mount_opts; }; static const struct fs_context_operations efs_context_opts = { .parse_param = efs_parse_param, .get_tree = efs_get_tree, .reconfigure = efs_reconfigure, .free = efs_free_fc, }; /* * Set up the filesystem mount context. */ static int efs_init_fs_context(struct fs_context *fc) { struct efs_context *ctx; ctx = kzalloc(sizeof(struct efs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; fc->fs_private = ctx; fc->ops = &efs_context_opts; return 0; } static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct efs_sb_info *sbi = SUPER_INFO(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = EFS_SUPER_MAGIC; /* efs magic number */ buf->f_bsize = EFS_BLOCKSIZE; /* blocksize */ buf->f_blocks = sbi->total_groups * /* total data blocks */ (sbi->group_size - sbi->inode_blocks); buf->f_bfree = sbi->data_free; /* free data blocks */ buf->f_bavail = sbi->data_free; /* free blocks for non-root */ buf->f_files = sbi->total_groups * /* total inodes */ sbi->inode_blocks * (EFS_BLOCKSIZE / sizeof(struct efs_dinode)); buf->f_ffree = sbi->inode_free; /* free inodes */ buf->f_fsid = u64_to_fsid(id); buf->f_namelen = EFS_MAXNAMELEN; /* max filename length */ return 0; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "TEE" target extension for Xtables * Copyright © Sebastian Claßen, 2007 * Jan Engelhardt, 2007-2010 * * based on ipt_ROUTE.c from Cédric de Launois * <delaunois@info.ucl.be> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/route.h> #include <linux/netfilter/x_tables.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/route.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #include <net/netfilter/ipv6/nf_dup_ipv6.h> #include <linux/netfilter/xt_TEE.h> struct xt_tee_priv { struct list_head list; struct xt_tee_tginfo *tginfo; int oif; }; static unsigned int tee_net_id __read_mostly; static const union nf_inet_addr tee_zero_address; struct tee_net { struct list_head priv_list; /* lock protects the priv_list */ struct mutex lock; }; static unsigned int tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv4(xt_net(par), skb, xt_hooknum(par), &info->gw.in, oif); return XT_CONTINUE; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv6(xt_net(par), skb, xt_hooknum(par), &info->gw.in6, oif); return XT_CONTINUE; } #endif static int tee_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct tee_net *tn = net_generic(net, tee_net_id); struct xt_tee_priv *priv; mutex_lock(&tn->lock); list_for_each_entry(priv, &tn->priv_list, list) { switch (event) { case NETDEV_REGISTER: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; break; case NETDEV_UNREGISTER: if (dev->ifindex == priv->oif) priv->oif = -1; break; case NETDEV_CHANGENAME: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; else if (dev->ifindex == priv->oif) priv->oif = -1; break; } } mutex_unlock(&tn->lock); return NOTIFY_DONE; } static int tee_tg_check(const struct xt_tgchk_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; struct xt_tee_priv *priv; /* 0.0.0.0 and :: not allowed */ if (memcmp(&info->gw, &tee_zero_address, sizeof(tee_zero_address)) == 0) return -EINVAL; if (info->oif[0]) { struct net_device *dev; if (info->oif[sizeof(info->oif)-1] != '\0') return -EINVAL; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) return -ENOMEM; priv->tginfo = info; priv->oif = -1; info->priv = priv; dev = dev_get_by_name(par->net, info->oif); if (dev) { priv->oif = dev->ifindex; dev_put(dev); } mutex_lock(&tn->lock); list_add(&priv->list, &tn->priv_list); mutex_unlock(&tn->lock); } else info->priv = NULL; static_key_slow_inc(&xt_tee_enabled); return 0; } static void tee_tg_destroy(const struct xt_tgdtor_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; if (info->priv) { mutex_lock(&tn->lock); list_del(&info->priv->list); mutex_unlock(&tn->lock); kfree(info->priv); } static_key_slow_dec(&xt_tee_enabled); } static struct xt_target tee_tg_reg[] __read_mostly = { { .name = "TEE", .revision = 1, .family = NFPROTO_IPV4, .target = tee_tg4, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "TEE", .revision = 1, .family = NFPROTO_IPV6, .target = tee_tg6, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __net_init tee_net_init(struct net *net) { struct tee_net *tn = net_generic(net, tee_net_id); INIT_LIST_HEAD(&tn->priv_list); mutex_init(&tn->lock); return 0; } static struct pernet_operations tee_net_ops = { .init = tee_net_init, .id = &tee_net_id, .size = sizeof(struct tee_net), }; static struct notifier_block tee_netdev_notifier = { .notifier_call = tee_netdev_event, }; static int __init tee_tg_init(void) { int ret; ret = register_pernet_subsys(&tee_net_ops); if (ret < 0) return ret; ret = xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); if (ret < 0) goto cleanup_subsys; ret = register_netdevice_notifier(&tee_netdev_notifier); if (ret < 0) goto unregister_targets; return 0; unregister_targets: xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); cleanup_subsys: unregister_pernet_subsys(&tee_net_ops); return ret; } static void __exit tee_tg_exit(void) { unregister_netdevice_notifier(&tee_netdev_notifier); xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); unregister_pernet_subsys(&tee_net_ops); } module_init(tee_tg_init); module_exit(tee_tg_exit); MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: Reroute packet copy"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_TEE"); MODULE_ALIAS("ip6t_TEE"); |
| 2 41 6 4946 4873 103 7 1077 2 65 18 49 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } /* * Architectures that #define INLINE_COPY_TO_USER use this function * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. * * Rust code always uses the extern definition. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (!check_copy_size(to, n, false)) return n; #ifdef INLINE_COPY_FROM_USER return _inline_copy_from_user(to, from, n); #else return _copy_from_user(to, from, n); #endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (!check_copy_size(from, n, true)) return n; #ifdef INLINE_COPY_TO_USER return _inline_copy_to_user(to, from, n); #else return _copy_to_user(to, from, n); #endif } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifndef __get_kernel_nofault #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 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 | /* ****************************************************************** * bitstream * Part of FSE library * Copyright (c) Yann Collet, Facebook, Inc. * * You can contact the author at : * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. ****************************************************************** */ #ifndef BITSTREAM_H_MODULE #define BITSTREAM_H_MODULE /* * This API consists of small unitary functions, which must be inlined for best performance. * Since link-time-optimization is not available for all compilers, * these functions are defined into a .h to be included. */ /*-**************************************** * Dependencies ******************************************/ #include "mem.h" /* unaligned access routines */ #include "compiler.h" /* UNLIKELY() */ #include "debug.h" /* assert(), DEBUGLOG(), RAWLOG() */ #include "error_private.h" /* error codes and messages */ /*========================================= * Target specific =========================================*/ #define STREAM_ACCUMULATOR_MIN_32 25 #define STREAM_ACCUMULATOR_MIN_64 57 #define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64)) /*-****************************************** * bitStream encoding API (write forward) ********************************************/ /* bitStream can mix input from multiple sources. * A critical property of these streams is that they encode and decode in **reverse** direction. * So the first bit sequence you add will be the last to be read, like a LIFO stack. */ typedef struct { size_t bitContainer; unsigned bitPos; char* startPtr; char* ptr; char* endPtr; } BIT_CStream_t; MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity); MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits); MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC); MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC); /* Start with initCStream, providing the size of buffer to write into. * bitStream will never write outside of this buffer. * `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code. * * bits are first added to a local register. * Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems. * Writing data into memory is an explicit operation, performed by the flushBits function. * Hence keep track how many bits are potentially stored into local register to avoid register overflow. * After a flushBits, a maximum of 7 bits might still be stored into local register. * * Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers. * * Last operation is to close the bitStream. * The function returns the final size of CStream in bytes. * If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable) */ /*-******************************************** * bitStream decoding API (read backward) **********************************************/ typedef struct { size_t bitContainer; unsigned bitsConsumed; const char* ptr; const char* start; const char* limitPtr; } BIT_DStream_t; typedef enum { BIT_DStream_unfinished = 0, BIT_DStream_endOfBuffer = 1, BIT_DStream_completed = 2, BIT_DStream_overflow = 3 } BIT_DStream_status; /* result of BIT_reloadDStream() */ /* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize); MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits); MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD); MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD); /* Start by invoking BIT_initDStream(). * A chunk of the bitStream is then stored into a local register. * Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t). * You can then retrieve bitFields stored into the local register, **in reverse order**. * Local register is explicitly reloaded from memory by the BIT_reloadDStream() method. * A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished. * Otherwise, it can be less than that, so proceed accordingly. * Checking if DStream has reached its end can be performed with BIT_endOfDStream(). */ /*-**************************************** * unsafe API ******************************************/ MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits); /* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */ MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC); /* unsafe version; does not check buffer overflow */ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits); /* faster, but works only if nbBits >= 1 */ /*-************************************************************** * Internal functions ****************************************************************/ MEM_STATIC unsigned BIT_highbit32 (U32 val) { assert(val != 0); { # if (__GNUC__ >= 3) /* Use GCC Intrinsic */ return __builtin_clz (val) ^ 31; # else /* Software version */ static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 }; U32 v = val; v |= v >> 1; v |= v >> 2; v |= v >> 4; v |= v >> 8; v |= v >> 16; return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27]; # endif } } /*===== Local Constants =====*/ static const unsigned BIT_mask[] = { 0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF, 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF, 0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */ #define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0])) /*-************************************************************** * bitStream encoding ****************************************************************/ /*! BIT_initCStream() : * `dstCapacity` must be > sizeof(size_t) * @return : 0 if success, * otherwise an error code (can be tested using ERR_isError()) */ MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* startPtr, size_t dstCapacity) { bitC->bitContainer = 0; bitC->bitPos = 0; bitC->startPtr = (char*)startPtr; bitC->ptr = bitC->startPtr; bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer); if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall); return 0; } /*! BIT_addBits() : * can add up to 31 bits into `bitC`. * Note : does not check for register overflow ! */ MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits) { DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32); assert(nbBits < BIT_MASK_SIZE); assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos; bitC->bitPos += nbBits; } /*! BIT_addBitsFast() : * works only if `value` is _clean_, * meaning all high bits above nbBits are 0 */ MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits) { assert((value>>nbBits) == 0); assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); bitC->bitContainer |= value << bitC->bitPos; bitC->bitPos += nbBits; } /*! BIT_flushBitsFast() : * assumption : bitContainer has not overflowed * unsafe version; does not check buffer overflow */ MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC) { size_t const nbBytes = bitC->bitPos >> 3; assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); assert(bitC->ptr <= bitC->endPtr); MEM_writeLEST(bitC->ptr, bitC->bitContainer); bitC->ptr += nbBytes; bitC->bitPos &= 7; bitC->bitContainer >>= nbBytes*8; } /*! BIT_flushBits() : * assumption : bitContainer has not overflowed * safe version; check for buffer overflow, and prevents it. * note : does not signal buffer overflow. * overflow will be revealed later on using BIT_closeCStream() */ MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC) { size_t const nbBytes = bitC->bitPos >> 3; assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); assert(bitC->ptr <= bitC->endPtr); MEM_writeLEST(bitC->ptr, bitC->bitContainer); bitC->ptr += nbBytes; if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr; bitC->bitPos &= 7; bitC->bitContainer >>= nbBytes*8; } /*! BIT_closeCStream() : * @return : size of CStream, in bytes, * or 0 if it could not fit into dstBuffer */ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC) { BIT_addBitsFast(bitC, 1, 1); /* endMark */ BIT_flushBits(bitC); if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */ return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0); } /*-******************************************************** * bitStream decoding **********************************************************/ /*! BIT_initDStream() : * Initialize a BIT_DStream_t. * `bitD` : a pointer to an already allocated BIT_DStream_t structure. * `srcSize` must be the *exact* size of the bitStream, in bytes. * @return : size of stream (== srcSize), or an errorCode if a problem is detected */ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize) { if (srcSize < 1) { ZSTD_memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); } bitD->start = (const char*)srcBuffer; bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer); if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */ bitD->ptr = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer); bitD->bitContainer = MEM_readLEST(bitD->ptr); { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; /* ensures bitsConsumed is always set */ if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ } } else { bitD->ptr = bitD->start; bitD->bitContainer = *(const BYTE*)(bitD->start); switch(srcSize) { case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16); ZSTD_FALLTHROUGH; case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24); ZSTD_FALLTHROUGH; case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32); ZSTD_FALLTHROUGH; case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; ZSTD_FALLTHROUGH; case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; ZSTD_FALLTHROUGH; case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; ZSTD_FALLTHROUGH; default: break; } { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; if (lastByte == 0) return ERROR(corruption_detected); /* endMark not present */ } bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8; } return srcSize; } MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getUpperBits(size_t bitContainer, U32 const start) { return bitContainer >> start; } MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits) { U32 const regMask = sizeof(bitContainer)*8 - 1; /* if start > regMask, bitstream is corrupted, and result is undefined */ assert(nbBits < BIT_MASK_SIZE); /* x86 transform & ((1 << nbBits) - 1) to bzhi instruction, it is better * than accessing memory. When bmi2 instruction is not present, we consider * such cpus old (pre-Haswell, 2013) and their performance is not of that * importance. */ #if defined(__x86_64__) || defined(_M_X86) return (bitContainer >> (start & regMask)) & ((((U64)1) << nbBits) - 1); #else return (bitContainer >> (start & regMask)) & BIT_mask[nbBits]; #endif } MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits) { assert(nbBits < BIT_MASK_SIZE); return bitContainer & BIT_mask[nbBits]; } /*! BIT_lookBits() : * Provides next n bits from local register. * local register is not modified. * On 32-bits, maxNbBits==24. * On 64-bits, maxNbBits==56. * @return : value extracted */ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits) { /* arbitrate between double-shift and shift+mask */ #if 1 /* if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8, * bitstream is likely corrupted, and result is undefined */ return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits); #else /* this code path is slower on my os-x laptop */ U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask); #endif } /*! BIT_lookBitsFast() : * unsafe version; only works if nbBits >= 1 */ MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits) { U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; assert(nbBits >= 1); return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask); } MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits) { bitD->bitsConsumed += nbBits; } /*! BIT_readBits() : * Read (consume) next n bits from local register and update. * Pay attention to not read more than nbBits contained into local register. * @return : extracted value. */ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits) { size_t const value = BIT_lookBits(bitD, nbBits); BIT_skipBits(bitD, nbBits); return value; } /*! BIT_readBitsFast() : * unsafe version; only works only if nbBits >= 1 */ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits) { size_t const value = BIT_lookBitsFast(bitD, nbBits); assert(nbBits >= 1); BIT_skipBits(bitD, nbBits); return value; } /*! BIT_reloadDStreamFast() : * Similar to BIT_reloadDStream(), but with two differences: * 1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold! * 2. Returns BIT_DStream_overflow when bitD->ptr < bitD->limitPtr, at this * point you must use BIT_reloadDStream() to reload. */ MEM_STATIC BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD) { if (UNLIKELY(bitD->ptr < bitD->limitPtr)) return BIT_DStream_overflow; assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8); bitD->ptr -= bitD->bitsConsumed >> 3; bitD->bitsConsumed &= 7; bitD->bitContainer = MEM_readLEST(bitD->ptr); return BIT_DStream_unfinished; } /*! BIT_reloadDStream() : * Refill `bitD` from buffer previously set in BIT_initDStream() . * This function is safe, it guarantees it will not read beyond src buffer. * @return : status of `BIT_DStream_t` internal register. * when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */ MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) { if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* overflow detected, like end of stream */ return BIT_DStream_overflow; if (bitD->ptr >= bitD->limitPtr) { return BIT_reloadDStreamFast(bitD); } if (bitD->ptr == bitD->start) { if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer; return BIT_DStream_completed; } /* start < ptr < limitPtr */ { U32 nbBytes = bitD->bitsConsumed >> 3; BIT_DStream_status result = BIT_DStream_unfinished; if (bitD->ptr - nbBytes < bitD->start) { nbBytes = (U32)(bitD->ptr - bitD->start); /* ptr > start */ result = BIT_DStream_endOfBuffer; } bitD->ptr -= nbBytes; bitD->bitsConsumed -= nbBytes*8; bitD->bitContainer = MEM_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */ return result; } } /*! BIT_endOfDStream() : * @return : 1 if DStream has _exactly_ reached its end (all bits consumed). */ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream) { return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8)); } #endif /* BITSTREAM_H_MODULE */ |
| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 | // SPDX-License-Identifier: GPL-2.0-or-later /* * vrf.c: device driver to encapsulate a VRF space * * Copyright (c) 2015 Cumulus Networks. All rights reserved. * Copyright (c) 2015 Shrijeet Mukherjee <shm@cumulusnetworks.com> * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> * * Based on dummy, team and ipvlan drivers */ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ip.h> #include <linux/init.h> #include <linux/moduleparam.h> #include <linux/netfilter.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <linux/u64_stats_sync.h> #include <linux/hashtable.h> #include <linux/spinlock_types.h> #include <linux/inetdevice.h> #include <net/arp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #include <net/fib_rules.h> #include <net/sch_generic.h> #include <net/netns/generic.h> #include <net/netfilter/nf_conntrack.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.1" #define FIB_RULE_PREF 1000 /* default preference for FIB rules */ #define HT_MAP_BITS 4 #define HASH_INITVAL ((u32)0xcafef00d) struct vrf_map { DECLARE_HASHTABLE(ht, HT_MAP_BITS); spinlock_t vmap_lock; /* shared_tables: * count how many distinct tables do not comply with the strict mode * requirement. * shared_tables value must be 0 in order to enable the strict mode. * * example of the evolution of shared_tables: * | time * add vrf0 --> table 100 shared_tables = 0 | t0 * add vrf1 --> table 101 shared_tables = 0 | t1 * add vrf2 --> table 100 shared_tables = 1 | t2 * add vrf3 --> table 100 shared_tables = 1 | t3 * add vrf4 --> table 101 shared_tables = 2 v t4 * * shared_tables is a "step function" (or "staircase function") * and it is increased by one when the second vrf is associated to a * table. * * at t2, vrf0 and vrf2 are bound to table 100: shared_tables = 1. * * at t3, another dev (vrf3) is bound to the same table 100 but the * value of shared_tables is still 1. * This means that no matter how many new vrfs will register on the * table 100, the shared_tables will not increase (considering only * table 100). * * at t4, vrf4 is bound to table 101, and shared_tables = 2. * * Looking at the value of shared_tables we can immediately know if * the strict_mode can or cannot be enforced. Indeed, strict_mode * can be enforced iff shared_tables = 0. * * Conversely, shared_tables is decreased when a vrf is de-associated * from a table with exactly two associated vrfs. */ u32 shared_tables; bool strict_mode; }; struct vrf_map_elem { struct hlist_node hnode; struct list_head vrf_list; /* VRFs registered to this table */ u32 table_id; int users; int ifindex; }; static unsigned int vrf_net_id; /* per netns vrf data */ struct netns_vrf { /* protected by rtnl lock */ bool add_fib_rules; struct vrf_map vmap; struct ctl_table_header *ctl_hdr; }; struct net_vrf { struct rtable __rcu *rth; struct rt6_info __rcu *rt6; #if IS_ENABLED(CONFIG_IPV6) struct fib6_table *fib6_table; #endif u32 tb_id; struct list_head me_list; /* entry in vrf_map_elem */ int ifindex; }; static void vrf_rx_stats(struct net_device *dev, int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_packets); u64_stats_add(&dstats->rx_bytes, len); u64_stats_update_end(&dstats->syncp); } static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) { vrf_dev->stats.tx_errors++; kfree_skb(skb); } static struct vrf_map *netns_vrf_map(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); return &nn_vrf->vmap; } static struct vrf_map *netns_vrf_map_by_dev(struct net_device *dev) { return netns_vrf_map(dev_net(dev)); } static int vrf_map_elem_get_vrf_ifindex(struct vrf_map_elem *me) { struct list_head *me_head = &me->vrf_list; struct net_vrf *vrf; if (list_empty(me_head)) return -ENODEV; vrf = list_first_entry(me_head, struct net_vrf, me_list); return vrf->ifindex; } static struct vrf_map_elem *vrf_map_elem_alloc(gfp_t flags) { struct vrf_map_elem *me; me = kmalloc(sizeof(*me), flags); if (!me) return NULL; return me; } static void vrf_map_elem_free(struct vrf_map_elem *me) { kfree(me); } static void vrf_map_elem_init(struct vrf_map_elem *me, int table_id, int ifindex, int users) { me->table_id = table_id; me->ifindex = ifindex; me->users = users; INIT_LIST_HEAD(&me->vrf_list); } static struct vrf_map_elem *vrf_map_lookup_elem(struct vrf_map *vmap, u32 table_id) { struct vrf_map_elem *me; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_for_each_possible(vmap->ht, me, hnode, key) { if (me->table_id == table_id) return me; } return NULL; } static void vrf_map_add_elem(struct vrf_map *vmap, struct vrf_map_elem *me) { u32 table_id = me->table_id; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_add(vmap->ht, &me->hnode, key); } static void vrf_map_del_elem(struct vrf_map_elem *me) { hash_del(&me->hnode); } static void vrf_map_lock(struct vrf_map *vmap) __acquires(&vmap->vmap_lock) { spin_lock(&vmap->vmap_lock); } static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock) { spin_unlock(&vmap->vmap_lock); } /* called with rtnl lock held */ static int vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); struct vrf_map_elem *new_me, *me; u32 table_id = vrf->tb_id; bool free_new_me = false; int users; int res; /* we pre-allocate elements used in the spin-locked section (so that we * keep the spinlock as short as possible). */ new_me = vrf_map_elem_alloc(GFP_KERNEL); if (!new_me) return -ENOMEM; vrf_map_elem_init(new_me, table_id, dev->ifindex, 0); vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) { me = new_me; vrf_map_add_elem(vmap, me); goto link_vrf; } /* we already have an entry in the vrf_map, so it means there is (at * least) a vrf registered on the specific table. */ free_new_me = true; if (vmap->strict_mode) { /* vrfs cannot share the same table */ NL_SET_ERR_MSG(extack, "Table is used by another VRF"); res = -EBUSY; goto unlock; } link_vrf: users = ++me->users; if (users == 2) ++vmap->shared_tables; list_add(&vrf->me_list, &me->vrf_list); res = 0; unlock: vrf_map_unlock(vmap); /* clean-up, if needed */ if (free_new_me) vrf_map_elem_free(new_me); return res; } /* called with rtnl lock held */ static void vrf_map_unregister_dev(struct net_device *dev) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); u32 table_id = vrf->tb_id; struct vrf_map_elem *me; int users; vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) goto unlock; list_del(&vrf->me_list); users = --me->users; if (users == 1) { --vmap->shared_tables; } else if (users == 0) { vrf_map_del_elem(me); /* no one will refer to this element anymore */ vrf_map_elem_free(me); } unlock: vrf_map_unlock(vmap); } /* return the vrf device index associated with the table_id */ static int vrf_ifindex_lookup_by_table_id(struct net *net, u32 table_id) { struct vrf_map *vmap = netns_vrf_map(net); struct vrf_map_elem *me; int ifindex; vrf_map_lock(vmap); if (!vmap->strict_mode) { ifindex = -EPERM; goto unlock; } me = vrf_map_lookup_elem(vmap, table_id); if (!me) { ifindex = -ENODEV; goto unlock; } ifindex = vrf_map_elem_get_vrf_ifindex(me); unlock: vrf_map_unlock(vmap); return ifindex; } /* by default VRF devices do not have a qdisc and are expected * to be created with only a single queue. */ static bool qdisc_tx_is_default(const struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; if (dev->num_tx_queues > 1) return false; txq = netdev_get_tx_queue(dev, 0); qdisc = rcu_access_pointer(txq->qdisc); return !qdisc->enqueue; } /* Local traffic destined to local address. Reinsert the packet to rx * path, similar to loopback handling. */ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { int len = skb->len; skb_orphan(skb); skb_dst_set(skb, dst); /* set pkt_type to avoid skb hitting packet taps twice - * once on Tx and again in Rx processing */ skb->pkt_type = PACKET_LOOPBACK; skb->protocol = eth_type_trans(skb, dev); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { vrf_rx_stats(dev, len); } else { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_drops); u64_stats_update_end(&dstats->syncp); } return NETDEV_TX_OK; } static void vrf_nf_set_untracked(struct sk_buff *skb) { if (skb_get_nfct(skb) == 0) nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } static void vrf_nf_reset_ct(struct sk_buff *skb) { if (skb_get_nfct(skb) == IP_CT_UNTRACKED) nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) static int vrf_ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) goto err; iph = ipv6_hdr(skb); memset(&fl6, 0, sizeof(fl6)); /* needed to match OIF rule */ fl6.flowi6_l3mdev = dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = iph->nexthdr; dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst) || dst == dst_null) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (dst->dev == dev) return vrf_local_xmit(skb, dev, dst); skb_dst_set(skb, dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); ret = vrf_ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(ret))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; return ret; err: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #else static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #endif /* based on ip_local_out; can't use it b/c the dst is switched pointing to us */ static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { struct iphdr *ip4h; int ret = NET_XMIT_DROP; struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) goto err; ip4h = ip_hdr(skb); memset(&fl4, 0, sizeof(fl4)); /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.flowi4_tos = RT_TOS(ip4h->tos); fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; fl4.saddr = ip4h->saddr; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (rt->dst.dev == vrf_dev) return vrf_local_xmit(skb, vrf_dev, &rt->dst); skb_dst_set(skb, &rt->dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); if (!ip4h->saddr) { ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0, RT_SCOPE_LINK); } memset(IPCB(skb), 0, sizeof(*IPCB(skb))); ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; out: return ret; err: vrf_tx_error(vrf_dev, skb); goto out; } static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) { switch (skb->protocol) { case htons(ETH_P_IP): return vrf_process_v4_outbound(skb, dev); case htons(ETH_P_IPV6): return vrf_process_v6_outbound(skb, dev); default: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } } static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); u64_stats_update_begin(&dstats->syncp); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { u64_stats_inc(&dstats->tx_packets); u64_stats_add(&dstats->tx_bytes, len); } else { u64_stats_inc(&dstats->tx_drops); } u64_stats_update_end(&dstats->syncp); return ret; } static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; if (!list_empty(&vrf_dev->ptype_all) && likely(skb_headroom(skb) >= ETH_HLEN)) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth_zero_addr(eth->h_dest); eth->h_proto = skb->protocol; dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, ETH_HLEN); } vrf_nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) /* modelled after ip6_finish_output2 */ static int vrf_finish_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; const struct in6_addr *nexthop; struct neighbour *neigh; int ret; vrf_nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } /* modelled after ip6_output */ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, vrf_finish_output6, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rt6_info *rt6; rcu_read_lock(); rt6 = rcu_dereference(vrf->rt6); if (likely(rt6)) { dst = &rt6->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output6_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip6_local_out(net, sk, skb); } static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IPV6); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output6_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip6_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert link scope packets */ if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); return vrf_ip6_out_redirect(vrf_dev, skb); } /* holding rtnl */ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { struct rt6_info *rt6 = rtnl_dereference(vrf->rt6); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rt6, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rt6) { dst = &rt6->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rt6_create(struct net_device *dev) { int flags = DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); struct rt6_info *rt6; int rc = -ENOMEM; /* IPv6 can be CONFIG enabled and then disabled runtime */ if (!ipv6_mod_enabled()) return 0; vrf->fib6_table = fib6_new_table(net, vrf->tb_id); if (!vrf->fib6_table) goto out; /* create a dst for routing packets out a VRF device */ rt6 = ip6_dst_alloc(net, dev, flags); if (!rt6) goto out; rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); rc = 0; out: return rc; } #else static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { return skb; } static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { } static int vrf_rt6_create(struct net_device *dev) { return 0; } #endif /* modelled after ip_finish_output2 */ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; vrf_nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) { dev->stats.tx_errors++; return -ENOMEM; } } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int ret; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return ret; } rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, vrf_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rtable *rth; rcu_read_lock(); rth = rcu_dereference(vrf->rth); if (likely(rth)) { dst = &rth->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip_local_out(net, sk, skb); } static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IP); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert multicast or local broadcast */ if (ipv4_is_multicast(ip_hdr(skb)->daddr) || ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); return vrf_ip_out_redirect(vrf_dev, skb); } /* called with rcu lock held */ static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_out(vrf_dev, sk, skb); case AF_INET6: return vrf_ip6_out(vrf_dev, sk, skb); } return skb; } /* holding rtnl */ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf) { struct rtable *rth = rtnl_dereference(vrf->rth); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rth, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rth) { dst = &rth->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rtable_create(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); struct rtable *rth; if (!fib_new_table(dev_net(dev), vrf->tb_id)) return -ENOMEM; /* create a dst for routing packets out through a VRF device */ rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1); if (!rth) return -ENOMEM; rth->dst.output = vrf_output; rcu_assign_pointer(vrf->rth, rth); return 0; } /**************************** device handling ********************/ /* cycle interface to flush neighbor cache and move routes across tables */ static void cycle_netdev(struct net_device *dev, struct netlink_ext_ack *extack) { unsigned int flags = dev->flags; int ret; if (!netif_running(dev)) return; ret = dev_change_flags(dev, flags & ~IFF_UP, extack); if (ret >= 0) ret = dev_change_flags(dev, flags, extack); if (ret < 0) { netdev_err(dev, "Failed to cycle device %s; route tables might be wrong!\n", dev->name); } } static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { int ret; /* do not allow loopback device to be enslaved to a VRF. * The vrf device acts as the loopback for the vrf. */ if (port_dev == dev_net(dev)->loopback_dev) { NL_SET_ERR_MSG(extack, "Can not enslave loopback device to a VRF"); return -EOPNOTSUPP; } port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; cycle_netdev(port_dev, extack); return 0; err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { if (netif_is_l3_master(port_dev)) { NL_SET_ERR_MSG(extack, "Can not enslave an L3 master device to a VRF"); return -EINVAL; } if (netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; cycle_netdev(port_dev, NULL); return 0; } static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { return do_vrf_del_slave(dev, port_dev); } static void vrf_dev_uninit(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; dev->flags = IFF_MASTER | IFF_NOARP; /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); return 0; out_rth: vrf_rtable_release(dev, vrf); out_nomem: return -ENOMEM; } static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, }; static u32 vrf_fib_table(const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return vrf->tb_id; } static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; } static int vrf_prepare_mac_header(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto) { struct ethhdr *eth; int err; /* in general, we do not know if there is enough space in the head of * the packet for hosting the mac header. */ err = skb_cow_head(skb, LL_RESERVED_SPACE(vrf_dev)); if (unlikely(err)) /* no space in the skb head */ return -ENOBUFS; __skb_push(skb, ETH_HLEN); eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. */ ether_addr_copy(eth->h_dest, vrf_dev->dev_addr); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth->h_proto = htons(proto); /* the destination address of the Ethernet frame corresponds to the * address set on the VRF interface; therefore, the packet is intended * to be processed locally. */ skb->protocol = eth->h_proto; skb->pkt_type = PACKET_HOST; skb_postpush_rcsum(skb, skb->data, ETH_HLEN); skb_pull_inline(skb, ETH_HLEN); return 0; } /* prepare and add the mac header to the packet if it was not set previously. * In this way, packet sniffers such as tcpdump can parse the packet correctly. * If the mac header was already set, the original mac header is left * untouched and the function returns immediately. */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto, struct net_device *orig_dev) { if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); } #if IS_ENABLED(CONFIG_IPV6) /* neighbor handling is done with actual device; do not want * to flip skb->dev for those ndisc packets. This really fails * for multiple next protocols (e.g., NEXTHDR_HOP). But it is * a start. */ static bool ipv6_ndisc_frame(const struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); bool rc = false; if (iph->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; struct icmp6hdr _icmph; icmph = skb_header_pointer(skb, sizeof(*iph), sizeof(_icmph), &_icmph); if (!icmph) goto out; switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: rc = true; break; } } out: return rc; } static struct rt6_info *vrf_ip6_route_lookup(struct net *net, const struct net_device *dev, struct flowi6 *fl6, int ifindex, const struct sk_buff *skb, int flags) { struct net_vrf *vrf = netdev_priv(dev); return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, int ifindex) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct flowi6 fl6 = { .flowi6_iif = ifindex, .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), }; struct net *net = dev_net(vrf_dev); struct rt6_info *rt6; rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb, RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE); if (unlikely(!rt6)) return; if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst)) return; skb_dst_set(skb, &rt6->dst); } static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. * For non-loopback strict packets, determine the dst using the original * ifindex. */ if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; if (skb->pkt_type == PACKET_LOOPBACK) skb->pkt_type = PACKET_HOST; else vrf_ip6_input_dst(skb, vrf_dev, orig_iif); goto out; } /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { struct net_device *orig_dev = skb->dev; vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IPV6, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } IP6CB(skb)->flags |= IP6SKB_L3SLAVE; } if (need_strict) vrf_ip6_input_dst(skb, vrf_dev, orig_iif); skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } #else static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { return skb; } #endif static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_device *orig_dev = skb->dev; skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; if (ipv4_is_multicast(ip_hdr(skb)->daddr)) goto out; /* loopback traffic; do not push through packet taps again. * Reset pkt_type for upper layers to process skb */ if (skb->pkt_type == PACKET_LOOPBACK) { skb->pkt_type = PACKET_HOST; goto out; } vrf_rx_stats(vrf_dev, skb->len); if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } /* called with rcu lock held */ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_rcv(vrf_dev, skb); case AF_INET6: return vrf_ip6_rcv(vrf_dev, skb); } return skb; } #if IS_ENABLED(CONFIG_IPV6) /* send to link-local or multicast address via interface enslaved to * VRF device. Force lookup to VRF table without changing flow struct * Note: Caller to this function must hold rcu_read_lock() and no refcnt * is taken on the dst by this function. */ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev, struct flowi6 *fl6) { struct net *net = dev_net(dev); int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_DST_NOREF; struct dst_entry *dst = NULL; struct rt6_info *rt; /* VRF device does not have a link-local address and * sending packets to link-local or mcast addresses over * a VRF device does not make sense */ if (fl6->flowi6_oif == dev->ifindex) { dst = &net->ipv6.ip6_null_entry->dst; return dst; } if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags); if (rt) dst = &rt->dst; return dst; } #endif static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_l3_rcv = vrf_l3_rcv, .l3mdev_l3_out = vrf_l3_out, #if IS_ENABLED(CONFIG_IPV6) .l3mdev_link_scope_lookup = vrf_link_scope_lookup, #endif }; static void vrf_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops vrf_ethtool_ops = { .get_drvinfo = vrf_get_drvinfo, }; static inline size_t vrf_fib_rule_nl_size(void) { size_t sz; sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) { struct fib_rule_hdr *frh; struct nlmsghdr *nlh; struct sk_buff *skb; int err; if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) && !ipv6_mod_enabled()) return 0; skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0); if (!nlh) goto nla_put_failure; /* rule only needs to appear once */ nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); frh->family = family; frh->action = FR_ACT_TO_TBL; if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) goto nla_put_failure; if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) goto nla_put_failure; nlmsg_end(skb, nlh); /* fib_nl_{new,del}rule handling looks for net from skb->sk */ skb->sk = dev_net(dev)->rtnl; if (add_it) { err = fib_nl_newrule(skb, nlh, NULL); if (err == -EEXIST) err = 0; } else { err = fib_nl_delrule(skb, nlh, NULL); if (err == -ENOENT) err = 0; } nlmsg_free(skb); return err; nla_put_failure: nlmsg_free(skb); return -EMSGSIZE; } static int vrf_add_fib_rules(const struct net_device *dev) { int err; err = vrf_fib_rule(dev, AF_INET, true); if (err < 0) goto out_err; err = vrf_fib_rule(dev, AF_INET6, true); if (err < 0) goto ipv6_err; #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true); if (err < 0) goto ipmr_err; #endif #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true); if (err < 0) goto ip6mr_err; #endif return 0; #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) ip6mr_err: vrf_fib_rule(dev, RTNL_FAMILY_IPMR, false); #endif #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) ipmr_err: vrf_fib_rule(dev, AF_INET6, false); #endif ipv6_err: vrf_fib_rule(dev, AF_INET, false); out_err: netdev_err(dev, "Failed to add FIB rules.\n"); return err; } static void vrf_setup(struct net_device *dev) { ether_setup(dev); /* Initialize the device structure. */ dev->netdev_ops = &vrf_netdev_ops; dev->l3mdev_ops = &vrf_l3mdev_ops; dev->ethtool_ops = &vrf_ethtool_ops; dev->needs_free_netdev = true; /* Fill in device structure with ethernet-generic values. */ eth_hw_addr_random(dev); /* don't acquire vrf device's netif_tx_lock when transmitting */ dev->features |= NETIF_F_LLTX; /* don't allow vrf devices to change network namespaces. */ dev->features |= NETIF_F_NETNS_LOCAL; /* does not make sense for a VLAN to be added to a vrf device */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* enable offload features */ dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->hw_features = dev->features; dev->hw_enc_features = dev->features; /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EADDRNOTAVAIL; } } return 0; } static void vrf_dellink(struct net_device *dev, struct list_head *head) { struct net_device *port_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) vrf_del_slave(dev, port_dev); vrf_map_unregister_dev(dev); unregister_netdevice_queue(dev, head); } static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); struct netns_vrf *nn_vrf; bool *add_fib_rules; struct net *net; int err; if (!data || !data[IFLA_VRF_TABLE]) { NL_SET_ERR_MSG(extack, "VRF table id is missing"); return -EINVAL; } vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); if (vrf->tb_id == RT_TABLE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE], "Invalid VRF table id"); return -EINVAL; } dev->priv_flags |= IFF_L3MDEV_MASTER; err = register_netdevice(dev); if (err) goto out; /* mapping between table_id and vrf; * note: such binding could not be done in the dev init function * because dev->ifindex id is not available yet. */ vrf->ifindex = dev->ifindex; err = vrf_map_register_dev(dev, extack); if (err) { unregister_netdevice(dev); goto out; } net = dev_net(dev); nn_vrf = net_generic(net, vrf_net_id); add_fib_rules = &nn_vrf->add_fib_rules; if (*add_fib_rules) { err = vrf_add_fib_rules(dev); if (err) { vrf_map_unregister_dev(dev); unregister_netdevice(dev); goto out; } *add_fib_rules = false; } out: return err; } static size_t vrf_nl_getsize(const struct net_device *dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_TABLE */ } static int vrf_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id); } static size_t vrf_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_PORT_TABLE */ } static int vrf_fill_slave_info(struct sk_buff *skb, const struct net_device *vrf_dev, const struct net_device *slave_dev) { struct net_vrf *vrf = netdev_priv(vrf_dev); if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id)) return -EMSGSIZE; return 0; } static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = { [IFLA_VRF_TABLE] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vrf_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct net_vrf), .get_size = vrf_nl_getsize, .policy = vrf_nl_policy, .validate = vrf_validate, .fill_info = vrf_fillinfo, .get_slave_size = vrf_get_slave_size, .fill_slave_info = vrf_fill_slave_info, .newlink = vrf_newlink, .dellink = vrf_dellink, .setup = vrf_setup, .maxtype = IFLA_VRF_MAX, }; static int vrf_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { struct net_device *vrf_dev; if (!netif_is_l3_slave(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); vrf_del_slave(vrf_dev, dev); } out: return NOTIFY_DONE; } static struct notifier_block vrf_notifier_block __read_mostly = { .notifier_call = vrf_device_event, }; static int vrf_map_init(struct vrf_map *vmap) { spin_lock_init(&vmap->vmap_lock); hash_init(vmap->ht); vmap->strict_mode = false; return 0; } #ifdef CONFIG_SYSCTL static bool vrf_strict_mode(struct vrf_map *vmap) { bool strict_mode; vrf_map_lock(vmap); strict_mode = vmap->strict_mode; vrf_map_unlock(vmap); return strict_mode; } static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) { bool *cur_mode; int res = 0; vrf_map_lock(vmap); cur_mode = &vmap->strict_mode; if (*cur_mode == new_mode) goto unlock; if (*cur_mode) { /* disable strict mode */ *cur_mode = false; } else { if (vmap->shared_tables) { /* we cannot allow strict_mode because there are some * vrfs that share one or more tables. */ res = -EBUSY; goto unlock; } /* no tables are shared among vrfs, so we can go back * to 1:1 association between a vrf with its table. */ *cur_mode = true; } unlock: vrf_map_unlock(vmap); return res; } static int vrf_shared_table_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->extra1; struct vrf_map *vmap = netns_vrf_map(net); int proc_strict_mode = 0; struct ctl_table tmp = { .procname = table->procname, .data = &proc_strict_mode, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; int ret; if (!write) proc_strict_mode = vrf_strict_mode(vmap); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = vrf_strict_mode_change(vmap, (bool)proc_strict_mode); return ret; } static const struct ctl_table vrf_table[] = { { .procname = "strict_mode", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = vrf_shared_table_handler, /* set by the vrf_netns_init */ .extra1 = NULL, }, }; static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { struct ctl_table *table; table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL); if (!table) return -ENOMEM; /* init the extra1 parameter with the reference to current netns */ table[0].extra1 = net; nn_vrf->ctl_hdr = register_net_sysctl_sz(net, "net/vrf", table, ARRAY_SIZE(vrf_table)); if (!nn_vrf->ctl_hdr) { kfree(table); return -ENOMEM; } return 0; } static void vrf_netns_exit_sysctl(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); const struct ctl_table *table; table = nn_vrf->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(nn_vrf->ctl_hdr); kfree(table); } #else static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { return 0; } static void vrf_netns_exit_sysctl(struct net *net) { } #endif /* Initialize per network namespace state */ static int __net_init vrf_netns_init(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); nn_vrf->add_fib_rules = true; vrf_map_init(&nn_vrf->vmap); return vrf_netns_init_sysctl(net, nn_vrf); } static void __net_exit vrf_netns_exit(struct net *net) { vrf_netns_exit_sysctl(net); } static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .exit = vrf_netns_exit, .id = &vrf_net_id, .size = sizeof(struct netns_vrf), }; static int __init vrf_init_module(void) { int rc; register_netdevice_notifier(&vrf_notifier_block); rc = register_pernet_subsys(&vrf_net_ops); if (rc < 0) goto error; rc = l3mdev_table_lookup_register(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); if (rc < 0) goto unreg_pernet; rc = rtnl_link_register(&vrf_link_ops); if (rc < 0) goto table_lookup_unreg; return 0; table_lookup_unreg: l3mdev_table_lookup_unregister(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); unreg_pernet: unregister_pernet_subsys(&vrf_net_ops); error: unregister_netdevice_notifier(&vrf_notifier_block); return rc; } module_init(vrf_init_module); MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern"); MODULE_DESCRIPTION("Device driver to instantiate VRF domains"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); MODULE_VERSION(DRV_VERSION); |
| 34 56 56 47 30 47 44 12 56 151 46 23 54 22 156 128 59 59 56 46 59 78 24 78 78 250 250 7 232 164 55 23 50 164 8 1 3 237 238 12 231 256 207 163 57 57 584 256 441 439 257 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fat/cache.c * * Written 1992,1993 by Werner Almesberger * * Mar 1999. AV. Changed cache, so that it uses the starting cluster instead * of inode number. * May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers. */ #include <linux/slab.h> #include "fat.h" /* this must be > 0. */ #define FAT_MAX_CACHE 8 struct fat_cache { struct list_head cache_list; int nr_contig; /* number of contiguous clusters */ int fcluster; /* cluster number in the file. */ int dcluster; /* cluster number on disk. */ }; struct fat_cache_id { unsigned int id; int nr_contig; int fcluster; int dcluster; }; static inline int fat_max_cache(struct inode *inode) { return FAT_MAX_CACHE; } static struct kmem_cache *fat_cache_cachep; static void init_once(void *foo) { struct fat_cache *cache = (struct fat_cache *)foo; INIT_LIST_HEAD(&cache->cache_list); } int __init fat_cache_init(void) { fat_cache_cachep = kmem_cache_create("fat_cache", sizeof(struct fat_cache), 0, SLAB_RECLAIM_ACCOUNT, init_once); if (fat_cache_cachep == NULL) return -ENOMEM; return 0; } void fat_cache_destroy(void) { kmem_cache_destroy(fat_cache_cachep); } static inline struct fat_cache *fat_cache_alloc(struct inode *inode) { return kmem_cache_alloc(fat_cache_cachep, GFP_NOFS); } static inline void fat_cache_free(struct fat_cache *cache) { BUG_ON(!list_empty(&cache->cache_list)); kmem_cache_free(fat_cache_cachep, cache); } static inline void fat_cache_update_lru(struct inode *inode, struct fat_cache *cache) { if (MSDOS_I(inode)->cache_lru.next != &cache->cache_list) list_move(&cache->cache_list, &MSDOS_I(inode)->cache_lru); } static int fat_cache_lookup(struct inode *inode, int fclus, struct fat_cache_id *cid, int *cached_fclus, int *cached_dclus) { static struct fat_cache nohit = { .fcluster = 0, }; struct fat_cache *hit = &nohit, *p; int offset = -1; spin_lock(&MSDOS_I(inode)->cache_lru_lock); list_for_each_entry(p, &MSDOS_I(inode)->cache_lru, cache_list) { /* Find the cache of "fclus" or nearest cache. */ if (p->fcluster <= fclus && hit->fcluster < p->fcluster) { hit = p; if ((hit->fcluster + hit->nr_contig) < fclus) { offset = hit->nr_contig; } else { offset = fclus - hit->fcluster; break; } } } if (hit != &nohit) { fat_cache_update_lru(inode, hit); cid->id = MSDOS_I(inode)->cache_valid_id; cid->nr_contig = hit->nr_contig; cid->fcluster = hit->fcluster; cid->dcluster = hit->dcluster; *cached_fclus = cid->fcluster + offset; *cached_dclus = cid->dcluster + offset; } spin_unlock(&MSDOS_I(inode)->cache_lru_lock); return offset; } static struct fat_cache *fat_cache_merge(struct inode *inode, struct fat_cache_id *new) { struct fat_cache *p; list_for_each_entry(p, &MSDOS_I(inode)->cache_lru, cache_list) { /* Find the same part as "new" in cluster-chain. */ if (p->fcluster == new->fcluster) { BUG_ON(p->dcluster != new->dcluster); if (new->nr_contig > p->nr_contig) p->nr_contig = new->nr_contig; return p; } } return NULL; } static void fat_cache_add(struct inode *inode, struct fat_cache_id *new) { struct fat_cache *cache, *tmp; if (new->fcluster == -1) /* dummy cache */ return; spin_lock(&MSDOS_I(inode)->cache_lru_lock); if (new->id != FAT_CACHE_VALID && new->id != MSDOS_I(inode)->cache_valid_id) goto out; /* this cache was invalidated */ cache = fat_cache_merge(inode, new); if (cache == NULL) { if (MSDOS_I(inode)->nr_caches < fat_max_cache(inode)) { MSDOS_I(inode)->nr_caches++; spin_unlock(&MSDOS_I(inode)->cache_lru_lock); tmp = fat_cache_alloc(inode); if (!tmp) { spin_lock(&MSDOS_I(inode)->cache_lru_lock); MSDOS_I(inode)->nr_caches--; spin_unlock(&MSDOS_I(inode)->cache_lru_lock); return; } spin_lock(&MSDOS_I(inode)->cache_lru_lock); cache = fat_cache_merge(inode, new); if (cache != NULL) { MSDOS_I(inode)->nr_caches--; fat_cache_free(tmp); goto out_update_lru; } cache = tmp; } else { struct list_head *p = MSDOS_I(inode)->cache_lru.prev; cache = list_entry(p, struct fat_cache, cache_list); } cache->fcluster = new->fcluster; cache->dcluster = new->dcluster; cache->nr_contig = new->nr_contig; } out_update_lru: fat_cache_update_lru(inode, cache); out: spin_unlock(&MSDOS_I(inode)->cache_lru_lock); } /* * Cache invalidation occurs rarely, thus the LRU chain is not updated. It * fixes itself after a while. */ static void __fat_cache_inval_inode(struct inode *inode) { struct msdos_inode_info *i = MSDOS_I(inode); struct fat_cache *cache; while (!list_empty(&i->cache_lru)) { cache = list_entry(i->cache_lru.next, struct fat_cache, cache_list); list_del_init(&cache->cache_list); i->nr_caches--; fat_cache_free(cache); } /* Update. The copy of caches before this id is discarded. */ i->cache_valid_id++; if (i->cache_valid_id == FAT_CACHE_VALID) i->cache_valid_id++; } void fat_cache_inval_inode(struct inode *inode) { spin_lock(&MSDOS_I(inode)->cache_lru_lock); __fat_cache_inval_inode(inode); spin_unlock(&MSDOS_I(inode)->cache_lru_lock); } static inline int cache_contiguous(struct fat_cache_id *cid, int dclus) { cid->nr_contig++; return ((cid->dcluster + cid->nr_contig) == dclus); } static inline void cache_init(struct fat_cache_id *cid, int fclus, int dclus) { cid->id = FAT_CACHE_VALID; cid->fcluster = fclus; cid->dcluster = dclus; cid->nr_contig = 0; } int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); const int limit = sb->s_maxbytes >> sbi->cluster_bits; struct fat_entry fatent; struct fat_cache_id cid; int nr; BUG_ON(MSDOS_I(inode)->i_start == 0); *fclus = 0; *dclus = MSDOS_I(inode)->i_start; if (!fat_valid_entry(sbi, *dclus)) { fat_fs_error_ratelimit(sb, "%s: invalid start cluster (i_pos %lld, start %08x)", __func__, MSDOS_I(inode)->i_pos, *dclus); return -EIO; } if (cluster == 0) return 0; if (fat_cache_lookup(inode, cluster, &cid, fclus, dclus) < 0) { /* * dummy, always not contiguous * This is reinitialized by cache_init(), later. */ cache_init(&cid, -1, -1); } fatent_init(&fatent); while (*fclus < cluster) { /* prevent the infinite loop of cluster chain */ if (*fclus > limit) { fat_fs_error_ratelimit(sb, "%s: detected the cluster chain loop (i_pos %lld)", __func__, MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } nr = fat_ent_read(inode, &fatent, *dclus); if (nr < 0) goto out; else if (nr == FAT_ENT_FREE) { fat_fs_error_ratelimit(sb, "%s: invalid cluster chain (i_pos %lld)", __func__, MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } else if (nr == FAT_ENT_EOF) { fat_cache_add(inode, &cid); goto out; } (*fclus)++; *dclus = nr; if (!cache_contiguous(&cid, *dclus)) cache_init(&cid, *fclus, *dclus); } nr = 0; fat_cache_add(inode, &cid); out: fatent_brelse(&fatent); return nr; } static int fat_bmap_cluster(struct inode *inode, int cluster) { struct super_block *sb = inode->i_sb; int ret, fclus, dclus; if (MSDOS_I(inode)->i_start == 0) return 0; ret = fat_get_cluster(inode, cluster, &fclus, &dclus); if (ret < 0) return ret; else if (ret == FAT_ENT_EOF) { fat_fs_error(sb, "%s: request beyond EOF (i_pos %lld)", __func__, MSDOS_I(inode)->i_pos); return -EIO; } return dclus; } int fat_get_mapped_cluster(struct inode *inode, sector_t sector, sector_t last_block, unsigned long *mapped_blocks, sector_t *bmap) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); int cluster, offset; cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits); offset = sector & (sbi->sec_per_clus - 1); cluster = fat_bmap_cluster(inode, cluster); if (cluster < 0) return cluster; else if (cluster) { *bmap = fat_clus_to_blknr(sbi, cluster) + offset; *mapped_blocks = sbi->sec_per_clus - offset; if (*mapped_blocks > last_block - sector) *mapped_blocks = last_block - sector; } return 0; } static int is_exceed_eof(struct inode *inode, sector_t sector, sector_t *last_block, int create) { struct super_block *sb = inode->i_sb; const unsigned long blocksize = sb->s_blocksize; const unsigned char blocksize_bits = sb->s_blocksize_bits; *last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits; if (sector >= *last_block) { if (!create) return 1; /* * ->mmu_private can access on only allocation path. * (caller must hold ->i_mutex) */ *last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1)) >> blocksize_bits; if (sector >= *last_block) return 1; } return 0; } int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, unsigned long *mapped_blocks, int create, bool from_bmap) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); sector_t last_block; *phys = 0; *mapped_blocks = 0; if (!is_fat32(sbi) && (inode->i_ino == MSDOS_ROOT_INO)) { if (sector < (sbi->dir_entries >> sbi->dir_per_block_bits)) { *phys = sector + sbi->dir_start; *mapped_blocks = 1; } return 0; } if (!from_bmap) { if (is_exceed_eof(inode, sector, &last_block, create)) return 0; } else { last_block = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); if (sector >= last_block) return 0; } return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks, phys); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_DISK_GROUPS_H #define _BCACHEFS_DISK_GROUPS_H #include "disk_groups_types.h" extern const struct bch_sb_field_ops bch_sb_field_ops_disk_groups; static inline unsigned disk_groups_nr(struct bch_sb_field_disk_groups *groups) { return groups ? (vstruct_end(&groups->field) - (void *) &groups->entries[0]) / sizeof(struct bch_disk_group) : 0; } struct target { enum { TARGET_NULL, TARGET_DEV, TARGET_GROUP, } type; union { unsigned dev; unsigned group; }; }; #define TARGET_DEV_START 1 #define TARGET_GROUP_START (256 + TARGET_DEV_START) static inline u16 dev_to_target(unsigned dev) { return TARGET_DEV_START + dev; } static inline u16 group_to_target(unsigned group) { return TARGET_GROUP_START + group; } static inline struct target target_decode(unsigned target) { if (target >= TARGET_GROUP_START) return (struct target) { .type = TARGET_GROUP, .group = target - TARGET_GROUP_START }; if (target >= TARGET_DEV_START) return (struct target) { .type = TARGET_DEV, .group = target - TARGET_DEV_START }; return (struct target) { .type = TARGET_NULL }; } const struct bch_devs_mask *bch2_target_to_mask(struct bch_fs *, unsigned); static inline struct bch_devs_mask target_rw_devs(struct bch_fs *c, enum bch_data_type data_type, u16 target) { struct bch_devs_mask devs = c->rw_devs[data_type]; const struct bch_devs_mask *t = bch2_target_to_mask(c, target); if (t) bitmap_and(devs.d, devs.d, t->d, BCH_SB_MEMBERS_MAX); return devs; } static inline bool bch2_target_accepts_data(struct bch_fs *c, enum bch_data_type data_type, u16 target) { struct bch_devs_mask rw_devs = target_rw_devs(c, data_type, target); return !bitmap_empty(rw_devs.d, BCH_SB_MEMBERS_MAX); } bool bch2_dev_in_target(struct bch_fs *, unsigned, unsigned); int bch2_disk_path_find(struct bch_sb_handle *, const char *); /* Exported for userspace bcachefs-tools: */ int bch2_disk_path_find_or_create(struct bch_sb_handle *, const char *); void bch2_disk_path_to_text(struct printbuf *, struct bch_fs *, unsigned); void bch2_disk_path_to_text_sb(struct printbuf *, struct bch_sb *, unsigned); void bch2_target_to_text(struct printbuf *out, struct bch_fs *, unsigned); int bch2_opt_target_parse(struct bch_fs *, const char *, u64 *, struct printbuf *); void bch2_opt_target_to_text(struct printbuf *, struct bch_fs *, struct bch_sb *, u64); #define bch2_opt_target (struct bch_opt_fn) { \ .parse = bch2_opt_target_parse, \ .to_text = bch2_opt_target_to_text, \ } int bch2_sb_disk_groups_to_cpu(struct bch_fs *); int __bch2_dev_group_set(struct bch_fs *, struct bch_dev *, const char *); int bch2_dev_group_set(struct bch_fs *, struct bch_dev *, const char *); const char *bch2_sb_validate_disk_groups(struct bch_sb *, struct bch_sb_field *); void bch2_disk_groups_to_text(struct printbuf *, struct bch_fs *); #endif /* _BCACHEFS_DISK_GROUPS_H */ |
| 8 9 6 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/time.h> #include <linux/gcd.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/timer.h> #include "pcm_local.h" /* * Timer functions */ void snd_pcm_timer_resolution_change(struct snd_pcm_substream *substream) { unsigned long rate, mult, fsize, l, post; struct snd_pcm_runtime *runtime = substream->runtime; mult = 1000000000; rate = runtime->rate; if (snd_BUG_ON(!rate)) return; l = gcd(mult, rate); mult /= l; rate /= l; fsize = runtime->period_size; if (snd_BUG_ON(!fsize)) return; l = gcd(rate, fsize); rate /= l; fsize /= l; post = 1; while ((mult * fsize) / fsize != mult) { mult /= 2; post *= 2; } if (rate == 0) { pcm_err(substream->pcm, "pcm timer resolution out of range (rate = %u, period_size = %lu)\n", runtime->rate, runtime->period_size); runtime->timer_resolution = -1; return; } runtime->timer_resolution = (mult * fsize / rate) * post; } static unsigned long snd_pcm_timer_resolution(struct snd_timer * timer) { struct snd_pcm_substream *substream; substream = timer->private_data; return substream->runtime ? substream->runtime->timer_resolution : 0; } static int snd_pcm_timer_start(struct snd_timer * timer) { struct snd_pcm_substream *substream; substream = snd_timer_chip(timer); substream->timer_running = 1; return 0; } static int snd_pcm_timer_stop(struct snd_timer * timer) { struct snd_pcm_substream *substream; substream = snd_timer_chip(timer); substream->timer_running = 0; return 0; } static const struct snd_timer_hardware snd_pcm_timer = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_SLAVE, .resolution = 0, .ticks = 1, .c_resolution = snd_pcm_timer_resolution, .start = snd_pcm_timer_start, .stop = snd_pcm_timer_stop, }; /* * Init functions */ static void snd_pcm_timer_free(struct snd_timer *timer) { struct snd_pcm_substream *substream = timer->private_data; substream->timer = NULL; } void snd_pcm_timer_init(struct snd_pcm_substream *substream) { struct snd_timer_id tid; struct snd_timer *timer; tid.dev_sclass = SNDRV_TIMER_SCLASS_NONE; tid.dev_class = SNDRV_TIMER_CLASS_PCM; tid.card = substream->pcm->card->number; tid.device = substream->pcm->device; tid.subdevice = (substream->number << 1) | (substream->stream & 1); if (snd_timer_new(substream->pcm->card, "PCM", &tid, &timer) < 0) return; sprintf(timer->name, "PCM %s %i-%i-%i", substream->stream == SNDRV_PCM_STREAM_CAPTURE ? "capture" : "playback", tid.card, tid.device, tid.subdevice); timer->hw = snd_pcm_timer; if (snd_device_register(timer->card, timer) < 0) { snd_device_free(timer->card, timer); return; } timer->private_data = substream; timer->private_free = snd_pcm_timer_free; substream->timer = timer; } void snd_pcm_timer_done(struct snd_pcm_substream *substream) { if (substream->timer) { snd_device_free(substream->pcm->card, substream->timer); substream->timer = NULL; } } |
| 112 26 112 112 98 |